Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pages 1576–1586, Lisbon, Portugal, 17-21 September 2015. c⃝2015 Association for Computational Linguistics. Multi-Perspective Sentence Similarity Modeling with Convolutional Neural Networks Hua He,1 Kevin Gimpel,2 and Jimmy Lin3 1 Department of Computer Science, University of Maryland, College Park 2 Toyota Technological Institute at Chicago 3 David R. Cheriton School of Computer Science, University of Waterloo huah@cs.umd.edu, kgimpel@ttic.edu, jimmylin@uwaterloo.ca Abstract Modeling sentence similarity is compli- cated by the ambiguity and variability of linguistic expression. To cope with these challenges, we propose a model for com- paring sentences that uses a multiplicity of perspectives. We first model each sentence using a convolutional neural network that extracts features at multiple levels of gran- ularity and uses multiple types of pooling. We then compare our sentence representa- tions at several granularities using multi- ple similarity metrics. We apply our model to three tasks, including the Microsoft Re- search paraphrase identification task and two SemEval semantic textual similarity tasks. We obtain strong performance on all tasks, rivaling or exceeding the state of the art without using external resources such as WordNet or parsers. 1 Introduction Measuring the semantic relatedness of two pieces of text is a fundamental problem in language processing tasks like plagiarism detection, query ranking, and question answering. In this paper, we address the sentence similarity measurement prob- lem: given a query sentence S1 and a comparison sentence S2, the task is to compute their similar- ity in terms of a score sim(S1, S2). This simi- larity score can be used within a system that de- termines whether two sentences are paraphrases, e.g., by comparing it to a threshold. Measuring sentence similarity is challenging because of the variability of linguistic expression and the limited amount of annotated training data. This makes it difficult to use sparse, hand-crafted features as in conventional approaches in NLP. Re- cent successes in sentence similarity have been ob- tained by using neural networks (Tai et al., 2015; Yin and Sch¨utze, 2015). Our approach is also based on neural networks: we propose a modular functional architecture with two components, sen- tence modeling and similarity measurement. For sentence modeling, we use a convolutional neural network featuring convolution filters with multiple granularities and window sizes, followed by multiple types of pooling. We experiment with two types of word embeddings as well as part- of-speech tag embeddings (Sec. 4). For similar- ity measurement, we compare pairs of local re- gions of the sentence representations, using multi- ple distance functions: cosine distance, Euclidean distance, and element-wise difference (Sec. 5). We demonstrate state-of-the-art performance on two SemEval semantic relatedness tasks (Agirre et al., 2012; Marelli et al., 2014), and highly com- petitive performance on the Microsoft Research paraphrase (MSRP) identification task (Dolan et al., 2004). On the SemEval-2014 task, we match the state-of-the-art dependency tree Long Short- Term Memory (LSTM) neural networks of Tai et al. (2015) without using parsers or part-of- speech taggers. On the MSRP task, we outper- form the recently-proposed …

Content truncated to 500 words