2021/02/10 by Zhuosheng Zhang, Junlong Li, Zhang, Zhuosheng +3
Computer Science · #Artificial Intelligence (cs.AI) #Artificial intelligence #Commonsense knowledge #Commonsense reasoning #Comprehension #Computation and Language (cs.CL) #Computer science #Context (archaeology) #Conversation #FOS: Computer and information sciences #Knowledge representation and reasoning #Linguistics #Matching (statistics) #Multimodal Machine Learning Applications #Natural Language Processing Techniques #Natural language #Natural language processing #Natural language understanding #Question answering #Selection (genetic algorithm) #Topic Modeling #Transformer #cs.AI #cs.CL
paper · pdf · doi:10.48550/arxiv.2102.05474
The early version accepted by IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP)
arxiv created 2021/02/10 · openalex publication_date 2021/02/10 · arxiv updated 2021/02/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Multi-turn dialogue reading comprehension aims to teach machines to read dialogue contexts and solve tasks such as response selection and answering questions. The major challenges involve noisy history contexts and especial prerequisites of commonsense knowledge that is unseen in the given material. Existing works mainly focus on context and response matching approaches. This work thus makes the first attempt to tackle the above two challenges by extracting substantially important turns as pivot utterances and utilizing external knowledge to enhance the representation of context. We propose a pivot-oriented deep selection model (PoDS) on top of the Transformer-based language models for dialogue comprehension. In detail, our model first picks out the pivot utterances from the conversation history according to the semantic matching with the candidate response or question, if any. Besides, knowledge items related to the dialogue context are extracted from a knowledge graph as external knowledge. Then, the pivot utterances and the external knowledge are combined with a well-designed mechanism for refining predictions. Experimental results on four dialogue comprehension benchmark tasks show that our proposed model achieves great improvements on baselines. A series of empirical comparisons are conducted to show how our selection strategies and the extra knowledge injection influence the results.