专栏首页专知【论文推荐】最新六篇自动问答相关论文—排序函数、文本摘要评估、信息抽取框架、层次递归编码器、半监督问答

【论文推荐】最新六篇自动问答相关论文—排序函数、文本摘要评估、信息抽取框架、层次递归编码器、半监督问答

【导读】既前两天推出十三篇自动问答(Question Answering)相关文章,专知内容组今天又推出六篇自动问答相关文章,为大家进行介绍,欢迎查看!

14. Training a Ranking Function for Open-Domain Question Answering(训练排序函数对开放式问题进行回答)



作者:Phu Mon Htut,Samuel R. Bowman,Kyunghyun Cho

机构:New York University

摘要:In recent years, there have been amazing advances in deep learning methods for machine reading. In machine reading, the machine reader has to extract the answer from the given ground truth paragraph. Recently, the state-of-the-art machine reading models achieve human level performance in SQuAD which is a reading comprehension-style question answering (QA) task. The success of machine reading has inspired researchers to combine information retrieval with machine reading to tackle open-domain QA. However, these systems perform poorly compared to reading comprehension-style QA because it is difficult to retrieve the pieces of paragraphs that contain the answer to the question. In this study, we propose two neural network rankers that assign scores to different passages based on their likelihood of containing the answer to a given question. Additionally, we analyze the relative importance of semantic similarity and word level relevance matching in open-domain QA.

期刊:arXiv, 2018年4月12日

网址

http://www.zhuanzhi.ai/document/bd075132f2b950ddfe3129606b6695cd

15. A Semantic QA-Based Approach for Text Summarization Evaluation(一种基于QA的文本摘要评估方法)



作者:Ping Chen,Fei Wu,Tong Wang,Wei Ding

机构:University of Massachusetts Boston

摘要:Many Natural Language Processing and Computational Linguistics applications involves the generation of new texts based on some existing texts, such as summarization, text simplification and machine translation. However, there has been a serious problem haunting these applications for decades, that is, how to automatically and accurately assess quality of these applications. In this paper, we will present some preliminary results on one especially useful and challenging problem in NLP system evaluation: how to pinpoint content differences of two text passages (especially for large pas-sages such as articles and books). Our idea is intuitive and very different from existing approaches. We treat one text passage as a small knowledge base, and ask it a large number of questions to exhaustively identify all content points in it. By comparing the correctly answered questions from two text passages, we will be able to compare their content precisely. The experiment using 2007 DUC summarization corpus clearly shows promising results.

期刊:arXiv, 2018年4月11日

网址

http://www.zhuanzhi.ai/document/bd075132f2b950ddfe3129606b6695cd

16. QA4IE: A Question Answering based Framework for Information Extraction(QA4IE:一个基于问答的信息抽取框架)



作者:Lin Qiu,Hao Zhou,Yanru Qu,Weinan Zhang,Suoheng Li,Shu Rong,Dongyu Ru,Lihua Qian,Kewei Tu,Yong Yu

机构:Shanghai Jiao Tong University

摘要:Information Extraction (IE) refers to automatically extracting structured relation tuples from unstructured texts. Common IE solutions, including Relation Extraction (RE) and open IE systems, can hardly handle cross-sentence tuples, and are severely restricted by limited relation types as well as informal relation specifications (e.g., free-text based relation tuples). In order to overcome these weaknesses, we propose a novel IE framework named QA4IE, which leverages the flexible question answering (QA) approaches to produce high quality relation triples across sentences. Based on the framework, we develop a large IE benchmark with high quality human evaluation. This benchmark contains 293K documents, 2M golden relation triples, and 636 relation types. We compare our system with some IE baselines on our benchmark and the results show that our system achieves great improvements.

期刊:arXiv, 2018年4月10日

网址

http://www.zhuanzhi.ai/document/100545a8407b2ec4d748cbf7579edbeb

17. Learning to Rank Question-Answer Pairs using Hierarchical Recurrent Encoder with Latent Topic Clustering(学习用层次式递归编码器和潜在的主题聚类对问题回答对进行排序)



作者:Seunghyun Yoon,Joongbo Shin,Kyomin Jung

机构:Seoul National University

摘要:In this paper, we propose a novel end-to-end neural architecture for ranking candidate answers, that adapts a hierarchical recurrent neural network and a latent topic clustering module. With our proposed model, a text is encoded to a vector representation from an word-level to a chunk-level to effectively capture the entire meaning. In particular, by adapting the hierarchical structure, our model shows very small performance degradations in longer text comprehension while other state-of-the-art recurrent neural network models suffer from it. Additionally, the latent topic clustering module extracts semantic information from target samples. This clustering module is useful for any text related tasks by allowing each data sample to find its nearest topic cluster, thus helping the neural network model analyze the entire data. We evaluate our models on the Ubuntu Dialogue Corpus and consumer electronic domain question answering dataset, which is related to Samsung products. The proposed model shows state-of-the-art results for ranking question-answer pairs.

