GitPlanet

Cheap and reliable Node.js hosting starts at $3/month, and $1/month static HTML hosting

Created with love in Canada, visit hostnodejs.com today

Feel like to post an Ad? Learn Details
All Projects → akjindal53244 → dependency_parsing_tf

akjindal53244 / dependency_parsing_tf

Licence: other
Tensorflow implementation of "A Fast and Accurate Dependency Parser using Neural Networks"

Programming Languages

python
139335 projects - #7 most used programming language

Labels

tensorflowdependency-parser

Projects that are alternatives of or similar to dependency parsing tf

udar
UDAR Does Accented Russian: A finite-state morphological analyzer of Russian that handles stressed wordforms.
Stars: ✭ 15 (-80.52%)
Mutual labels:  dependency-parser
ipymarkup
NER, syntax markup visualizations
Stars: ✭ 108 (+40.26%)
Mutual labels:  dependency-parser
stanford-corenlp-docker
build/run the most current Stanford CoreNLP server in a docker container
Stars: ✭ 38 (-50.65%)
Mutual labels:  dependency-parser
FAParser
A Fast(er) and Accurate Syntactic Parsing by Exacter Searching.
Stars: ✭ 17 (-77.92%)
Mutual labels:  dependency-parser
datalinguist
Stanford CoreNLP in idiomatic Clojure.
Stars: ✭ 93 (+20.78%)
Mutual labels:  dependency-parser
dpar
Neural network transition-based dependency parser (in Rust)
Stars: ✭ 41 (-46.75%)
Mutual labels:  dependency-parser
frog
Frog is an integration of memory-based natural language processing (NLP) modules developed for Dutch. All NLP modules are based on Timbl, the Tilburg memory-based learning software package.
Stars: ✭ 70 (-9.09%)
Mutual labels:  dependency-parser
TweebankNLP
[LREC 2022] An off-the-shelf pre-trained Tweet NLP Toolkit (NER, tokenization, lemmatization, POS tagging, dependency parsing) + Tweebank-NER dataset
Stars: ✭ 84 (+9.09%)
Mutual labels:  dependency-parser
syntaxnet
Syntaxnet Parsey McParseface wrapper for POS tagging and dependency parsing
Stars: ✭ 77 (+0%)
Mutual labels:  dependency-parser
yap
Yet Another (natural language) Parser
Stars: ✭ 40 (-48.05%)
Mutual labels:  dependency-parser
Pyhanlp
中文分词 词性标注 命名实体识别 依存句法分析 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁 自然语言处理
Stars: ✭ 2,564 (+3229.87%)
Mutual labels:  dependency-parser
Hanlp
中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理
Stars: ✭ 24,626 (+31881.82%)
Mutual labels:  dependency-parser

dependency_parsing_tf

Tensorflow implementation of "A Fast and Accurate Dependency Parser using Neural Networks" https://cs.stanford.edu/~danqi/papers/emnlp2014.pdf

Tensorboard

tensorboard --logdir=path of model variables' folder

example: tensorboard --logdir=/dependency_parsing_tf/data/params_2017-09-18

Recent changes

  1. transition to tf 1.2
  2. added cube activation function (ref: paper)
  3. trainable word embeddings - initialized with 50d word2vec
  4. l2 loss for regularization (ref: paper)
  5. tensorboard visualization
  6. Dev UAS: 90.03 Test UAS: 90.42
  7. No functionality for LAS currently. it can be done with few changes in feature_extraction.py. I will try to add it.

training (exisiting dataset)

python parser_model.py

For new dataset

  1. Build new vocabulary & embedding matrices -> set "load_existing_dump=False" in parser_model.py. This will overwrite existing "data/dump" directory content
  2. python parser_model.py

training dataset

CONLL format

Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].