TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Named Entity Recognition (NER)	CoNLL 2003 (English)	S-LSTM	F1	91.57	# 58
Sentiment Analysis	IMDb	S-LSTM	Accuracy	87.15	# 39
Sentiment Analysis	MR	S-LSTM	Accuracy	76.2	# 16
Part-Of-Speech Tagging	Penn Treebank	S-LSTM	Accuracy	97.55	# 10

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sentence-state-lstm-for-text-representation/part-of-speech-tagging-on-penn-treebank)](https://paperswithcode.com/sota/part-of-speech-tagging-on-penn-treebank?p=sentence-state-lstm-for-text-representation)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sentence-state-lstm-for-text-representation/sentiment-analysis-on-mr)](https://paperswithcode.com/sota/sentiment-analysis-on-mr?p=sentence-state-lstm-for-text-representation)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sentence-state-lstm-for-text-representation/sentiment-analysis-on-imdb)](https://paperswithcode.com/sota/sentiment-analysis-on-imdb?p=sentence-state-lstm-for-text-representation)`
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/sentence-state-lstm-for-text-representation/named-entity-recognition-ner-on-conll-2003)](https://paperswithcode.com/sota/named-entity-recognition-ner-on-conll-2003?p=sentence-state-lstm-for-text-representation)`

Sentence-State LSTM for Text Representation

ACL 2018 · Yue Zhang, Qi Liu, Linfeng Song ·

Bi-directional LSTMs are a powerful tool for text representation. On the other hand, they have been shown to suffer various limitations due to their sequential nature. We investigate an alternative LSTM structure for encoding text, which consists of a parallel state for each word. Recurrent steps are used to perform local and global information exchange between words simultaneously, rather than incremental reading of a sequence of words. Results on various classification and sequence labelling benchmarks show that the proposed model has strong representation power, giving highly competitive performances compared to stacked BiLSTM models with similar parameter numbers.

PDF Abstract ACL 2018 PDF ACL 2018 Abstract

Code

Add Remove Mark official

leuchine/S-LSTM

156

LahiruSen/S-LSTM_Sinhala

Tasks

Add Remove

General Classification

Named Entity Recognition (NER)

Part-Of-Speech Tagging

Sentence

Sentiment Analysis

Text Classification

Datasets

IMDb Movie Reviews

Penn Treebank CoNLL 2003 CoNLL

Results from the Paper

Edit

Ranked #10 on Part-Of-Speech Tagging on Penn Treebank

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
Named Entity Recognition (NER)	CoNLL 2003 (English)	S-LSTM	F1	91.57	# 58	Compare
Sentiment Analysis	IMDb	S-LSTM	Accuracy	87.15	# 39	Compare
Sentiment Analysis	MR	S-LSTM	Accuracy	76.2	# 16	Compare
Part-Of-Speech Tagging	Penn Treebank	S-LSTM	Accuracy	97.55	# 10	Compare

Methods

Add Remove

BiLSTM • LSTM • Sigmoid Activation • Tanh Activation

Edit Social Preview

Sentence-State LSTM for Text Representation

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove