A Python library for automatic term extraction (ATE) from text corpora. JATE provides 14 classical ATE algorithms, corpus-level statistics, built-in evaluation, and a CLI — all pip-installable with no external services required.

JATE v3 is a complete rewrite of the original Java JATE library (84+ GitHub stars), which was built on Apache Solr and used in academic and industry settings for over a decade. The Python version preserves all 13 original classical algorithms from the Java codebase — with every formula verified line-by-line against the original source — while removing the Solr dependency in favour of a self-contained, pip-installable package. It also adds ensemble voting via reciprocal rank fusion when comparing multiple algorithms. The original Java library is preserved on the legacy/java branch.

Launch the live demo on Hugging Face Spaces — paste any text, pick from 14 algorithms, and see extracted terms instantly in your browser.

The local UI gives you everything the online demo has and more — corpus-level extraction across entire directories, multi-algorithm comparison with a shared NLP pipeline, real-time progress streaming, and full CSV/JSON export. All processing happens on your machine, so there are no size limits and your data stays private.

pip install "jate[server]"
jate ui

pip install jate

Or from source:

git clone https://github.com/ziqizhang/jate.git
cd jate
pip install .

Requires Python 3.11+ and a spaCy model:

python -m spacy download en_core_web_sm

import jate

# Extract terms from text (default: C-Value + POS pattern extraction)
result = jate.extract("Your document text here...")

for term in result:
    print(f"{term.string:30s}  score={term.score:.4f}  surfaces={term.surface_forms}")

import jate

# From a list of texts
result = jate.extract_corpus(
    ["First document...", "Second document..."],
    algorithm="tfidf",
)

# From a directory of text files
result = jate.extract_corpus("path/to/corpus/", algorithm="cvalue")

# Export results
df = result.to_dataframe()
print(result.to_csv())

import jate

results = jate.compare(
    ["Doc one...", "Doc two..."],
    algorithms=["cvalue", "tfidf", "rake", "weirdness"],
)

for algo_name, result in results.items():
    print(f"\n{algo_name}: {len(result)} terms")
    for term in list(result)[:5]:
        print(f"  {term.string:30s}  {term.score:.4f}")

For large corpora, NLP processing (spaCy) uses multi-threaded C-level batching, and feature building (adjacent word computation) uses multi-process parallelism automatically.

import jate

result = jate.extract_corpus(docs, algorithm="cvalue")

evaluator = jate.Evaluator({"machine learning", "neural network", ...})
eval_result = evaluator.evaluate(result)
print(eval_result.summary())
# P=0.2800  R=0.0644  F1=0.1047  TP=28  FP=72  FN=407  predicted=100  gold=435

# Evaluate top-k
eval_at_50 = evaluator.evaluate_at_k(result, k=50)

# Extract terms from text
jate extract "Your text here" --algorithm cvalue --top 20

# Extract from a corpus directory
jate corpus path/to/docs/ --algorithm tfidf --output csv

# Compare algorithms on a corpus
jate compare path/to/docs/ --algorithms cvalue tfidf rake

# Run benchmark on built-in dataset (use --list-datasets to see all options)
jate benchmark --dataset acl_rdtec_mini --top 100

JATE now ships a thin JSON API server on top of the core extraction API.

Install server dependencies:

pip install "jate[server]"

Start the server:

jate-api

Or with Python module execution:

python -m uvicorn jate.server:app --host 0.0.0.0 --port 8000

Extract terms over HTTP:

curl --header "Content-Type: application/json" \
    --request POST \
    --data '{"text":"text to process","algorithm":"cvalue"}' \
    http://localhost:8000/jate/api/v1/extract

Health checks:

curl http://localhost:8000/health/live
curl http://localhost:8000/health/ready

Build the image from repo root:

docker build -t jate:latest .

Run modes:

# 1) CLI mode (default)
docker run --rm jate:latest jate extract "local post office" --algorithm cvalue --top 20

# Corpus mode with local volume mount (recommended for local files)
docker run --rm -v "/path/to/local/folder:/data" jate:latest \
    jate corpus /data --algorithm cvalue --top 20

# 2) API mode (explicit)
docker run --rm -d -p 8000:8000 --name jate-api-test jate:latest jate-api

# 3) Interactive mode with local corpus volume
docker run -it --rm -v "$(pwd)/path/to/docs:/data" jate:latest sh
# inside container:
# jate corpus /data --algorithm tfidf --output csv

Test API endpoints (when running API mode):

# Liveness
curl -s http://localhost:8000/health/live

# Readiness (validates spaCy model availability)
curl -s http://localhost:8000/health/ready

# Capabilities
curl -s http://localhost:8000/jate/api/v1/capabilities

# Extract terms
curl -s -X POST http://localhost:8000/jate/api/v1/extract \
    -H "Content-Type: application/json" \
    -d '{"text":"Russia says its consulate in Isfahan, Iran was damaged over the weekend as a result of strikes on the local governor'\''s office.","algorithm":"cvalue","top":6}'

