# huggingface/hmtl

🌊HMTL: Hierarchical Multi-Task Learning - A State-of-the-Art neural network model for several NLP tasks based on PyTorch and AllenNLP

Repository: https://github.com/huggingface/hmtl
Canonical: https://ross.abutalabs.com/products/hmtl
Language: Python
License: MIT
License Family: permissive
Topics: natural-language-processing, multi-task-learning, nlp, pytorch
Last push: 2023-08-01T22:48:49+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2863, "days_push": 1128, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1195, forks 146 (observed 2026-08-28T04:03:56.877858+00:00)

## What it is
HMTL is a Hierarchical Multi-Task Learning model for NLP that jointly trains Named Entity Recognition, Entity Mention Detection, Relation Extraction, and Coreference Resolution using PyTorch and AllenNLP. It includes code for training, fine-tuning, and evaluating the model, plus pre-trained weights and an online demo.

## Use cases
- train a multi-task NLP model for NER and relation extraction
- run named entity recognition with pre-trained weights
- learn hierarchical multi-task learning in PyTorch
- evaluate sentence embeddings from semantic tasks with SentEval
- build custom multi-task models on AllenNLP
- reproduce AAAI 2019 paper results

## When to choose
- you want a state-of-the-art multi-task model for NER, entity mention detection, relation extraction, or coreference
- you're researching multi-task learning architectures in PyTorch/AllenNLP
- you need pre-trained semantic task models with a demo

## When to avoid
- you need a maintained production NLP library (AllenNLP is deprecated and the repo is in maintenance)
- you want transformer-based models like those in Hugging Face Transformers
- you need tasks beyond the four supported semantic tasks

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: multi-task-learning, pytorch, allennlp, named-entity-recognition, relation-extraction, coreference-resolution, research, natural-language-processing

## Member repositories
- huggingface/hmtl (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:56.877858+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T06:22:06.058622+00:00, confidence not recorded.
  - readme: https://github.com/huggingface/hmtl (fetched 2026-08-28T04:03:56.877858+00:00, sha 314421b2c3be)
- Data as of 2026-08-30T08:39:29.467469+00:00.