Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".

Last update: Nov 08, 2022

Overview

crfsrl

Yu Zhang, Qingrong Xia, Shilin Zhou, Yong Jiang, Zhenghua Li, Guohong Fu, Min Zhang. Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments. 2021. [arxiv]

Setup

The following packages should be installed:

SuPar: == 1.1.3
PyTorch: >= 1.7
Transformers: >= 4.0

Run the following scripts to obtain the training data. Please make sure PTB and OntoNotes are available:

bash scripts/conll05.sh PTB=<path-to-ptb>             SRL=data
bash scripts/conll12.sh ONTONOTES=<path-to-ontonotes> SRL=data

Run

Try the following commands to train first-order CRF and second-order CRF2o models:

# LSTM
# CRF
python -u crf.py   train -b -c configs/conll05.crf.srl.lstm.char-lemma.ini   -d 0 -f char lemma -p exp/conll05.crf.srl.lstm.char-lemma/model
# CRF2o
python -u crf2o.py train -b -c configs/conll05.crf2o.srl.lstm.char-lemma.ini -d 0 -f char lemma -p exp/conll05.crf2o.srl.lstm.char-lemma/model
# BERT finetuning
# CRF
python -u crf.py   train -b -c configs/conll05.crf.srl.bert.ini   -d 0 -p exp/conll05.crf.srl.bert/model   --batch-size=1000 --encoder bert --bert bert-large-cased 
# CRF2o
python -u crf2o.py train -b -c configs/conll05.crf2o.srl.bert.ini -d 0 -p exp/conll05.crf2o.srl.bert/model --batch-size=1000 --encoder bert --bert bert-large-cased

To do evaluation:

# end-to-end
python -u crf.py   evaluate -c configs/conll05.crf.srl.bert.ini  -d 0 -p exp/conll05.crf.srl.bert/model    --data data/conll05/test.conllu
# w/ gold predicates
python -u crf.py   evaluate -c configs/conll05.crf.srl.bert.ini  -d 0 -p exp/conll05.crf.srl.bert/model    --data data/conll05/test.conllu --prd

To make predictions:

python -u crf.py   predict  -c configs/conll05.crf.srl.bert.ini   -d 0 -p exp/conll05.crf.srl.bert/model   --data data/conll05/test.conllu --pred pred.conllu
bash scripts/eval.sh pred=pred.conllu gold=data/conll05/test.conllu

Contact

If you have any questions, feel free to contact me via emails.

Code for "Semantic Role Labeling as Dependency Parsing: Exploring Latent Tree Structures Inside Arguments".

Related tags

Overview

crfsrl

Setup

Run

Contact

Owner

Yu Zhang

Python library for parsing resumes using natural language processing and machine learning

Healthsea is a spaCy pipeline for analyzing user reviews of supplementary products for their effects on health.

Meta learning algorithms to train cross-lingual NLI (multi-task) models

Baseline code for Korean open domain question answering(ODQA)

Chinese named entity recognization (bert/roberta/macbert/bert_wwm with Keras)

Cải thiện Elasticsearch trong bài toán semantic search sử dụng phương pháp Sentence Embeddings

neural network based speaker embedder

Official source for spanish Language Models and resources made @ BSC-TEMU within the "Plan de las Tecnologías del Lenguaje" (Plan-TL).

Ray-based parallel data preprocessing for NLP and ML.

Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation

Stand-alone language identification system

Translates basic English sentences into the Huna language (hoo-NAH)

Coreference resolution for English, French, German and Polish, optimised for limited training data and easily extensible for further languages

Python package to easily retrain OpenAI's GPT-2 text-generating model on new texts

A full spaCy pipeline and models for scientific/biomedical documents.

An open source framework for seq2seq models in PyTorch.

The proliferation of disinformation across social media has led the application of deep learning techniques to detect fake news.

translate using your voice

Espial is an engine for automated organization and discovery of personal knowledge

Code for "Finetuning Pretrained Transformers into Variational Autoencoders"