Paper Info
Title
Paraphrase thought: Sentence embedding module imitating human language recognition
Abstract
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for various natural language processing tasks, such as machine translation and document classification. Thus far, various sentence embedding models have been proposed, and their feasibility has been demonstrated through good performances on tasks following embedding, such as sentiment analysis and sentence classification. However, because the performances of sentence classification and sentiment analysis can be enhanced by using a simple sentence representation method, it is not sufficient to claim that these models fully reflect the meanings of sentences based on good performances for such tasks. In this paper, inspired by human language recognition, we propose the following concept of semantic coherence, which should be satisfied for a good sentence embedding method: similar sentences should be located close to each other in the embedding space. Then, we propose the Paraphrase-Thought (P-thought) model to pursue semantic coherence as much as possible. Experimental results on three paraphrase identification datasets (MS COCO, STS benchmark, SICK) show that the P-thought models outperform the benchmarked sentence embedding methods.
Year
DOI
Venue
2018
10.1016/j.ins.2020.05.129
Information Sciences
Keywords
Field
DocType
Sentence embedding,Recurrent neural network,Paraphrase,Semantic coherence,Natural language processing
Document classification,Embedding,Sentiment analysis,Computer science,Machine translation,Coherence (physics),Paraphrase,Language recognition,Natural language processing,Artificial intelligence,Sentence
Journal
Volume
ISSN
Citations 
541
0020-0255
1
PageRank 
References 
Authors
0.35
0
2
Name
Order
Citations
PageRank
Myeongjun Jang110.35
Pilsung Kang233928.22