diff --git a/doccano_client/cli/active_learning/__init__.py b/doccano_client/cli/active_learning/__init__.py
new file mode 100644
index 0000000..e69de29
diff --git a/doccano_client/cli/active_learning/languages.py b/doccano_client/cli/active_learning/languages.py
new file mode 100644
index 0000000..bd5937d
--- /dev/null
+++ b/doccano_client/cli/active_learning/languages.py
@@ -0,0 +1,35 @@
+# fastText embeddings
+# https://github.com/flairNLP/flair/blob/cebd2b1c81be4507f62e967f8a2e7701e332dbd3/resources/docs/embeddings/CLASSIC_WORD_EMBEDDINGS.md
+LANGUAGES = [
+    "en",  # English
+    "de",  # German
+    "nl",  # Dutch
+    "fr",  # French
+    "it",  # Italian
+    "es",  # Spanish
+    "pt",  # Portuguese
+    "ro",  # Romanian
+    "ca",  # Catalan
+    "sv",  # Swedish
+    "da",  # Danish
+    "no",  # Norwegian
+    "fi",  # Finnish
+    "pl",  # Polish
+    "cz",  # Czech
+    "sk",  # Slovak
+    "sl",  # Slovenian
+    "sr",  # Serbian
+    "hr",  # Croatian
+    "bg",  # Bulgarian
+    "ru",  # Russian
+    "ar",  # Arabic
+    "he",  # Hebrew
+    "tr",  # Turkish
+    "fa",  # Persian
+    "ja",  # Japanese
+    "ko",  # Korean
+    "zh",  # Chinese
+    "hi",  # Hindi
+    "id",  # Indonesian
+    "eu",  # Basque
+]
diff --git a/doccano_client/cli/active_learning/manager.py b/doccano_client/cli/active_learning/manager.py
new file mode 100644
index 0000000..cbd494e
--- /dev/null
+++ b/doccano_client/cli/active_learning/manager.py
@@ -0,0 +1,72 @@
+import time
+from typing import List, Literal, Optional, Tuple
+
+from flair.trainers import ModelTrainer
+from seqal.tagger import SequenceTagger
+from tqdm import tqdm
+
+from doccano_client import DoccanoClient
+
+from .preparation import DOCCANO_HOME, prepare_datasets
+from .strategies import get_query_strategy
+from .trainer import get_tagger_params, get_trainer_params
+
+
+def execute_one_iteration(
+    client: DoccanoClient,
+    project_id: int,
+    lang: str = "en",
+    query_strategy_name: Literal["LC", "MNLP"] = "MNLP",
+    transformer_model: Optional[str] = None,
+) -> Tuple[List[float], List[int]]:
+    print("Maybe downloading dataset...")
+    labeled_dataset, unlabeled_dataset = prepare_datasets(client, project_id, lang=lang)
+
+    # Prepare tagger
+    tagger_params = get_tagger_params(labeled_dataset, lang=lang, transformer_model=transformer_model)
+    tagger = SequenceTagger(**tagger_params)
+
+    # Prepare trainer
+    trainer = ModelTrainer(tagger, labeled_dataset)
+    trainer_params = get_trainer_params()
+
+    print("Training...")
+    model_dir = DOCCANO_HOME / str(project_id) / "models"
+    trainer.train(model_dir, **trainer_params)
+    print("Training completed.")
+
+    # Query unlabeled dataset
+    print("Calculating confidence scores...")
+    query_strategy = get_query_strategy(query_strategy_name)
+    scores = query_strategy(unlabeled_dataset.sentences, tagger)
+    print("Calculation completed.")
+    return scores, unlabeled_dataset.ids
+
+
+def execute_active_learning(
+    client: DoccanoClient,
+    project_id: int,
+    lang: str = "en",
+    query_strategy_name: Literal["LC", "MNLP"] = "MNLP",
+    transformer_model: Optional[str] = None,
+    train_frequency: int = 100,
+):
+    prev_completed = 0
+    while True:
+        progress = client.get_progress(project_id)
+        if progress.is_finished():
+            break
+        if progress.completed - prev_completed >= train_frequency:
+            prev_completed = progress.completed
+            scores, example_ids = execute_one_iteration(
+                client,
+                project_id=project_id,
+                lang=lang,
+                query_strategy_name=query_strategy_name,
+                transformer_model=transformer_model,
+            )
+            print("Update confidence scores...")
+            for score, example_id in tqdm(zip(scores, example_ids)):
+                client.update_example(project_id, example_id, meta={"confidence": score})
+            print("Update completed.")
+        time.sleep(10)
diff --git a/doccano_client/cli/active_learning/models.py b/doccano_client/cli/active_learning/models.py
new file mode 100644
index 0000000..941d12b
--- /dev/null
+++ b/doccano_client/cli/active_learning/models.py
@@ -0,0 +1,150 @@
+import json
+import pathlib
+from typing import Dict, Iterable, Iterator, List, Optional, Tuple
+
+from sklearn.model_selection import train_test_split
+
+from doccano_client.models.example import Example
+from doccano_client.models.label import Span
+
+
+class Examples:
+    filename = "examples.json"
+
+    def __init__(self, examples: Iterable[Example] = None):
+        if examples is None:
+            examples = []
+        self.items = {int(example.id): example for example in examples if example.id}
+
+    def __getitem__(self, example_id: Optional[int]) -> Example:
+        if example_id is None:
+            raise ValueError("Example ID is None.")
+        return self.items[example_id]
+
+    @property
+    def ids(self) -> List[int]:
+        return list(self.items.keys())
+
+    def save(self, project_dir: pathlib.Path):
+        path = project_dir / self.filename
+        with path.open("w") as f:
+            examples = [example.dict() for example in self.items.values()]
+            json.dump(examples, f)
+
+    @classmethod
+    def load(cls, project_dir: pathlib.Path):
+        path = project_dir / cls.filename
+        if not path.exists():
+            return cls()
+        with path.open() as f:
+            items = [Example.parse_obj(example) for example in json.load(f)]
+        examples = cls(items)
+        return examples
+
+    def confirm(self, example_id: Optional[int]):
+        if example_id is None:
+            return
+        self.items[example_id].is_confirmed = True
+
+    def filter_by(self, is_confirmed: bool) -> "Examples":
+        return Examples(example for example in self.items.values() if example.is_confirmed == is_confirmed)
+
+    def filter_by_ids(self, ids: Iterable[int]) -> "Examples":
+        return Examples(self.items[example_id] for example_id in ids)
+
+
+class Spans:
+    filename = "spans.json"
+
+    def __init__(self, spans: Dict[int, List[Span]] = None):
+        self.items = spans or {}
+
+    def __contains__(self, example_id: Optional[int]) -> bool:
+        if example_id is None:
+            return False
+        return example_id in self.items
+
+    def __getitem__(self, example_id: Optional[int]) -> List[Span]:
+        if example_id is None:
+            raise ValueError("Example ID is None.")
