Data

Tools

Indexes

Applications

Experiments

Open Source Science

transformer-srl

Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.

https://github.com/riccorl/transformer-srl

Science Score: 54.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ✓
    Academic publication links
    Links to: arxiv.org
  • ○
    Committers with academic emails
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (10.3%) to scientific vocabulary

Keywords

allennlp bert conll2012 dataset labeling natural-language-processing nlp propbank pytorch role semantic semantic-role-labeling shi span srl srl-annotations srltagger transformer transformers verbatlas
Last synced: 6 months ago · JSON representation ·

Repository

Reimplementation of a BERT based model (Shi et al, 2019), currently the state-of-the-art for English SRL. This model implements also predicate disambiguation.

Basic Info
  • Host: GitHub
  • Owner: Riccorl
  • Language: Perl
  • Default Branch: master
  • Homepage:
  • Size: 1.21 MB
Statistics
  • Stars: 70
  • Watchers: 6
  • Forks: 9
  • Open Issues: 5
  • Releases: 8
Topics
allennlp bert conll2012 dataset labeling natural-language-processing nlp propbank pytorch role semantic semantic-role-labeling shi span srl srl-annotations srltagger transformer transformers verbatlas
Created over 5 years ago · Last pushed almost 4 years ago
Metadata Files
Readme Citation

README.md

Upload Python Package Code style: black

Semantic Role Lableing with BERT

Semantic Role Labeling based on AllenNLP implementation of Shi et al, 2019. Can be trained using both PropBank and VerbAtlas inventories and implements also the predicate disambiguation task, in addition to arguments identification and disambiguation.

How to use

Install the library

bash pip install transformer-srl

Pre-trained model

You can also use a pre-trained model. To use it, first install the correct version of transformer-srl:

bash pip install transformer-srl==2.4.6

then download the pretrained model srl_bert_base_conll2012.tar.gz from here.

| File | Model | Version | F1 Argument | F1 Predicate | | :---: | :---: | :---: | :---: | :---: | | srlbertbase_conll2012.tar.gz | bert-base-cased | 2.4.6 | 86.0 | 95.5 |

CLI

bash echo '{"sentence": "Did Uriah honestly think he could beat the game in under three hours?"}' | \ allennlp predict path/to/srl_bert_base_conll2012.tar.gz - --include-package transformer_srl

Inside Python Code

```python from transformersrl import datasetreaders, models, predictors

predictor = predictors.SrlTransformersPredictor.frompath("path/to/srlbertbaseconll2012.tar.gz, "transformer_srl") predictor.predict( sentence="Did Uriah honestly think he could beat the game in under three hours?" ) ```

Infos

  • Language Model: BERT
  • Dataset: CoNLL 2012

Results with VerbAtlas

With bert-base-cased: ```

Dev set

  • F1 arguments 87.6
  • F1 predicates 95.5 # Test set
  • F1 arguments x
  • F1 predicates x ```

With bert-base-multilingual-cased: ```

Dev set

  • F1 arguments 86.2
  • F1 predicates 94.2 # Test set
  • F1 arguments 86.1
  • F1 predicates 94.9 ```

To-Dos

  • [x] Works with both PropBank and VerbAtlas (infer inventory from dataset reader)
  • [ ] Compatibility with all models from Huggingface's Transformers. - Now works only with models that accept 1 as token type id
  • [ ] Predicate identification (without using spacy)

Owner

  • Name: Riccardo Orlando
  • Login: Riccorl
  • Kind: user
  • Location: Rome, Italy
  • Company: PhD @SapienzaNLP

PhD Student at @SapienzaNLP group

Citation (CITATION.cff) 

# This CITATION.cff file was generated with cffinit.
# Visit https://bit.ly/cffinit to generate yours today!

cff-version: 1.2.0
title: transformer-srl
message: >-
  If you use this software, please cite it using the
  metadata from this file.
type: software
authors:
  - email: orlandoricc@gmail.com
    given-names: Riccardo
    family-names: Orlando

GitHub Events

Total
  • Watch event: 2
Last Year
  • Watch event: 2

Committers

Last synced: about 2 years ago

All Time
  • Total Commits: 147
  • Total Committers: 2
  • Avg Commits per committer: 73.5
  • Development Distribution Score (DDS): 0.054
Past Year
  • Commits: 0
  • Committers: 0
  • Avg Commits per committer: 0.0
  • Development Distribution Score (DDS): 0.0
Top Committers
Name Email Commits
Riccardo Orlando o****c@g****m 139
Riccardo Orlando R****l 8

Issues and Pull Requests

Last synced: 7 months ago

All Time
  • Total issues: 22
  • Total pull requests: 1
  • Average time to close issues: 23 days
  • Average time to close pull requests: 15 minutes
  • Total issue authors: 17
  • Total pull request authors: 1
  • Average comments per issue: 5.68
  • Average comments per pull request: 0.0
  • Merged pull requests: 1
  • Bot issues: 0
  • Bot pull requests: 0
Past Year
  • Issues: 0
  • Pull requests: 0
  • Average time to close issues: N/A
  • Average time to close pull requests: N/A
  • Issue authors: 0
  • Pull request authors: 0
  • Average comments per issue: 0
  • Average comments per pull request: 0
  • Merged pull requests: 0
  • Bot issues: 0
  • Bot pull requests: 0
View more stats
Top Authors
Issue Authors
  • LeonHammerla (3)
  • sev777 (2)
  • Zoher15 (2)
  • logicReasoner (2)
  • egumasa (1)
  • KTRosenberg (1)
  • pragyakatyayan (1)
  • alirezamshi-zz (1)
  • Wangpeiyi9979 (1)
  • creatorrr (1)
  • DavidSorge (1)
  • felgaet (1)
  • therealhieu (1)
  • Suneal (1)
  • Lisa-aa (1)
Pull Request Authors
  • Riccorl (1)
Top Labels
Issue Labels
Pull Request Labels

Packages

  • Total packages: 1
  • Total downloads:
    • pypi 227 last-month
  • Total dependent packages: 0
  • Total dependent repositories: 1
  • Total versions: 74
  • Total maintainers: 1
pypi.org: transformer-srl

SRL Transformer model

  • Versions: 74
  • Dependent Packages: 0
  • Dependent Repositories: 1
  • Downloads: 227 Last month
Rankings
Stargazers count: 8.3%
Dependent packages count: 10.1%
Forks count: 11.4%
Average: 13.1%
Downloads: 13.9%
Dependent repos count: 21.5%
Maintainers (1)
riccorl
Last synced: 6 months ago

Dependencies

setup.py pypi
  • allennlp >=2.0,<2.1
  • allennlp_models >=2.0,<2.1
  • spacy >=2.3,<2.4