Filters








972,854 Hits in 5.2 sec

Accelerating Real-Time Question Answering via Question Generation [article]

Yuwei Fang, Shuohang Wang, Zhe Gan, Siqi Sun, Jingjing Liu, Chenguang Zhu
2021 arXiv   pre-print
of Questions), which introduces a new question generation (QG) model to generate a large pool of QA pairs offline, then in real time matches an input question with the candidate QA pool to predict the  ...  To reduce the computational cost and accelerate real-time question answering (RTQA) for practical usage, we propose to remove all the neural networks from online QA systems, and present Ocean-Q (an Ocean  ...  Moreover, to the best of our knowledge, we are the first work to connect neural question generator with real-time question answering.  ... 
arXiv:2009.05167v2 fatcat:sqy6s5f2jvbyfpltataeayoozm

Meaningful Answer Generation of E-Commerce Question-Answering [article]

Shen Gao, Xiuying Chen, Zhaochun Ren, Dongyan Zhao, Rui Yan
2020 arXiv   pre-print
Finally, we propose an answer editor to generate the final answer by taking the question and the above parts as input.  ...  Our key idea is to obtain the correct question-aware information from a large scale collection of reviews and learn how to write a coherent and meaningful answer from an existing prototype answer.  ...  ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their constructive comments. We would also like to thank Anna  ... 
arXiv:2011.07307v1 fatcat:vweubhp7wbg4rjclgyat7atsey

Product-Aware Answer Generation in E-Commerce Question-Answering [article]

Shen Gao, Zhaochun Ren, Yihong Eric Zhao, Dongyan Zhao, Dawei Yin, Rui Yan
2019 arXiv   pre-print
To extract the salience part of reviews, an attention-based review reader is proposed to capture the most relevant words given the question.  ...  Specifically, we employ a convolutional discriminator to distinguish whether our generated answer matches the facts.  ...  ACKNOWLEDGMENTS We would like to thank the anonymous reviewers for their constructive comments.  ... 
arXiv:1901.07696v2 fatcat:lskfjm4jtzdhzo6y2mggc7cify

Neural Question Generation with Answer Pivot

Bingning Wang, Xiaochuan Wang, Ting Tao, Qi Zhang, Jingfang Xu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
Previous answer-aware NQG methods suffer from the problem that the generated answers are focusing on entity and most of the questions are trivial to be answered.  ...  In this paper, we treat the answers as the hidden pivot for question generation and combine the question generation and answer selection process in a joint model.  ...  Acknowledgments We thank the anonymous reviewers for their helpful comments.  ... 
doi:10.1609/aaai.v34i05.6449 fatcat:mmr62vdeyvgdnpypsrh7pqa5em

Opinion-aware Answer Generation for Review-driven Question Answering in E-Commerce [article]

Yang Deng, Wenxuan Zhang, Wai Lam
2020 arXiv   pre-print
the question and reviews to capture important information for answer generation, (ii) aggregating diverse opinion information to uncover the common opinion towards the given question.  ...  Two kinds of opinion fusion strategies, namely, static and dynamic fusion, are proposed to distill and aggregate important opinion information learned from the opinion mining task into the answer generation  ...  most influential review during the whole generation process.  ... 
arXiv:2008.11972v2 fatcat:uncuhn3qrneo7jbdbb5by2sreq

Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering [article]

Yang Deng, Wai Lam, Yuexiang Xie, Daoyuan Chen, Yaliang Li, Min Yang, Ying Shen
2019 arXiv   pre-print
To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model.  ...  Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating  ...  However, due to the length of answers, extractive methods sometimes fall short of generalization of all the important information in the whole answer and consistency of the core idea.  ... 
arXiv:1911.09801v1 fatcat:vhqqmmswzrbr7kvxliswoivikm

QA4QG: Using Question Answering to Constrain Multi-Hop Question Generation [article]

Dan Su, Peng Xu, Pascale Fung
2022 arXiv   pre-print
Multi-hop question generation (MQG) aims to generate complex questions which require reasoning over multiple pieces of information of the input passage.  ...  It augments the standard BART model with an additional multi-hop QA module to further constrain the generated question.  ...  We believe the A sof t generated by the HGN model, 2 when trained to answer multi-hop question, can naturally learn the answeraware multi-hop information related to the question inside the context C.  ... 
arXiv:2202.06538v1 fatcat:dmhtinvwcrfe5m7eflzfm3idd4

Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering [article]

Shiyue Zhang, Mohit Bansal
2019 arXiv   pre-print
., the semantics of the model-generated question drifts away from the given context and answer.  ...  In this paper, we first propose two semantics-enhanced rewards obtained from downstream question paraphrasing and question answering tasks to regularize the QG model to generate semantically valid questions  ...  The views contained in this article are those of the authors and not of the funding agency.  ... 
arXiv:1909.06356v1 fatcat:i3tk3v4525hnhi4givw524fidm