+        if example_id not in self.items:
+            return []
+        return self.items[example_id]
+
+    def add(self, example_id: Optional[int], spans: List[Span]):
+        if example_id is None:
+            return
+        self.items[example_id] = spans
+
+    def save(self, project_dir: pathlib.Path):
+        path = project_dir / self.filename
+        with path.open("w") as f:
+            spans = {example_id: [span.dict() for span in spans] for example_id, spans in self.items.items()}
+            json.dump(spans, f)
+
+    @classmethod
+    def load(cls, project_dir: pathlib.Path):
+        path = project_dir / cls.filename
+        if not path.exists():
+            return cls()
+        with path.open() as f:
+            items = json.load(f)
+        items = {int(example_id): [Span.parse_obj(span) for span in spans] for example_id, spans in items.items()}
+        spans = cls(items)
+        return spans
+
+    def filter_by(self, example_ids: List[int]) -> "Spans":
+        return Spans({example_id: self.items[example_id] for example_id in example_ids})
+
+
+class NERDataset:
+    def __init__(self, examples: Examples = None, spans: Spans = None):
+        self.examples = examples or Examples()
+        self.spans = spans or Spans()
+
+    def __iter__(self) -> Iterator[Tuple[Example, List[Span]]]:
+        for example_id in self.examples.ids:
+            yield self.examples[example_id], self.spans[example_id]
+
+    def split(self, test_size: float = 0.2, random_state: int = 42) -> Iterable["NERDataset"]:
+        train_ids, test_ids = train_test_split(self.examples.ids, test_size=test_size, random_state=random_state)
+        train_examples = self.examples.filter_by_ids(train_ids)
+        train_spans = self.spans.filter_by(train_ids)
+        test_examples = self.examples.filter_by_ids(test_ids)
+        test_spans = self.spans.filter_by(test_ids)
+        return NERDataset(train_examples, train_spans), NERDataset(test_examples, test_spans)
+
+    def save(self, project_dir: pathlib.Path):
+        self.examples.save(project_dir)
+        self.spans.save(project_dir)
+
+    @classmethod
+    def load(cls, project_dir: pathlib.Path):
+        examples = Examples.load(project_dir)
+        spans = Spans.load(project_dir)
+        return cls(examples, spans)
+
+    def add_spans(self, example_id: Optional[int], spans: List[Span]):
+        if example_id is None:
+            return
+        self.spans.add(example_id, spans)
+
+    def has_spans(self, example_id: Optional[int]) -> bool:
+        if example_id is None:
+            return False
+        return example_id in self.spans
+
+    def confirm(self, example_id: Optional[int]):
+        if example_id is None:
+            return
+        self.examples.confirm(example_id)
+
+    @property
+    def labeled(self) -> "NERDataset":
+        examples = self.examples.filter_by(is_confirmed=True)
+        spans = self.spans.filter_by(examples.ids)
+        return NERDataset(examples, spans)
+
+    @property
+    def unlabeled(self) -> "NERDataset":
+        return NERDataset(self.examples.filter_by(is_confirmed=False))
diff --git a/doccano_client/cli/active_learning/preparation.py b/doccano_client/cli/active_learning/preparation.py
new file mode 100644
index 0000000..7b65e80
--- /dev/null
+++ b/doccano_client/cli/active_learning/preparation.py
@@ -0,0 +1,122 @@
+import os
+import pathlib
+from typing import List
+
+import spacy
+from flair.data import Sentence, Token
+from flair.datasets import ColumnCorpus
+from spacy.training import offsets_to_biluo_tags
+
+from doccano_client import DoccanoClient
+from doccano_client.models.example import Example
+from doccano_client.models.label import Span
+
+from .models import Examples, NERDataset
+
+DOCCANO_HOME = pathlib.Path(os.path.expanduser(os.environ.get("DOCCANO_HOME", "~/doccano")))
+
+
+class UnlabeledDataset:
+    def __init__(self):
+        self.items = []
+
+    @property
+    def sentences(self):
+        return [sentence for _, sentence in self.items]
+
+    @property
+    def ids(self):
+        return [example_id for example_id, _ in self.items]
+
+    def add(self, example: Example, sentence: Sentence):
+        self.items.append((example.id, sentence))
+
+
+def download_dataset(client: DoccanoClient, project_id: int) -> NERDataset:
+    dataset_dir = DOCCANO_HOME / str(project_id) / "dataset"
+    if not dataset_dir.exists():
+        print(f"Downloading dataset for project {project_id}")
+        dataset_dir.mkdir(parents=True, exist_ok=True)
+        examples = Examples(client.list_examples(project_id))
+        dataset = NERDataset(examples)
+        dataset.save(dataset_dir)
+    else:
+        print(f"Loading dataset for project {project_id}")
+        dataset = NERDataset.load(dataset_dir)
+
+    for example in client.list_examples(project_id, is_confirmed=True):
+        if not dataset.has_spans(example.id):
+            spans = client.list_spans(project_id, example.id)  # type: ignore
+            dataset.add_spans(example.id, spans)
+            dataset.confirm(example.id)
+    dataset.save(dataset_dir)
+    return dataset
+
+
+def make_nlp(lang: str = "en"):
+    if lang == "cz":
+        lang = "cs"
+    nlp = spacy.blank(lang)
+    return nlp
+
+
+def prepare_datasets(client: DoccanoClient, project_id: int, lang: str = "en"):
+    # download dataset
+    dataset = download_dataset(client, project_id)
+
+    # split train/test dataset
+    train_dataset, test_dataset = dataset.labeled.split(test_size=0.5)
+
+    # convert dataset to conll format
+    nlp = make_nlp(lang)
+    save_dir = DOCCANO_HOME / str(project_id) / "dataset"
+    export_examples_to_conll(nlp, train_dataset, save_dir / "train.txt")
+    export_examples_to_conll(nlp, test_dataset, save_dir / "test.txt")
+
+    # load datasets for flair
+    labeled_dataset = load_labeled_dataset(save_dir)
+    unlabeled_dataset = load_unlabeled_dataset(nlp, dataset.unlabeled)
+    return labeled_dataset, unlabeled_dataset
+
+
+def convert_example_to_conll(nlp: spacy.Language, example: Example, spans: List[Span]):
+    doc = nlp(example.text)  # type: ignore
+    ents = [span.to_tuple() for span in spans]
+    tags = offsets_to_biluo_tags(doc, ents)  # type: ignore
+    for token, tag in zip(doc, tags):
+        tag = tag.replace("U-", "S-")
+        tag = tag.replace("L-", "E-")
+        yield f"{token.text}\t{tag}\n"
+
+
+def export_examples_to_conll(nlp: spacy.Language, dataset: NERDataset, path: pathlib.Path):
+    with path.open("w", encoding="utf-8") as f:
+        for example, spans in dataset:
