A Cross-Layer Connection Based Approach for Cross-Lingual Open Question Answering
Cross-lingual open domain question answering(Open-QA)has become an increasingly important topic.When training a mono-lingual model,it is often necessary to use a large number of labeled data for supervised training,which makes it difficult to real applica-tions,especially for low-resource languages.Recently,thanks to multi-lingual BERT model,a new task,so called zero-shot cross-lingual QA has emerged in this field,i.e.,training a model for a language rich in resources and directly testing in other languages.The existing problems in the current research include two main points.The one is in document retrieval stage,directly working multilingual pretraining model for simi-larity calculation will result in insufficient retrieval accuracy.The other is in the stage of answer extraction,the answers will involve different levels of abstraction related to retrieved documents,which needs deep explo-ration.This paper puts forward a cross-layer connection based approach for cross-lingual Open-QA.It consists of Match-Retrieval module and Connection-Extraction module.The matching network in the retrieval module makes heuristic adjustment and expansion on the learned fea-tures to improve the retrieval quality.In the answer extraction module,the reuse of deep semantic features is realized at the network structure level through cross-layer connection.Experimental results on a public cross-lingual Open-QA dataset show the superiority of our proposed app-roach over the state-of-the-art methods.
Cross-language Open-QA Semantic feature Heuristic adjustment Cross-layer connection
Lin Li Miao Kong Dong Li Dong Zhou
Wuhan University of Technology,Wuhan,China Hunan University of Science and Technology,Xiangtan,Hunan,China
国际会议
9th CCF International Conference on Natural Language Processing and Chinese Computing (NLPCC 2020)
郑州
英文
470-481
2020-10-14（万方平台首次上网日期，不代表论文的发表时间）