Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model

Proceedings of the 11th International Workshop on Semantic Evaluations (SemEval-2017), pages 164–169, Vancouver, Canada, August 3 - 4, 2017. c⃝2017 Association for Computational Linguistics Neobility at SemEval-2017 Task 1: An Attention-based Sentence Similarity Model WenLi Zhuang ∗ Shan-Si Elementary School ChangHua County, Taiwan bibo9901@gmail.com Ernie Chang Department of Linguistics University of Washington Seattle, WA 98195, USA cyc025@uw.edu Abstract This paper describes a neural-network model which performed competitively (top 6) at the SemEval 2017 cross-lingual Semantic Textual Similarity (STS) task. Our system employs an attention-based recurrent neural network model that op- timizes the sentence similarity. In this paper, we describe our participation in the multilingual STS task which measures similarity across English, Spanish, and Arabic. 1 Introduction Semantic textual similarity (STS) measures the degree of equivalence between the meanings of two text sequences (Agirre et al., 2016). The similarity of the text pair can be represented as discrete or continuous values ranging from irrel- evance (1) to exact semantic equivalence (5). It is widely applicable to many NLP tasks includ- ing summarization (Wong et al., 2008; Nenkova et al., 2011), generation and question answering (Vo et al., 2015), paraphrase detection (Fernando and Stevenson, 2008), and machine translation (Corley and Mihalcea, 2005). In this paper, we describe a system that is able to learn context-sensitive features within the sen- tences. Further, we encode the sequential informa- tion with Recurrent Neural Network (RNN) and perform attention mechanism (Bahdanau et al., 2015) on RNN outputs for both sentences. Atten- tion mechanism was performed to increase sen- sitivity of the system to words of similarity sig- nificance. We also optimize directly on the Pear- son correlation score as part of our neural-based approach. Moreover, we include a pair feature ∗The author is currently serving in his Alternative Mili- tary Service of Education. adapter module that could be used to include more features to further improve performance. How- ever, for this competition we include merely the TakeLab features (ˇSari´c et al., 2012). 1 2 Related Works Most proposed approaches in the past adopted a hybrid of varying text unit sizes ranging from character-based, token-based, to knowledge-based similarity measure (Gomaa and Fahmy, 2013). The linguistic depths of these measures often vary between lexical, syntactic, and semantic levels. Most solutions include an ensemble of modules that employs features coming from different unit sizes and depths. More recent approaches gen- erally include the word embedding-based similar- ity (Liebeck et al., 2016; Brychc´ın and Svoboda, 2016) as a component of the final ensemble. The top performing team in 2016 (Rychalska et al., 2016) uses an ensemble of multiple modules in- cluding recursive autoencoders with WordNet and monolingual aligner (Sultan et al., 2016). UMD- TTIC-UW (He et al., 2016) proposes the MPCNN model that requires no feature engineering and managed to perform competitively at the 6th place. MPCNN is able to extract the hidden information using the Convolutional Neural Network (CNN) and adds an attention layer to extract the vital sim- ilarity information. 3 Methods 3.1 Model Given two sentences I1 …

Content truncated to 500 words