+            lines = convert_example_to_conll(nlp, example, spans)
+            f.writelines(lines)
+            f.write("\n")
+
+
+def load_labeled_dataset(data_dir: pathlib.Path):
+    columns = {0: "text", 1: "ner"}
+    corpus = ColumnCorpus(
+        data_dir,
+        columns,
+        train_file="train.txt",
+        dev_file="test.txt",
+        test_file="test.txt",
+    )
+    return corpus
+
+
+def load_unlabeled_dataset(nlp: spacy.Language, dataset: NERDataset):
+    unlabeled_dataset = UnlabeledDataset()
+    for example, _ in dataset:
+        doc = nlp(example.text)  # type: ignore
+        sentence = Sentence()
+        for word in doc:
+            token = Token(text=word.text, start_position=word.idx, whitespace_after=word.whitespace_)
+            token.add_tag("ner", "O")
+            sentence.add_token(token)
+        unlabeled_dataset.add(example, sentence)
+    return unlabeled_dataset
diff --git a/doccano_client/cli/active_learning/strategies.py b/doccano_client/cli/active_learning/strategies.py
new file mode 100644
index 0000000..32e3207
--- /dev/null
+++ b/doccano_client/cli/active_learning/strategies.py
@@ -0,0 +1,33 @@
+from typing import List, Literal
+
+import numpy as np
+from flair.data import Sentence
+from seqal.tagger import SequenceTagger
+
+
+def least_confidence(
+    sentences: List[Sentence],
+    tagger: SequenceTagger,
+) -> np.ndarray:
+    log_probs = tagger.log_probability(sentences)
+    # scores = 1 - np.exp(log_probs)
+    scores = np.exp(log_probs)
+    return scores
+
+
+def maximum_normalized_log_probability(
+    sentences: List[Sentence],
+    tagger: SequenceTagger,
+) -> np.ndarray:
+    log_probs = tagger.log_probability(sentences)
+    lengths = np.array([len(sent) for sent in sentences])
+    normed_log_probs = log_probs / lengths
+    return normed_log_probs
+
+
+def get_query_strategy(query_strategy: Literal["MNLP", "LC"] = "MNLP"):
+    if query_strategy == "LC":
+        return least_confidence
+    elif query_strategy == "MNLP":
+        return maximum_normalized_log_probability
+    raise ValueError(f"Query strategy {query_strategy} is not available")
diff --git a/doccano_client/cli/active_learning/trainer.py b/doccano_client/cli/active_learning/trainer.py
new file mode 100644
index 0000000..553e6b2
--- /dev/null
+++ b/doccano_client/cli/active_learning/trainer.py
@@ -0,0 +1,52 @@
+from typing import Any, Dict
+
+from flair.data import Corpus
+from flair.embeddings import TransformerWordEmbeddings, WordEmbeddings
+
+from .languages import LANGUAGES
+
+
+def get_tagger_params(
+    corpus: Corpus,
+    lang: str = "en",
+    transformer_model: str = None,
+    hidden_size: int = 256,
+    use_rnn: bool = False,
+    use_crf: bool = True,
+    **kwargs,
+) -> Dict[str, Any]:
+    if lang not in LANGUAGES and transformer_model is None:
+        raise ValueError(f"Language {lang} is not available")
+
+    if transformer_model:
+        embeddings = TransformerWordEmbeddings(transformer_model)
+    else:
+        embeddings = WordEmbeddings("glove")
+
+    tagger_params = {
+        "tag_type": "ner",
+        "tag_dictionary": corpus.make_tag_dictionary(tag_type="ner"),
+        "embeddings": embeddings,
+        "hidden_size": hidden_size,
+        "use_rnn": use_rnn,
+        "use_crf": use_crf,
+    }
+    return tagger_params
+
+
+def get_trainer_params(
+    max_epochs: int = 10,
+    patience: int = 3,
+    learning_rate: float = 0.1,
+    mini_batch_size: int = 32,
+    shuffle: bool = True,
+    **kwargs,
+) -> Dict[str, Any]:
+    trainer_params = {
+        "max_epochs": max_epochs,
+        "learning_rate": learning_rate,
+        "mini_batch_size": mini_batch_size,
+        "patience": patience,
+        "shuffle": shuffle,
+    }
+    return trainer_params
diff --git a/doccano_client/cli/commands.py b/doccano_client/cli/commands.py
index 03ef7ff..22e3043 100644
--- a/doccano_client/cli/commands.py
+++ b/doccano_client/cli/commands.py
@@ -7,6 +7,7 @@
 from pathlib import Path
 
 from doccano_client import DoccanoClient
+from doccano_client.cli.active_learning.languages import LANGUAGES
 from doccano_client.cli.estimators import select_estimator_class
 from doccano_client.cli.usecases import build_annotator
 
@@ -46,6 +47,21 @@ def command_predict(args):
     client.logout()
 
 
+def command_teach(args):
+    from .active_learning.manager import execute_active_learning
+
+    client = command_login(args)
+    execute_active_learning(
+        client,
+        project_id=args.project,
+        lang=args.lang,
+        query_strategy_name=args.query_strategy,
+        transformer_model=args.transformer_model,
+        train_frequency=args.train_frequency,
+    )
+    client.logout()
+
+
 def command_help(args):
     print(parser.parse_args([args.command, "--help"]))
 
@@ -70,6 +86,30 @@ def main():
     parser_predict.add_argument("--framework", default="spacy", choices=["spacy"], help="framework to predict output")
     parser_predict.set_defaults(handler=command_predict)
 
+    # Create a parser for active learning
+    parser_teach = subparsers.add_parser("teach", help="see `teach -h`")
+    parser_teach.add_argument("--task", type=str, choices=["ner"], required=True, help="task name")
+    parser_teach.add_argument("--project", type=int, required=True, help="project id")
+    parser_teach.add_argument("--lang", type=str, choices=LANGUAGES, default="en", required=True, help="language code")
+    parser_teach.add_argument(
+        "--query_strategy",
+        type=str,
+        choices=["LC", "MNLP"],
+        default="MNLP",
+        required=True,
+        help="query strategy. LC is least confidence, MNLP is maximum normalized log-probability.",
+    )
+    parser_teach.add_argument(
+        "--transformer_model", type=str, required=False, help="transformer model name(e.g. bert-base-uncased)"
+    )
+    parser_teach.add_argument(
+        "--train_frequency",
+        type=int,
+        default=50,
+        help="How often to train during annotation (number of confirmed examples)",
+    )
+    parser_teach.set_defaults(handler=command_teach)
+
     # Create a parser for help.
     parser_help = subparsers.add_parser("help", help="see `help -h`")
     parser_help.add_argument("command", help="command name which help is shown")
diff --git a/doccano_client/models/label.py b/doccano_client/models/label.py
index cfa3822..5ddc116 100644
--- a/doccano_client/models/label.py
+++ b/doccano_client/models/label.py
@@ -34,6 +34,9 @@ def check_start_offset_is_less_than_end_offset(cls, values):
             raise ValueError("start_offset must be less than end_offset.")
