Abstract
Deep learning is the crucial technology in intelligent question answering research tasks. Nowadays, extensive studies on question answering have been conducted by adopting the methods of deep learning. The challenge is that it not only requires an effective semantic understanding model to generate a textual representation but also needs the consideration of semantic interaction between questions and answers simultaneously. In this paper, we propose a stacked Bidirectional Long Short-Term Memory (BiLSTM) neural network based on the coattention mechanism to extract the interaction between questions and answers, combining cosine similarity and Euclidean distance to score the question and answer sentences. Experiments are tested and evaluated on publicly available Text REtrieval Conference (TREC) 8-13 dataset and Wiki-QA dataset. Experimental results confirm that the proposed model is efficient and particularly it achieves a higher mean average precision (MAR) of 0.7613 and mean reciprocal rank (MRR) of 0.8401 on the TREC dataset.
Highlights
Deep learning forms a more abstract high-level representation attribute feature by combining low-level features to discover the distributed feature representations of data
(1) Different from the traditional work of Yih et al [18] and Yu et al [38], who analyzed the problem from the perspective of sentence structure, it can be obviously discovered that both our experiments and many previous studies such as Bidirectional Long Short-Term Memory (BiLSTM) [1] and convolutional neural networks (CNN) [39] have achieved better performance. ese researches show that the semantic analyses of sentences are very necessary for NLP tasks and the deep neural networks are able to make the sentence vectors more representatives
When the number of epoch continues to increase, both mean average precision (MAP) and mean reciprocal rank (MRR) have a slight downward trend. e experimental results prove that the problem-solving of the model architecture analysis in this paper is effective for the sentence semantics, and prove that the model has good accuracy and robustness
Summary
Deep learning forms a more abstract high-level representation attribute feature by combining low-level features to discover the distributed feature representations of data It provides an effective method for NLP research. In the past few years, most question answering studies [2,3,4] were based on knowledge bases and FAQs, which use machine learning to analyze and retrieve keywords. Both of them lack relevant semantic analysis of the questions and answers, which results in a shortcoming of strong artificial dependency and poor scalability
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
