Question Answering with Character-Level LSTM Encoders and Model-Based Data Augmentation
This paper presents a character-level encoder-decoder mod-eling method for question answering(QA)from large-scale knowledge bases(KB).This method improves the existing approach ”9” from three aspects.First,long short-term memory(LSTM)structures are adopted to replace the convolutional neural networks(CNN)for encoding the can-didate entities and predicates.Second,a new strategy of generating neg-ative samples for model training is adopted.Third,a data augmentation strategy is applied to increase the size of the training set by generating factoid questions using another trained encoder-decoder model.Experi-mental results on the SimpleQuestions dataset and the Freebase5M KB demonstrates the effectiveness of the proposed method,which improves the state-of-the-art accuracy from 70.3%to 78.8%when augmenting the training set with 70,000 generated triple-question pairs.
Question Answering Knowledge Base Long Short-TermMemory Encoder-Decoder
Run-Ze Wang Chen-Di Zhan Zhen-Hua Ling
National Engineering Laboratory for Speech and Language Information Processing,University of Science and Technology of China,Hefei,China
国内会议
第十六届全国计算语言学学术会议暨第五届基于自然标注大数据的自然语言处理国际学术研讨会
南京
英文
1-11
2017-10-13（万方平台首次上网日期，不代表论文的发表时间）