         return values
 
+    def to_tuple(self) -> tuple:
+        return self.start_offset, self.end_offset, self.label
+
 
 class Relation(Label):
     from_id: int
diff --git a/doccano_client/models/metrics.py b/doccano_client/models/metrics.py
index 3261455..d03c45a 100644
--- a/doccano_client/models/metrics.py
+++ b/doccano_client/models/metrics.py
@@ -22,6 +22,9 @@ class Progress(BaseModel):
     remaining: int
     completed: int
 
+    def is_finished(self) -> bool:
+        return self.remaining == 0
+
 
 class MemberProgress(BaseModel):
     username: str
diff --git a/docs/cli.md b/docs/cli.md
index c800262..0c8f97d 100644
--- a/docs/cli.md
+++ b/docs/cli.md
@@ -71,3 +71,34 @@ docli predict asr \
   --project <project_id> \
   --model base
 ```
+
+## Active Learning
+
+To use this feature, you need to install doccano-client as follows:
+
+```bash
+pip install doccano-client[al]
+```
+
+First, you need to login to doccano:
+
+```bash
+docli login \
+  --host http://127.0.0.1:8000 \
+  --username admin \
+  --password password
+```
+
+Then, you can use active learning as follows:
+
+```bash
+docli teach \
+  --task <ner> \
+  --project <project_id> \
+  --lang [en] \
+  --query_strategy [MNLP] \
+  --train_frequency [50] \
+  --transformer_model [bert-base-uncased]
+```
+
+Currently, only `ner` is supported as a task.
diff --git a/poetry.lock b/poetry.lock
index 8b40419..d300fc0 100644
--- a/poetry.lock
+++ b/poetry.lock
@@ -39,12 +39,27 @@ name = "blis"
 version = "0.9.1"
 description = "The Blis BLAS-like linear algebra library, as a self-contained C-extension."
 category = "main"
-optional = true
+optional = false
 python-versions = "*"
 
 [package.dependencies]
 numpy = ">=1.15.0"
 
+[[package]]
+name = "bpemb"
+version = "0.3.4"
+description = "Byte-pair embeddings in 275 languages"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+gensim = "*"
+numpy = "*"
+requests = "*"
+sentencepiece = "*"
+tqdm = "*"
+
 [[package]]
 name = "cached-property"
 version = "1.5.2"
@@ -58,7 +73,7 @@ name = "catalogue"
 version = "2.0.8"
 description = "Super lightweight function registries for your library"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [[package]]
@@ -104,19 +119,53 @@ name = "confection"
 version = "0.0.1"
 description = "The sweetest config system for Python"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
 pydantic = ">=1.7.4,<1.8 || >1.8,<1.8.1 || >1.8.1,<1.10.0"
 srsly = ">=2.4.0,<3.0.0"
 
+[[package]]
+name = "conllu"
+version = "4.5.2"
+description = "CoNLL-U Parser parses a CoNLL-U formatted string into a nested python dictionary"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[[package]]
+name = "contourpy"
+version = "1.0.5"
+description = "Python library for calculating contours of 2D quadrilateral grids"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+numpy = ">=1.16"
+
+[package.extras]
+test-no-codebase = ["pillow", "matplotlib", "pytest"]
+test-minimal = ["pytest"]
+test = ["isort", "flake8", "pillow", "matplotlib", "pytest"]
+docs = ["sphinx-rtd-theme", "sphinx", "docutils (<0.18)"]
+bokeh = ["selenium", "bokeh"]
+
+[[package]]
+name = "cycler"
+version = "0.11.0"
+description = "Composable style cycles"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "cymem"
 version = "2.0.6"
 description = "Manage calls to calloc/free through Cython"
 category = "main"
-optional = true
+optional = false
 python-versions = "*"
 
 [[package]]
@@ -143,6 +192,20 @@ typing-inspect = ">=0.4.0"
 [package.extras]
 dev = ["pytest (>=6.2.3)", "ipython", "mypy (>=0.710)", "hypothesis", "portray", "flake8", "simplejson", "types-dataclasses"]
 
+[[package]]
+name = "deprecated"
+version = "1.2.13"
+description = "Python @deprecated decorator to deprecate old python classes, functions or methods."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
+[package.dependencies]
+wrapt = ">=1.10,<2"
+
+[package.extras]
+dev = ["tox", "bump2version (<1)", "sphinx (<2)", "importlib-metadata (<3)", "importlib-resources (<4)", "configparser (<5)", "sphinxcontrib-websupport (<2)", "zipp (<2)", "PyTest (<5)", "PyTest-Cov (<2.6)", "pytest", "pytest-cov"]
+
 [[package]]
 name = "ffmpeg-python"
 version = "0.2.0"
@@ -162,13 +225,48 @@ name = "filelock"
 version = "3.8.0"
 description = "A platform independent file lock."
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.7"
 
 [package.extras]
 docs = ["furo (>=2022.6.21)", "sphinx (>=5.1.1)", "sphinx-autodoc-typehints (>=1.19.1)"]
 testing = ["covdefaults (>=2.2)", "coverage (>=6.4.2)", "pytest (>=7.1.2)", "pytest-cov (>=3)", "pytest-timeout (>=2.1)"]
 
+[[package]]
+name = "flair"
+version = "0.10"
+description = "A very simple framework for state-of-the-art NLP"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+bpemb = ">=0.3.2"
+conllu = ">=4.0"
+deprecated = ">=1.2.4"
+ftfy = "*"
+gdown = "3.12.2"
+gensim = ">=3.4.0"
+huggingface-hub = "*"
+janome = "*"
+konoha = ">=4.0.0,<5.0.0"
+langdetect = "*"
+lxml = "*"
+matplotlib = ">=2.2.3"
+more-itertools = ">=8.8.0,<8.9.0"
+mpld3 = "0.3"
+python-dateutil = ">=2.6.1"
+regex = "*"
+scikit-learn = ">=0.21.3"
+segtok = ">=1.5.7"
+sentencepiece = "0.1.95"
+sqlitedict = ">=1.6.0"
+tabulate = "*"
+torch = ">=1.5.0,<1.8 || >1.8"
+tqdm = ">=4.26.0"
+transformers = ">=4.0.0"
+wikipedia-api = "*"
+
 [[package]]
 name = "flake8"
 version = "5.0.4"
@@ -182,6 +280,39 @@ mccabe = ">=0.7.0,<0.8.0"
 pycodestyle = ">=2.9.0,<2.10.0"
 pyflakes = ">=2.5.0,<2.6.0"
 
+[[package]]
+name = "fonttools"
+version = "4.37.4"
+description = "Tools to manipulate font files"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+all = ["fs (>=2.2.0,<3)", "lxml (>=4.0,<5)", "zopfli (>=0.1.4)", "lz4 (>=1.7.4.2)", "matplotlib", "sympy", "skia-pathops (>=0.5.0)", "uharfbuzz (>=0.23.0)", "brotlicffi (>=0.8.0)", "scipy", "brotli (>=1.0.1)", "munkres", "unicodedata2 (>=14.0.0)", "xattr"]
+graphite = ["lz4 (>=1.7.4.2)"]
+interpolatable = ["scipy", "munkres"]
+lxml = ["lxml (>=4.0,<5)"]
+pathops = ["skia-pathops (>=0.5.0)"]
+plot = ["matplotlib"]
+repacker = ["uharfbuzz (>=0.23.0)"]
+symfont = ["sympy"]
+type1 = ["xattr"]
+ufo = ["fs (>=2.2.0,<3)"]
+unicode = ["unicodedata2 (>=14.0.0)"]