Stop API mode container:

docker stop jate-api-test

Run dual-mode Docker smoke checks (CLI + API) with one build:

bash scripts/docker_smoke_test.sh

Expected extract response shape:

{
    "algorithm": "cvalue",
    "extractor": "pos_pattern",
    "model": "en_core_web_sm",
    "top": 6,
    "terms": [
        {
            "rank": 1,
            "term": "local governors office",
            "score": 1.6323,
            "frequency": 1,
            "surface_forms": ["local governors office"],
            "metadata": {}
        }
    ]
}

Multi-algorithm comparison is available via jate.compare(), which also supports ensemble voting via reciprocal rank fusion (voting=True).

JATE also supports transformer-based term taggers that extract terms per-document using BIO sequence labelling. Install with pip install "jate[neural]".

from jate.algorithms.bert_tagger import XLMRTagger

tagger = XLMRTagger()  # auto-downloads from HuggingFace on first use
result = tagger.tag("Corruption in public procurement is a major challenge.")

for term in result:
    print(f"{term.string:30s}  confidence={term.score:.4f}")

Pre-trained model: ziqizhang2026/jate-ate-xlmr (trained on ACTER). Train your own: python examples/train_bert_tagger.ipynb on Google Colab.

Try the demo: python examples/tagger_demo.py

1. Candidate extraction — identifies potential terms using POS patterns, n-grams, or noun phrases
2. Lemmatisation — normalises candidates to their lemmatised form (e.g. "neural networks" and "neural network" become one entry)
3. Sentence context (automatic) — builds sentence co-occurrence and adjacency features for algorithms that use them (Chi-Square, NC-Value)
4. Corpus statistics — builds frequency and co-occurrence counts (in-memory or SQLite-backed)
5. Scoring — applies the chosen algorithm to rank candidates
6. Output — returns TermExtractionResult with the normalised term, score, and all observed surface forms

Each Term in the result contains:

• string — the canonical (lemmatised) form, used for scoring and evaluation
• score — algorithm-assigned score
• frequency — total corpus frequency
• surface_forms — all surface variants observed (e.g. {"neural network", "neural networks", "Neural Networks"})

JATE can be used as a native spaCy pipeline component, reusing the NLP processing already done by spaCy (no double computation):

import spacy
import jate

nlp = spacy.load("en_core_web_sm")
nlp.add_pipe("jate", config={"algorithm": "cvalue"})

doc = nlp("Machine learning and neural networks improve deep learning models.")

for term in doc._.terms:
    surface = doc.text[term.spans[0].start:term.spans[0].end] if term.spans else ""
    print(f"{term.string:30s}  score={term.score:.4f}  at {surface!r}")

Configuration options:

Important notes:

• One algorithm per pipeline (for multi-algorithm comparison, use jate.compare())
• All algorithms will warn about single-document mode — they are corpus-level methods designed for multi-document extraction. Results on single documents are functional but weaker.
• TF-IDF will return empty results on single documents (IDF = 0).

Try the demo: python examples/spacy_demo.py

The local UI (jate ui) opens at http://localhost:8080 with two modes:

Extract — paste text or upload a file, select from 14 algorithms with per-algorithm tuning parameters, view results as a ranked table or as highlighted text, and export to CSV/JSON.

Corpus — point to a directory of .txt files, select multiple algorithms at once (the shared NLP pipeline makes multi-algorithm runs significantly faster than running them separately), watch real-time progress via Server-Sent Events, and compare results side-by-side.

Or run via Docker:

docker run --rm -p 8080:8080 jate:latest jate ui

JATE is evaluated on 4 standard ATE datasets using P@K (precision at top-K ranked terms). Best algorithm per dataset at P@100:

Full results with P@100 through P@10,000 for all 13 algorithms, methodology notes, and comparison with published baselines: benchmark results.

Please read the contributing guide first for development setup, branch workflow, and agentic coding harness details. JATE is in active development and we welcome contributions. Here's how you can get involved:

• Browse open issues — check the feature roadmap for planned enhancements
• Good first issues — look for issues labelled good first issue if you're new to the project
• Feature requests — open an issue to suggest new features
• Bug reports — report here
• Star the repo to follow progress

JATE was originally developed as part of research at the University of Sheffield, with publications in venues including ACM TKDD and the Semantic Web Journal. The library has been used in academic and industry settings for terminology extraction, ontology learning, and knowledge graph construction.

Key publications:

• Zhang, Z., Gao, J., Ciravegna, F. (2018). SemRe-Rank: Improving Automatic Term Extraction By Incorporating Semantic Relatedness With Personalised PageRank. ACM TKDD.
• Zhang, Z., Iria, J., Brewster, C., Ciravegna, F. (2008). A Comparative Evaluation of Term Recognition Algorithms. LREC.

Apache 2.0 — see LICENSE for details.