ITNLP-ARC at SemEval-2018 Task 12: Argument Reasoning Comprehension with Attention

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 1089–1093 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics ITNLP-ARC at SemEval-2018 Task 12: Argument Reasoning Comprehension with Attention Wenjie Liu, Chengjie Sun, Lei Lin, Bingquan Liu School of Computer Science and Technology Harbin Institute of Technology Harbin, China {wjliu, cjsun, linl, liubq}@insun.hit.edu.cn Abstract Reasoning is a very important topic and has many important applications in the field of natural language processing. Semantic Eval- uation (SemEval) 2018 Task 12 “The Argu- ment Reasoning Comprehension” committed to research natural language reasoning. In this task, we proposed a novel argument reasoning comprehension system, ITNLP-ARC, which use Neural Networks technology to solve this problem. In our system, the LSTM model is involved to encode both the premise sen- tences and the warrant sentences. The atten- tion model is used to merge the two premise sentence vectors. Through comparing the sim- ilarity between the attention vector and each of the two warrant vectors, we choose the one with higher similarity as our system’s final an- swer. 1 Introduction Reasoning is a very challenging, but basic part of Natural Language Inference (NLI) (Chen et al., 2017), and many relevant tasks have been pro- posed such as Recognizing Textual Entailment (RTE) and so on. Stanford University provided Stanford Natural Language Inference (SNLI) cor- pus to support Natural Language Inference task. It contained two kinds of sentences-the premise sen- tence and the warrant sentence.The mission is to judge whether the two sentences are inference or not. Semantic Evaluation (SemEval) 2018 Task 12-The Argument Reasoning Comprehension- give an argument consisting of the claim, the rea- son and two warrants. The goal is to select the correct warrant that explains reasoning with this particular argument. There are two options given and only one is correct. Compare with Stanford Natural Language Inference (SNLI) task (Bow- man et al., 2015; Shen et al., 2018), it has more challenges. Because it has abundant premise in- formation such as the reason, the claim, text infor- mation, as well as the option warrants have high semantic textual similarity (Habernal et al., 2017). In this task, we need to find an effective method to extract important information from these premise sentences. Natural Language Reasoning can be applied to various fields such as question and answering, information retrieval and so on. With the de- velopment of Neural Networks applied in Natu- ral Language Processing, sentence representation and reasoning have been researched and taken significant step forwards. In order to deal with the sequence problem, recurrent neural networks (RNN) (Mikolov et al., 2010, 2011) proposes the concept of hidden state, which can extract features from sequence-shaped data and then convert it to output. It can be used to encode the sentence to fixed-length vector representations. In most re- cent years, long short-term memory (LSTM) net- work (Bengio et al., 1994; Hochreiter and Schmid- huber, 1997), BiLSTM (Pennington et al., 2014a) and gated recurrent unit (GRU) (Cho et al., 2014) are widely used to …

Content truncated to 500 words