YNU Deep at SemEval-2018 Task 12: A BiLSTM Model with Neural Attention for Argument Reasoning Comprehension

Proceedings of the 12th International Workshop on Semantic Evaluation (SemEval-2018), pages 1120–1123 New Orleans, Louisiana, June 5–6, 2018. ©2018 Association for Computational Linguistics YNU Deep at SemEval-2018 Task 12: A BiLSTM Model with Neural Attention for Argument Reasoning Comprehension Peng Ding, Xiaobing Zhou∗ School of Information Science and Engineering Yunnan University, Yunnan, P.R. China ∗Corresponding author, zhouxb.cn@gmail.com Abstract This paper describes the system submitted to SemEval-2018 Task 12 (The Argument Rea- soning Comprehension Task). Enabling a computer to understand a text so that it can an- swer comprehension questions is still a chal- lenging goal of NLP. We propose a Bidirec- tional LSTM (BiLSTM) model that reads two sentences separated by a delimiter to deter- mine which warrant is correct. We extend this model with a neural attention mechanism that encourages the model to make reasoning over the given claims and reasons. Officially re- leased results show that our system ranks 6th among 22 submissions to this task. 1 Introduction Machine comprehension of text is an important problem in natural language processing. Tra- ditional approaches to machine comprehension are based on either hand engineered grammars (Riloff and Thelen, 2000), or information extrac- tion methods (Poon et al., 2010). Recently, recurrent neural networks (RNNs) with long short-term memory (LSTM) cells (Hochreiter and Schmidhuber, 1997) have been successfully applied to a wide range of NLP tasks, such as machine translation (Sutskever et al., 2014), constituency parsing (Vinyals et al., 2015), language modeling (Zaremba et al., 2014) and ma- chine comprehension (Hermann et al., 2015). A potential issue with the LSTM models is that a neural network needs to be able to compress all the necessary information of a source sentence into a fixed-length vector (Bahdanau et al., 2014). This may make it difficult for the neural network to cope with long sentences. In order to address this issue, attention mechanisms have been success- fully extended to the LSTMs. Attentive Reader (Hermann et al., 2015) used a tanh layer to com- pute the attention between document and question embeddings. This allows a model to focus on the aspects of a document that it believes helpful to an- swer a question. The attention-based LSTM mod- els have achieved state-of-the-art results in ma- chine comprehension tasks (Kadlec et al., 2016; Chen et al., 2016; Tseng et al., 2016). The argument reasoning comprehension task has been presented by (Habernal et al., 2018). The problem can be described as follows: Given an argument consisting of a claim and a reason, the goal is to select the correct warrant that explains reasoning of this particular argument. Compared to traditional machine comprehension task, argu- ment reasoning comprehension requires models to possess extra reasoning abilities. Some mod- els increase the depth of the network, continu- ously updating the representations of the docu- ments and questions to realize the reasoning pro- cess (Sukhbaatar et al., 2015; Tseng et al., 2016; Dhingra et al., 2017; Sordoni et al., 2016). In this paper, we use a BiLSTM model to en- code the reason …

Content truncated to 500 words