Attention-based LSTM Network for Cross-Lingual Sentiment Classification
By Xinjie Zhou, Xiaojun Wan, Jianguo Xiao. 2016
261 citations recorded by the source corpus.
Most of the state-of-the-art sentiment classifi-cation methods are based on supervised learning algorithms which require large amounts of manually labeled data. However, the labeled resources are usually imbalanced in different languages. Cross-lingual sentiment classification tackles the problem by adapting the sentiment resources in a resource-rich language to resource-poor languages. In this study, we propose an attention-based bilingual representation learning model which learns the distributed semantics of the documents in both the source and the target languages. In each language, we use Long Short Term Memory (LSTM) network to model the documents, which has been proved to be very effective for word sequences. Meanwhile, we propose a hierarchical attention mechanism for the bilingual LSTM network. The sentence-level attention model learns which sentences of a document are more important for determining the overall sentiment while the word-level attention model learns which words in each sentence are decisive. The proposed model achieves good results on a benchmark dataset using English as the source language and Chinese as the target language.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
Citations in the corpus
- Joint Embedding of Words and Labels for Text Classification (2018, methodology): “, 2015), with successful applications to sentiment classification (Zhou et al., 2016), sentence pair modeling (Yin et al.”
- Sentiment Classification by Leveraging the Shared Knowledge from a Sequence of Domains (2019, background): “Many neural network based sentiment classification techniques have been reported [4,27,32,41,48].”
- A Survey on Text Classification: From Traditional to Deep Learning (2020, background): “2016 BI-Attention [110] NAACL SA Accuracy NLP&CC 2013 [111] 2016 LSTMN [112] EMNLP SA [113] Accuracy SST-1 2017 Lin et al.”
- Deep learning for sentiment analysis: A survey (2018, background): “Word embeddings to dense document vector Input encoder and LSTM Hierarchical attention Aspect/target information Zhou et al.(46) Word embeddings to dense document vector LSTM Hierarchical attention Cross-lingual information Li et al.”
- A review on the long short-term memory model (2020, methodology): “Zhou et al. (2016) used an attention-based BLSTM to model bilingual texts with the goal of cross-language sentiment classification.”
- Learning with Limited Data for Multilingual Reading Comprehension (2019, methodology): “Not only for question answering, such method has been successful in sentiment classication (Zhou et al., 2016), relation extraction (Faruqui and Kumar, 2015), and causal commonsense (Yeo et al.”
- Deep Learning--based Text Classification (2020, background): “[80] extend the hierarchical attention model to cross-lingual sentiment classification.”
- Document Re-Ranking Model for Machine-Reading and Comprehension (2020, background): “In Equation (2), ↔ Pn denotes an n-gram phrase vector of a passage, and Q̃n denotes an n-gram phrase vector of a query mapped onto the dQ̃n dimension using a conventional pooling mechanism [19].”
- A Survey on Text Classification: From Shallow to Deep Learning (2020, background): “BI-Attention [125] is proposed for cross-lingual text classification to catch bilingual long-distance dependencies.”