archybrid-parser

KO | EN

gitlite — search

#python #hacktoberfest #react #golang #machine-learning #rust #docker #java #windows #cli #awesome-list #vue #pytorch #openai

archybrid-parser

(★ 9)

A transition-based dependency parser for both projective and non-projective trees, using Bi-LSTM as a feature extractor

archybrid-parser 최신버젼 다운로드

최종 버전 다운로드 (.zip)

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# A transition-based dependency parser for both projective and non-projective trees
This is a PyTorch implement of ['Simple and Accurate Dependency Parsing Using Bidirectional LSTM Feature Representations'.](https://aclweb.org/anthology/Q16-1023) and ['Arc-Hybrid Non-Projective Dependency Parsing with a Static-Dynamic Oracle'](https://www.aclweb.org/anthology/W17-6314).

It is a transition-based dependency parser for both projective and non-projective trees, using BiLSTM networks and arc-hybrid systems.
Although it is just a naive implement of these papers without much optimization, its performance is beyond expectation.

## Requirements
+ Python (>= 3.6)
+ PyTorch (>= 1.0)

## About dataset
The dataset I used for training is a treebank in Chinese. It is class-use only, so I can't upload it to github.
It is preprocessed into 'json' format. Each word in the sentence has these attributes: 'id', 'word', 'pos', 'father', 'emb'.

## Reference
+ https://github.com/elikip/bist-parser
+ https://github.com/UppsalaNLP/uuparser
+ https://github.com/MathijsMul/lm_parser/blob/master/arc_hybrid.py

archybrid-parser

archybrid-parser 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

archybrid-parser

archybrid-parser 최신버젼 다운로드

오늘의 추천 프로젝트

Was this content helpful?

Recent Feedback

Download README