Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation

Yao, Yushi; Huang, Zheng

doi:10.1007/978-3-319-46681-1_42

Cited by 106 publications

(53 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…BiLSTM has two parallel layers propagating in both directions . The final output of such a network would be the concatenation of the output of these two layers.…”

Section: Deep Learning Models For Sentiment Classificationmentioning

confidence: 99%

“…BiLSTM has two parallel layers propagating in both directions. 66 The final output of such a network would be the concatenation of the output of these two layers. With h F (t) as the hidden state of the forward propagating layer and h B (t) as the hidden state of the backward propagating layer, h (t) the hidden state of the BiLSTM can be calculated as follows:…”

Section: Bi-directional Long Short Time Memory (Bilstm)mentioning

confidence: 99%

See 1 more Smart Citation

Evaluating deep learning models for sentiment classification

Karakus

Talo

Hallac

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

Summary Deep learning has emerged as an effective solution to various text mining problems such as document classification and clustering, document summarization, web mining, and sentiment analysis. In this paper, we describe our work on investigating several deep learning models for a binary sentiment classification problem. We used movie reviews in Turkish from the website http://www.beyazperde.com to train and test the deep learning models. We also report a detailed comparison of the models in terms of accuracy and time performances. Two major deep learning architectures used in this study are Convolutional Neural Networks and Long Short‐Term Memory. We built several variants of these models by changing the number of layers, tuning the hyper‐parameters, and combining models. Additionally, word embeddings were created by applying the word2vec algorithm with a skip‐gram model on a large dataset (∼ 13 M words) composed of movie reviews. We investigate the effect of using the pre‐word embeddings with these models. Experimental results have shown that the use of word embeddings with deep neural networks effectively yields performance improvements in terms of run time and accuracy.

show abstract

“…BiLSTM has two parallel layers propagating in both directions . The final output of such a network would be the concatenation of the output of these two layers.…”

Section: Deep Learning Models For Sentiment Classificationmentioning

confidence: 99%

Section: Bi-directional Long Short Time Memory (Bilstm)mentioning

confidence: 99%

Evaluating deep learning models for sentiment classification

Karakus

Talo

Hallac

et al. 2018

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…For segmentation, Yao and Huang (2016) successfully used a bi-directional LSTM model for segmenting Chinese text. In this paper, we build on their work and extend it in two ways, namely combining bi-LSTM with CRF and applying on Arabic, which is an alphabetic language.…”

Section: Related Workmentioning

confidence: 99%

A Neural Architecture for Dialectal Arabic Segmentation

Samih¹,

Attia²,

Eldesouki³

et al. 2017

Proceedings of the Third Arabic Natural Language Processing Workshop

View full text Add to dashboard Cite

The automated processing of Arabic dialects is challenging due to the lack of spelling standards and the scarcity of annotated data and resources in general. Segmentation of words into their constituent tokens is an important processing step for natural language processing. In this paper, we show how a segmenter can be trained on only 350 annotated tweets using neural networks without any normalization or reliance on lexical features or linguistic resources. We deal with segmentation as a sequence labeling problem at the character level. We show experimentally that our model can rival state-of-the-art methods that heavily depend on additional resources.

show abstract

“…In the past few years, neural networks have been widely used to solve NLP problems. Specially, several RNN-based neural networks have been proposed to handle sequence labeling tasks including Chinese word segmentation (Yao and Huang, 2016), POS tagging (Huang et al, 2015), NER (Chiu and Nichols, 2015) (Lample et al, 2016), which achieved outstanding performance against traditional methods.…”

Section: Introductionmentioning

confidence: 99%

DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic features

Ma¹,

Zheng²,

Xie³

et al. 2018

Proceedings of the 12th International Workshop on Semantic Evaluation

View full text Add to dashboard Cite

This paper describes our submissions for SemEval-2018 Task 8: Semantic Extraction from CybersecUrity REports using NLP. The DM NLP participated in two subtasks: SubTask 1 classifies if a sentence is useful for inferring malware actions and capabilities, and SubTask 2 predicts token labels ("Action", "Entity", "Modifier" and "Others") for a given malware-related sentence. Since we leverage results of Subtask 2 directly to infer the result of Subtask 1, the paper focus on the system solving Subtask 2. By taking Subtask 2 as a sequence labeling task, our system relies on a recurrent neural network named BiLSTM-CNN-CRF with rich linguistic features, such as POS tags, dependency parsing labels, chunking labels, NER labels, Brown clustering. Our system achieved the highest F1 score in both token level and phrase level.

show abstract

Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation

Cited by 106 publications

References 12 publications

Evaluating deep learning models for sentiment classification

Evaluating deep learning models for sentiment classification

A Neural Architecture for Dialectal Arabic Segmentation

DM_NLP at SemEval-2018 Task 8: neural sequence labeling with linguistic features

Contact Info

Product

Resources

About