+woff = ["zopfli (>=0.1.4)", "brotlicffi (>=0.8.0)", "brotli (>=1.0.1)"]
+
+[[package]]
+name = "ftfy"
+version = "6.1.1"
+description = "Fixes mojibake and other problems with Unicode, after the fact"
+category = "main"
+optional = false
+python-versions = ">=3.7,<4"
+
+[package.dependencies]
+wcwidth = ">=0.2.5"
+
 [[package]]
 name = "future"
 version = "0.18.2"
@@ -190,6 +321,39 @@ category = "main"
 optional = false
 python-versions = ">=2.6, !=3.0.*, !=3.1.*, !=3.2.*"
 
+[[package]]
+name = "gdown"
+version = "3.12.2"
+description = "Google Drive direct download of big files."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+filelock = "*"
+requests = {version = "*", extras = ["socks"]}
+six = "*"
+tqdm = "*"
+
+[[package]]
+name = "gensim"
+version = "4.2.0"
+description = "Python framework for fast Vector Space Modelling"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
+[package.dependencies]
+numpy = ">=1.17.0"
+scipy = ">=0.18.1"
+smart-open = ">=1.8.1"
+
+[package.extras]
+distributed = ["Pyro4 (>=4.27)"]
+docs = ["pytest", "pytest-cov", "mock", "cython", "testfixtures", "pyemd", "nmslib", "Pyro4 (>=4.27)", "visdom (>0.1.8.7)", "sphinx", "sphinx-gallery", "sphinxcontrib.programoutput", "sphinxcontrib-napoleon", "matplotlib", "memory-profiler", "annoy", "pyro4", "nltk", "statsmodels", "pandas"]
+test = ["pytest", "pytest-cov", "mock", "cython", "testfixtures", "pyemd", "nmslib", "visdom (>0.1.8.7)"]
+test-win = ["pytest", "pytest-cov", "mock", "cython", "testfixtures", "pyemd", "nmslib"]
+
 [[package]]
 name = "ghp-import"
 version = "2.1.0"
@@ -220,7 +384,7 @@ name = "huggingface-hub"
 version = "0.9.1"
 description = "Client library to download and publish models, datasets and other repos on the huggingface.co hub"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.7.0"
 
 [package.dependencies]
@@ -286,6 +450,14 @@ requirements_deprecated_finder = ["pipreqs", "pip-api"]
 colors = ["colorama (>=0.4.3,<0.5.0)"]
 plugins = ["setuptools"]
 
+[[package]]
+name = "janome"
+version = "0.4.2"
+description = "Japanese morphological analysis engine."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "jinja2"
 version = "3.1.2"
@@ -300,17 +472,83 @@ MarkupSafe = ">=2.0"
 [package.extras]
 i18n = ["Babel (>=2.7)"]
 
+[[package]]
+name = "joblib"
+version = "1.2.0"
+description = "Lightweight pipelining with Python functions"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "kiwisolver"
+version = "1.4.4"
+description = "A fast implementation of the Cassowary constraint solver"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[[package]]
+name = "konoha"
+version = "4.6.3"
+description = "A tiny sentence/word tokenizer for Japanese text written in Python"
+category = "main"
+optional = false
+python-versions = ">=3.6.1,<4.0.0"
+
+[package.dependencies]
+overrides = ">=3.0.0,<4.0.0"
+
+[package.extras]
+janome = ["janome (>=0.3.10,<0.4.0)"]
+all = ["janome (>=0.3.10,<0.4.0)", "natto-py (>=0.9.0,<0.10.0)", "kytea (>=0.1.4,<0.2.0)", "sentencepiece (>=0.1.85,<0.2.0)", "sudachipy (==0.4.9)", "boto3 (>=1.11.0,<2.0.0)", "fastapi (>=0.54.1,<0.55.0)", "uvicorn (>=0.11.5,<0.12.0)", "sudachidict-core (>=20200330,<20200331)", "nagisa (>=0.2.7,<0.3.0)"]
+all_with_integrations = ["janome (>=0.3.10,<0.4.0)", "natto-py (>=0.9.0,<0.10.0)", "kytea (>=0.1.4,<0.2.0)", "sentencepiece (>=0.1.85,<0.2.0)", "sudachipy (==0.4.9)", "boto3 (>=1.11.0,<2.0.0)", "allennlp (>=1.3.0,<2.0.0)", "fastapi (>=0.54.1,<0.55.0)", "uvicorn (>=0.11.5,<0.12.0)", "sudachidict-core (>=20200330,<20200331)", "nagisa (>=0.2.7,<0.3.0)"]
+mecab = ["natto-py (>=0.9.0,<0.10.0)"]
+kytea = ["kytea (>=0.1.4,<0.2.0)"]
+sentencepiece = ["sentencepiece (>=0.1.85,<0.2.0)"]
+sudachi = ["sudachipy (==0.4.9)", "sudachidict-core (>=20200330,<20200331)"]
+remote = ["boto3 (>=1.11.0,<2.0.0)"]
+allennlp = ["allennlp (>=1.3.0,<2.0.0)"]
+server = ["fastapi (>=0.54.1,<0.55.0)", "uvicorn (>=0.11.5,<0.12.0)"]
+docs = ["sphinx (>=3.1.1,<4.0.0)", "sphinx_rtd_theme (>=0.4.3,<0.5.0)"]
+nagisa = ["nagisa (>=0.2.7,<0.3.0)"]
+
 [[package]]
 name = "langcodes"
 version = "3.3.0"
 description = "Tools for labeling human languages with IETF language tags"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.extras]
 data = ["language-data (>=1.1,<2.0)"]
 
+[[package]]
+name = "langdetect"
+version = "1.0.9"
+description = "Language detection library ported from Google's language-detection."
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+six = "*"
+
+[[package]]
+name = "lxml"
+version = "4.9.1"
+description = "Powerful and Pythonic XML processing library combining libxml2/libxslt with the ElementTree API."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*, != 3.4.*"
+
+[package.extras]
+cssselect = ["cssselect (>=0.7)"]
+html5 = ["html5lib"]
+htmlsoup = ["beautifulsoup4"]
+source = ["Cython (>=0.29.7)"]
+
 [[package]]
 name = "markdown"
 version = "3.3.7"
@@ -372,6 +610,26 @@ python-versions = "*"
 [package.dependencies]
 marshmallow = ">=2.0.0"
 
+[[package]]
+name = "matplotlib"
+version = "3.6.1"
+description = "Python plotting package"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+contourpy = ">=1.0.1"
+cycler = ">=0.10"
+fonttools = ">=4.22.0"
+kiwisolver = ">=1.0.1"
+numpy = ">=1.19"
+packaging = ">=20.0"
+pillow = ">=6.2.0"
+pyparsing = ">=2.2.1"
+python-dateutil = ">=2.7"
+setuptools_scm = ">=7"
+
 [[package]]
 name = "mccabe"
 version = "0.7.0"
@@ -510,6 +768,22 @@ python-versions = ">=3.7"
 griffe = ">=0.11.1"
 mkdocstrings = ">=0.19"
 
+[[package]]
+name = "more-itertools"
+version = "8.8.0"
+description = "More routines for operating on iterables, beyond itertools"
+category = "main"
+optional = false
+python-versions = ">=3.5"
+
+[[package]]
+name = "mpld3"
+version = "0.3"
+description = "D3 Viewer for Matplotlib"
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "mslex"
 version = "0.3.0"
@@ -531,7 +805,7 @@ name = "murmurhash"
 version = "1.0.8"
 description = "Cython bindings for MurmurHash"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [[package]]
@@ -565,9 +839,17 @@ name = "numpy"
 version = "1.23.3"
 description = "NumPy is the fundamental package for array computing with Python."