Improving Neural Question Generation using Answer Separation [article]

Yanghoon Kim and Hwanhee Lee and Joongbo Shin and Kyomin Jung
2018 arXiv   pre-print
By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used.  ...  Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks.  ...  This approach to separate the target answer from the passage helps our model to identify the question type related to the target answer because the model learns to capture the position and contextual information  ... 
arXiv:1809.02393v2 fatcat:cpcnlyxgrnabjfrorjin37r3w4

Answer Generating Methods for Community Question and Answering Portals [chapter]

Haoxiong Tao, Yu Hao, Xiaoyan Zhu
2012 Communications in Computer and Information Science  
Community users can search questions in cQA portals, but the returning answers often contain information which is redundant or irrelevant to the questions.  ...  The results show that the answer generating methods can improve the answer quality significantly.  ...  This work was carried out with the aid of a grant from the International Development Research Center, Ottawa, Canada, number:104519-006.  ... 
doi:10.1007/978-3-642-34456-5_23 fatcat:2666hcnk4vdnbmrzzooxuuxbhm

Improving Question Generation with Sentence-level Semantic Matching and Answer Position Inferring [article]

Xiyao Ma, Qile Zhu, Yanlin Zhou, Xiaolin Li, Dapeng Wu
2020 arXiv   pre-print
Taking an answer and its context as input, sequence-to-sequence models have made considerable progress on question generation.  ...  Owing to its generality, our work also improves the existing models significantly.  ...  Acknowledgement This research was supported by CBL industry and agency members and by the IUCRC Program of the National Science Foundation under Grant No. CNS-1747783.  ... 
arXiv:1912.00879v3 fatcat:gmimwqqbtngg7c6tfopq7skmcu

Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data [article]

Fanyi Qu, Xin Jia, Yunfang Wu
2021 arXiv   pre-print
Accordingly, we propose a multi-agent communication model to generate and optimize the question and keyphrases iteratively, and then apply the generated question and keyphrases to guide the generation  ...  To capture the important information of the input passage we first automatically generate(rather than extracting) keyphrases, thus this task is reduced to keyphrase-question-answer triplet joint generation  ...  Acknowledgement This work is supported in part by the National Hi-Tech RD Program of China (No. 2020AAA0106600), the National Natural Science Foundation of China (No.62076008, No.61773026).  ... 
arXiv:2109.05179v2 fatcat:sjemkrozwnfshcywyv5672oiju

Challenges in Generalization in Open Domain Question Answering [article]

Linqing Liu, Patrick Lewis, Sebastian Riedel, Pontus Stenetorp
2022 arXiv   pre-print
is 13.1/5.4% and 9.6/1.5% lower compared to that for the full test set -- indicating the challenge posed by these types of questions.  ...  Drawing upon studies on systematic generalization, we introduce and annotate questions according to three categories that measure different levels and kinds of generalization: training set overlap, compositional  ...  Despite the success for various datasets, there is little work analyzing the whole pipeline of question answering systems.  ... 
arXiv:2109.01156v3 fatcat:ijma4hbgxnc2pod6mmnpl7bxuq

Improving Neural Question Generation Using Answer Separation

Yanghoon Kim, Hwanhee Lee, Joongbo Shin, Kyomin Jung
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
By replacing the target answer in the original passage with a special token, our model learns to identify which interrogative word should be used.  ...  Neural question generation (NQG) is the task of generating a question from a given passage with deep neural networks.  ...  This approach to separate the target answer from the passage helps our model to identify the question type related to the target answer because the model learns to capture the position and contextual information  ... 
doi:10.1609/aaai.v33i01.33016602 fatcat:anx2sx4eifhtbkdiul23mn6334

Joint Learning of Answer Selection and Answer Summary Generation in Community Question Answering

Yang Deng, Wai Lam, Yuexiang Xie, Daoyuan Chen, Yaliang Li, Min Yang, Ying Shen
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To solve these problems, we tackle the tasks of answer selection and answer summary generation in CQA with a novel joint learning model.  ...  Specifically, we design a question-driven pointer-generator network, which exploits the correlation information between question-answer pairs to aid in attending the essential information when generating  ...  However, due to the length of answers, extractive methods sometimes fall short of generalization of all the important information in the whole answer and consistency of the core idea.  ... 
doi:10.1609/aaai.v34i05.6266 fatcat:oxlfvs7hvndypmyxrwaeclgtcy
« Previous Showing results 1 — 15 out of 972,854 results