期刊:arXiv, 2018年4月9日

网址

http://www.zhuanzhi.ai/document/3ed10f562bf0cb5d81c85a7ee339969f

18. Simple and Effective Semi-Supervised Question Answering(简单有效的半监督问答)



作者:Bhuwan Dhingra,Danish Pruthi,Dheeraj Rajagopal

机构:Carnegie Mellon University

摘要:Recent success of deep learning models for the task of extractive Question Answering (QA) is hinged on the availability of large annotated corpora. However, large domain specific annotated corpora are limited and expensive to construct. In this work, we envision a system where the end user specifies a set of base documents and only a few labelled examples. Our system exploits the document structure to create cloze-style questions from these base documents; pre-trains a powerful neural network on the cloze style questions; and further fine-tunes the model on the labeled examples. We evaluate our proposed system across three diverse datasets from different domains, and find it to be highly effective with very little labeled data. We attain more than 50% F1 score on SQuAD and TriviaQA with less than a thousand labelled examples. We are also releasing a set of 3.2M cloze-style questions for practitioners to use while building QA systems.

期刊:arXiv, 2018年4月3日

网址

http://www.zhuanzhi.ai/document/6036d026edb9f761e3a61d4ac11b61bc

19. Pay More Attention - Neural Architectures for Question-Answering(更多的关注-基于神经结构的问答)



作者:Zia Hasan,Sebastian Fischer

摘要:Machine comprehension is a representative task of natural language understanding. Typically, we are given context paragraph and the objective is to answer a question that depends on the context. Such a problem requires to model the complex interactions between the context paragraph and the question. Lately, attention mechanisms have been found to be quite successful at these tasks and in particular, attention mechanisms with attention flow from both context-to-question and question-to-context have been proven to be quite useful. In this paper, we study two state-of-the-art attention mechanisms called Bi-Directional Attention Flow (BiDAF) and Dynamic Co-Attention Network (DCN) and propose a hybrid scheme combining these two architectures that gives better overall performance. Moreover, we also suggest a new simpler attention mechanism that we call Double Cross Attention (DCA) that provides better results compared to both BiDAF and Co-Attention mechanisms while providing similar performance as the hybrid scheme. The objective of our paper is to focus particularly on the attention layer and to suggest improvements on that. Our experimental evaluations show that both our proposed models achieve superior results on the Stanford Question Answering Dataset (SQuAD) compared to BiDAF and DCN attention mechanisms.

期刊:arXiv, 2018年3月25日

网址

http://www.zhuanzhi.ai/document/9923a1c986b1e65f0eb7060a305c864d

-END-

专 · 知

本文分享自微信公众号 - 专知(Quan_Zhuanzhi),作者:专知内容组

原文出处及转载信息见文内详细说明,如有侵权,请联系 yunjia_community@tencent.com 删除。

原始发表时间:2018-05-10

本文参与腾讯云自媒体分享计划,欢迎正在阅读的你也加入,一起分享。

我来说两句

0 条评论
登录 后参与评论

相关文章

  • 学界 | NLP年度盛宴EMNLP/CoNLL 2018最精彩论文精选(摘要+评论)

    每年,全球最顶尖的NLP研究者们会在这两个大会上展示最前沿的NLP科研成果。然而,动辄上千篇的论文却令很多关注NLP领域最新动态的小伙伴望而却步。

    zenRRan
  • 学界 | NLP年度盛宴EMNLP/CoNLL 2018最精彩论文精选(摘要+评论)

    每年,全球最顶尖的NLP研究者们会在这两个大会上展示最前沿的NLP科研成果。然而,动辄上千篇的论文却令很多关注NLP领域最新动态的小伙伴望而却步。

    大数据文摘
  • 今日 Paper | 强化学习;可重构GANs;BachGAN;时间序列分类等

    论文名称:Ranking Sentences for Extractive Summarization with Reinforcement Learning

    AI科技评论
  • 干货|当深度学习遇见自动文本摘要,seq2seq+attention

    昱良
  • 【论文】NAACL2019 抽取式摘要之 SUMO

    论文题目:Single Document Summarization as Tree Induction

    zenRRan
  • 当深度学习遇见自动文本摘要

    | 导语 随着近几年文本信息的爆发式增长,人们每天能接触到海量的文本信息,如新闻、博客、聊天、报告、论文、微博等。从大量文本信息中提取重要的内容,已成为我们的一...

    腾讯知文实验室
  • 当深度学习遇见自动文本摘要

    随着近几年文本信息的爆发式增长,人们每天能接触到海量的文本信息,从大量文本信息中提取重要的内容,已成为我们的一个迫切需求。

    云加社区
  • 深度学习盛会 ICLR-17 最佳论文出炉!机器自主编程 NPI 再称雄

    1 新智元编译 来源:iclr.cc、openreview.net 编译:闻菲、张易、刘小芹 【新智元导读】深度学习盛会 ICLR 2017 日程及最佳论文...

    新智元
  • 精选论文 | 自然语言处理中的语言模型预训练方法【附打包下载】

    最近,在自然语言处理(NLP)领域中,使用语言模型预训练方法在多项 NLP 任务上都获得了不错的提升,广泛受到了各界的关注。今天,两位主讲嘉宾为大家精选了近期语...

    马上科普尚尚

扫码关注云+社区

领取腾讯云代金券