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.8"
 
+[[package]]
+name = "overrides"
+version = "3.1.0"
+description = "A decorator to automatically detect mismatch when overriding a method."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "packaging"
 version = "21.3"
@@ -603,7 +885,7 @@ name = "pathy"
 version = "0.6.2"
 description = "pathlib.Path subclasses for local and cloud bucket storage"
 category = "main"
-optional = true
+optional = false
 python-versions = ">= 3.6"
 
 [package.dependencies]
@@ -616,6 +898,18 @@ s3 = ["boto3"]
 gcs = ["google-cloud-storage (>=1.26.0,<2.0.0)"]
 all = ["typer-cli", "mock", "pytest-coverage", "pytest", "boto3", "google-cloud-storage (>=1.26.0,<2.0.0)"]
 
+[[package]]
+name = "pillow"
+version = "9.2.0"
+description = "Python Imaging Library (Fork)"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+docs = ["furo", "olefile", "sphinx (>=2.4)", "sphinx-copybutton", "sphinx-issues (>=3.0.1)", "sphinx-removed-in", "sphinxext-opengraph"]
+tests = ["check-manifest", "coverage", "defusedxml", "markdown2", "olefile", "packaging", "pyroma", "pytest", "pytest-cov", "pytest-timeout"]
+
 [[package]]
 name = "platformdirs"
 version = "2.5.2"
@@ -645,7 +939,7 @@ name = "preshed"
 version = "3.0.7"
 description = "Cython hash table that trusts the keys are pre-hashed"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
@@ -747,6 +1041,14 @@ python-versions = "*"
 flake8 = "5.0.4"
 tomli = {version = "*", markers = "python_version < \"3.11\""}
 
+[[package]]
+name = "pysocks"
+version = "1.7.1"
+description = "A Python SOCKS client module. See https://github.com/Anorov/PySocks for more information."
+category = "main"
+optional = false
+python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*, !=3.3.*"
+
 [[package]]
 name = "pytest"
 version = "7.1.3"
@@ -771,7 +1073,7 @@ testing = ["argcomplete", "hypothesis (>=3.56)", "mock", "nose", "pygments (>=2.
 name = "python-dateutil"
 version = "2.8.2"
 description = "Extensions to the standard Python datetime module"
-category = "dev"
+category = "main"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,>=2.7"
 
@@ -810,7 +1112,7 @@ name = "regex"
 version = "2022.9.13"
 description = "Alternative regular expression module, to replace re."
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [[package]]
@@ -825,6 +1127,7 @@ python-versions = ">=3.7, <4"
 certifi = ">=2017.4.17"
 charset-normalizer = ">=2,<3"
 idna = ">=2.5,<4"
+PySocks = {version = ">=1.5.6,<1.5.7 || >1.5.7", optional = true, markers = "extra == \"socks\""}
 urllib3 = ">=1.21.1,<1.27"
 
 [package.extras]
@@ -857,11 +1160,97 @@ urllib3 = ">=1.25.10"
 [package.extras]
 tests = ["pytest (>=7.0.0)", "coverage (>=6.0.0)", "pytest-cov", "pytest-asyncio", "pytest-localserver", "flake8", "types-mock", "types-requests", "mypy"]
 
+[[package]]
+name = "scikit-learn"
+version = "1.1.2"
+description = "A set of python modules for machine learning and data mining"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+joblib = ">=1.0.0"
+numpy = ">=1.17.3"
+scipy = ">=1.3.2"
+threadpoolctl = ">=2.0.0"
+
+[package.extras]
+tests = ["numpydoc (>=1.2.0)", "pyamg (>=4.0.0)", "mypy (>=0.961)", "black (>=22.3.0)", "flake8 (>=3.8.2)", "pytest-cov (>=2.9.0)", "pytest (>=5.0.1)", "pandas (>=1.0.5)", "scikit-image (>=0.16.2)", "matplotlib (>=3.1.2)"]
+examples = ["seaborn (>=0.9.0)", "pandas (>=1.0.5)", "scikit-image (>=0.16.2)", "matplotlib (>=3.1.2)"]
+docs = ["sphinxext-opengraph (>=0.4.2)", "sphinx-prompt (>=1.3.0)", "Pillow (>=7.1.2)", "numpydoc (>=1.2.0)", "sphinx-gallery (>=0.7.0)", "sphinx (>=4.0.1)", "memory-profiler (>=0.57.0)", "seaborn (>=0.9.0)", "pandas (>=1.0.5)", "scikit-image (>=0.16.2)", "matplotlib (>=3.1.2)"]
+benchmark = ["memory-profiler (>=0.57.0)", "pandas (>=1.0.5)", "matplotlib (>=3.1.2)"]
+
+[[package]]
+name = "scipy"
+version = "1.9.2"
+description = "Fundamental algorithms for scientific computing in Python"
+category = "main"
+optional = false
+python-versions = ">=3.8"
+
+[package.dependencies]
+numpy = ">=1.18.5,<1.26.0"
+
+[package.extras]
+test = ["pytest", "pytest-cov", "pytest-xdist", "asv", "mpmath", "gmpy2", "threadpoolctl", "scikit-umfpack"]
+doc = ["sphinx (!=4.1.0)", "pydata-sphinx-theme (==0.9.0)", "sphinx-panels (>=0.5.2)", "matplotlib (>2)", "numpydoc", "sphinx-tabs"]
+dev = ["mypy", "typing-extensions", "pycodestyle", "flake8"]
+
+[[package]]
+name = "segtok"
+version = "1.5.11"
+description = "sentence segmentation and word tokenization tools"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+regex = "*"
+
+[[package]]
+name = "sentencepiece"
+version = "0.1.95"
+description = "SentencePiece python wrapper"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "seqal"
+version = "0.3.4"
+description = "Sequence labeling active learning framework for Python"
+category = "main"
+optional = false
+python-versions = ">=3.8,<4.0"
+
+[package.dependencies]
+flair = "0.10"
+scipy = ">=1.8.0,<2.0.0"
+spacy = ">=3.4.1,<4.0.0"
+torch = ">=1.10.0,<2.0.0"
+
+[[package]]
+name = "setuptools-scm"
+version = "7.0.5"
+description = "the blessed package to manage your versions by scm tags"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.dependencies]
+packaging = ">=20.0"
+tomli = ">=1.0.0"
+typing-extensions = "*"
+
+[package.extras]
+test = ["pytest (>=6.2)", "virtualenv (>20)"]
+toml = ["setuptools (>=42)"]
+
 [[package]]
 name = "six"
 version = "1.16.0"
 description = "Python 2 and 3 compatibility utilities"
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=2.7, !=3.0.*, !=3.1.*, !=3.2.*"
 
@@ -870,7 +1259,7 @@ name = "smart-open"
 version = "5.2.1"
 description = "Utils for streaming large files (S3, HDFS, GCS, Azure Blob Storage, gzip, bz2...)"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6,<4.0"
 
 [package.extras]
@@ -887,7 +1276,7 @@ name = "spacy"
 version = "3.4.1"
 description = "Industrial-strength Natural Language Processing (NLP) in Python"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
@@ -949,7 +1338,7 @@ name = "spacy-legacy"
 version = "3.0.10"
 description = "Legacy registered functions for spaCy backwards compatibility"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [[package]]
@@ -957,7 +1346,7 @@ name = "spacy-loggers"
 version = "1.0.3"
 description = "Logging utilities for SpaCy"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
@@ -1007,17 +1396,36 @@ cuda90 = ["cupy-cuda90 (>=5.0.0b4)"]
 cuda91 = ["cupy-cuda91 (>=5.0.0b4)"]
 cuda92 = ["cupy-cuda92 (>=5.0.0b4)"]
 
+[[package]]
+name = "sqlitedict"
+version = "2.0.0"
+description = "Persistent dict in Python, backed up by sqlite3 and pickle, multithread-safe."
+category = "main"
+optional = false
+python-versions = "*"
+
 [[package]]
 name = "srsly"
 version = "2.4.4"
 description = "Modern high-performance serialization utilities for Python"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
 catalogue = ">=2.0.3,<2.1.0"
 
+[[package]]
+name = "tabulate"
+version = "0.9.0"
+description = "Pretty-print tabular data"
+category = "main"
+optional = false
+python-versions = ">=3.7"
+
+[package.extras]
+widechars = ["wcwidth"]
+
 [[package]]
 name = "taskipy"
 version = "1.10.3"
@@ -1037,7 +1445,7 @@ name = "thinc"
 version = "8.1.1"
 description = "A refreshing functional take on deep learning, compatible with your favorite libraries"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
@@ -1072,12 +1480,20 @@ mxnet = ["mxnet (>=1.5.1,<1.6.0)"]
 tensorflow = ["tensorflow (>=2.0.0,<2.6.0)"]
 torch = ["torch (>=1.6.0)"]
 
+[[package]]
+name = "threadpoolctl"
+version = "3.1.0"
+description = "threadpoolctl"
+category = "main"
+optional = false
+python-versions = ">=3.6"
+
 [[package]]
 name = "tokenizers"
 version = "0.12.1"
 description = "Fast and Customizable Tokenizers"
 category = "main"
-optional = true
+optional = false
 python-versions = "*"
 
 [package.extras]
@@ -1088,7 +1504,7 @@ testing = ["pytest", "requests", "numpy", "datasets"]
 name = "tomli"
 version = "2.0.1"
 description = "A lil' TOML parser"
-category = "dev"
+category = "main"
 optional = false
 python-versions = ">=3.7"
 
@@ -1097,7 +1513,7 @@ name = "torch"
 version = "1.12.1"
 description = "Tensors and Dynamic neural networks in Python with strong GPU acceleration"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.7.0"
 
 [package.dependencies]
@@ -1108,7 +1524,7 @@ name = "tqdm"
 version = "4.64.1"
 description = "Fast, Extensible Progress Meter"
 category = "main"
-optional = true
+optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,>=2.7"
 
 [package.dependencies]
@@ -1125,7 +1541,7 @@ name = "transformers"
 version = "4.21.3"
 description = "State-of-the-art Machine Learning for JAX, PyTorch and TensorFlow"
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.7.0"
 
 [package.dependencies]
@@ -1186,7 +1602,7 @@ name = "typer"
 version = "0.4.2"
 description = "Typer, build great CLIs. Easy to code. Based on Python type hints."
 category = "main"
-optional = true
+optional = false
 python-versions = ">=3.6"
 
 [package.dependencies]
@@ -1269,7 +1685,7 @@ name = "wasabi"
 version = "0.10.1"
 description = "A lightweight console printing and formatting toolkit"
 category = "main"
-optional = true
+optional = false
 python-versions = "*"
 
 [[package]]
@@ -1283,11 +1699,30 @@ python-versions = ">=3.6"
 [package.extras]
 watchmedo = ["PyYAML (>=3.10)"]
 
+[[package]]
+name = "wcwidth"
+version = "0.2.5"
+description = "Measures the displayed width of unicode strings in a terminal"
+category = "main"
+optional = false
+python-versions = "*"
+
+[[package]]
+name = "wikipedia-api"
+version = "0.5.4"
+description = "Python Wrapper for Wikipedia"
+category = "main"
+optional = false
+python-versions = "*"
+
+[package.dependencies]
+requests = "*"
+
 [[package]]
 name = "wrapt"
 version = "1.14.1"
 description = "Module for decorators, wrappers and monkey patching."
-category = "dev"
+category = "main"
 optional = false
 python-versions = "!=3.0.*,!=3.1.*,!=3.2.*,!=3.3.*,!=3.4.*,>=2.7"
 
@@ -1322,12 +1757,13 @@ whisper = ["ffmpeg-python", "tqdm"]
 [metadata]
 lock-version = "1.1"
 python-versions = "^3.8"
-content-hash = "1adf7f2ae26bfd5204c3d7002c7a16bfa45f4cd0e8722e538ed17c65bc24fd45"
+content-hash = "9eccff9b94ba2b7eb61c7cb5b8befe35cda83b30d23332128fef797765a41c17"
 
 [metadata.files]
 attrs = []
 black = []
 blis = []
+bpemb = []
 cached-property = []
 catalogue = []
 certifi = []
@@ -1338,6 +1774,9 @@ click = [
 ]
 colorama = []
 confection = []
+conllu = []
+contourpy = []
+cycler = []
 cymem = [
     {file = "cymem-2.0.6-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:700540b68e96a7056d0691d467df2bbaaf0934a3e6fe2383669998cbee19580a"},
     {file = "cymem-2.0.6-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:a261f51796a2705f3900ed22b8442519a0f230f50a816fb5bd89cb9b027dc5ac"},
@@ -1361,10 +1800,16 @@ cymem = [
 ]
 darglint = []
 dataclasses-json = []
+deprecated = []
 ffmpeg-python = []
 filelock = []
+flair = []
 flake8 = []
+fonttools = []
+ftfy = []
 future = []
+gdown = []
+gensim = []
 ghp-import = []
 griffe = []
 huggingface-hub = []
@@ -1378,14 +1823,20 @@ isort = [
     {file = "isort-5.10.1-py3-none-any.whl", hash = "sha256:6f62d78e2f89b4500b080fe3a81690850cd254227f27f75c3a0c491a1f351ba7"},
     {file = "isort-5.10.1.tar.gz", hash = "sha256:e8443a5e7a020e9d7f97f1d7d9cd17c88bcb3bc7e218bf9cf5095fe550be2951"},
 ]
+janome = []
 jinja2 = [
     {file = "Jinja2-3.1.2-py3-none-any.whl", hash = "sha256:6088930bfe239f0e6710546ab9c19c9ef35e29792895fed6e6e31a023a182a61"},
     {file = "Jinja2-3.1.2.tar.gz", hash = "sha256:31351a702a408a9e7595a8fc6150fc3f43bb6bf7e319770cbc0db9df9437e852"},
 ]
+joblib = []
+kiwisolver = []
+konoha = []
 langcodes = [
     {file = "langcodes-3.3.0-py3-none-any.whl", hash = "sha256:4d89fc9acb6e9c8fdef70bcdf376113a3db09b67285d9e1d534de6d8818e7e69"},
     {file = "langcodes-3.3.0.tar.gz", hash = "sha256:794d07d5a28781231ac335a1561b8442f8648ca07cd518310aeb45d6f0807ef6"},
 ]
+langdetect = []
+lxml = []
 markdown = []
 markdown-callouts = []
 markupsafe = [
@@ -1432,6 +1883,7 @@ markupsafe = [
 ]
 marshmallow = []
 marshmallow-enum = []
+matplotlib = []
 mccabe = []
 mergedeep = []
 mkdocs = []
@@ -1442,6 +1894,8 @@ mkdocs-same-dir = []
 mkdocstrings = []
 mkdocstrings-crystal = []
 mkdocstrings-python = []
+more-itertools = []
+mpld3 = []
 mslex = []
 multidict = []
 murmurhash = []
@@ -1451,6 +1905,7 @@ mypy-extensions = [
     {file = "mypy_extensions-0.4.3.tar.gz", hash = "sha256:2d82818f5bb3e369420cb3c4060a7970edba416647068eb4c5343488a6c604a8"},
 ]
 numpy = []
+overrides = []
 packaging = [
     {file = "packaging-21.3-py3-none-any.whl", hash = "sha256:ef103e05f519cdc783ae24ea4e2e0f508a9c99b2d4969652eed6a2e1ea5bd522"},
     {file = "packaging-21.3.tar.gz", hash = "sha256:dd47c42927d89ab911e606518907cc2d3a1f38bbd026385970643f9c5b8ecfeb"},
@@ -1458,6 +1913,7 @@ packaging = [
 partial-tagger = []
 pathspec = []
 pathy = []
+pillow = []
 platformdirs = [
     {file = "platformdirs-2.5.2-py3-none-any.whl", hash = "sha256:027d8e83a2d7de06bbac4e5ef7e023c02b863d7ea5d079477e722bb41ab25788"},
     {file = "platformdirs-2.5.2.tar.gz", hash = "sha256:58c8abb07dcb441e6ee4b11d8df0ac856038f944ab98b7be6b27b2a3c7feef19"},
@@ -1482,6 +1938,7 @@ pyparsing = [
     {file = "pyparsing-3.0.9.tar.gz", hash = "sha256:2b020ecf7d21b687f219b71ecad3631f644a47f01403fa1d1036b0c6416d70fb"},
 ]
 pyproject-flake8 = []
+pysocks = []
 pytest = []
 python-dateutil = [
     {file = "python-dateutil-2.8.2.tar.gz", hash = "sha256:0123cacc1627ae19ddf3c27a5de5bd67ee4586fbdd6440d9748f8abb483d3e86"},
@@ -1494,6 +1951,12 @@ regex = []
 requests = []
 requests-toolbelt = []
 responses = []
+scikit-learn = []
+scipy = []
+segtok = []
+sentencepiece = []
+seqal = []
+setuptools-scm = []
 six = [
     {file = "six-1.16.0-py2.py3-none-any.whl", hash = "sha256:8abb2f1d86890a2dfb989f9a77cfcfd3e47c2a354b01111771326f8aa26e0254"},
     {file = "six-1.16.0.tar.gz", hash = "sha256:1e61c37477a1626458e36f7b1d82aa5c9b094fa4802892072e49de9c60c4c926"},
@@ -1508,9 +1971,15 @@ spacy-legacy = []
 spacy-loggers = []
 spacy-partial-tagger = []
 spacy-transformers = []
+sqlitedict = []
 srsly = []
+tabulate = []
 taskipy = []
 thinc = []
+threadpoolctl = [
+    {file = "threadpoolctl-3.1.0-py3-none-any.whl", hash = "sha256:8b99adda265feb6773280df41eece7b2e6561b772d21ffd52e372f999024907b"},
+    {file = "threadpoolctl-3.1.0.tar.gz", hash = "sha256:a335baacfaa4400ae1f0d8e3a58d6674d2f8828e3716bb2802c44955ad391380"},
+]
 tokenizers = []
 tomli = [
     {file = "tomli-2.0.1-py3-none-any.whl", hash = "sha256:939de3e7a6161af0c887ef91b7d41a53e7c5a1ca976325f429cb46ea9bc30ecc"},
@@ -1528,6 +1997,11 @@ urllib3 = []
 vcrpy = []
 wasabi = []
 watchdog = []
+wcwidth = [
+    {file = "wcwidth-0.2.5-py2.py3-none-any.whl", hash = "sha256:beb4802a9cebb9144e99086eff703a642a13d6a0052920003a230f3294bbe784"},
+    {file = "wcwidth-0.2.5.tar.gz", hash = "sha256:c4d647b99872929fdb7bdcaa4fbe7f01413ed3d98077df798530e5b04f116c83"},
+]
+wikipedia-api = []
 wrapt = []
 yarl = []
 zipp = []
diff --git a/pyproject.toml b/pyproject.toml
index abf1a25..5081609 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -26,7 +26,8 @@ spacy-partial-tagger = { version = "^0.9.1", optional = true }
 tqdm = { version = "^4.64.1", optional = true }
 pydantic = "^1.9.2"
 requests-toolbelt = "^0.9.1"
-ffmpeg-python = {version = "^0.2.0", extras = ["whisper"]}
+ffmpeg-python = { version = "^0.2.0", optional = true }
+seqal = { version = "^0.3.4", optional = true }
 
 [tool.poetry.dev-dependencies]
 flake8 = "^5.0.4"
@@ -48,6 +49,7 @@ mkdocstrings = {extras = ["python", "crystal"], version = "^0.19.0"}
 [tool.poetry.extras]
 spacy = ["spacy", "spacy-partial-tagger", "tqdm"]
 whisper = ["ffmpeg-python", "tqdm"]
+al = ["spacy", "seqal"]
 
 [build-system]
 requires = ["poetry-core>=1.0.0"]