专栏首页专知【论文推荐】最新六篇聊天机器人相关论文—弱监督信息、内容驱动、对话管理系统、可扩展情感序列到序列、自主性

【论文推荐】最新六篇聊天机器人相关论文—弱监督信息、内容驱动、对话管理系统、可扩展情感序列到序列、自主性

【导读】专知内容组整理了最近六篇聊天机器人(Chatbot)相关文章,为大家进行介绍,欢迎查看!

1. Learning Matching Models with Weak Supervision for Response Selection in Retrieval-based Chatbots(利用弱监督信息学习匹配模型以实现基于检索的聊天机器人的响应选择)



作者:Yu Wu,Wei Wu,Zhoujun Li,Ming Zhou

accepted by ACL 2018 as a short paper

机构:Beihang University, Microsoft Research

摘要:We propose a method that can leverage unlabeled data to learn a matching model for response selection in retrieval-based chatbots. The method employs a sequence-to-sequence architecture (Seq2Seq) model as a weak annotator to judge the matching degree of unlabeled pairs, and then performs learning with both the weak signals and the unlabeled data. Experimental results on two public data sets indicate that matching models get significant improvements when they are learned with the proposed method.

期刊:arXiv, 2018年5月7日

网址

http://www.zhuanzhi.ai/document/c08d5aaf08a1e82547380d311740afc5

2. Sounding Board: A User-Centric and Content-Driven Social Chatbot(Sounding Board:用户为中心内容驱动的社交聊天机器人)



作者:Hao Fang,Hao Cheng,Maarten Sap,Elizabeth Clark,Ari Holtzman,Yejin Choi,Noah A. Smith,Mari Ostendorf

NAACL 2018

机构:University of Washington

摘要:We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize. The system architecture consists of several components including spoken language processing, dialogue management, language generation, and content management, with emphasis on user-centric and content-driven design. We also share insights gained from large-scale online logs based on 160,000 conversations with real-world users.

期刊:arXiv, 2018年4月26日

网址

http://www.zhuanzhi.ai/document/f472bfcd8af4449a5213d8e50a2bccfd

3. Improv Chat: Second Response Generation for Chatbot



作者:Furu Wei

机构:Microsoft Research Asia

摘要:Existing research on response generation for chatbot focuses on \textbf{First Response Generation} which aims to teach the chatbot to say the first response (e.g. a sentence) appropriate to the conversation context (e.g. the user's query). In this paper, we introduce a new task \textbf{Second Response Generation}, termed as Improv chat, which aims to teach the chatbot to say the second response after saying the first response with respect the conversation context, so as to lighten the burden on the user to keep the conversation going. Specifically, we propose a general learning based framework and develop a retrieval based system which can generate the second responses with the users' query and the chatbot's first response as input. We present the approach to building the conversation corpus for Improv chat from public forums and social networks, as well as the neural networks based models for response matching and ranking. We include the preliminary experiments and results in this paper. This work could be further advanced with better deep matching models for retrieval base systems or generative models for generation based systems as well as extensive evaluations in real-life applications.

期刊:arXiv, 2018年5月10日

网址

http://www.zhuanzhi.ai/document/02208768d2bbeb287f103e33466ee06c

4. An Ontology-Based Dialogue Management System for Banking and Finance Dialogue Systems(用于银行和金融对话的基于本体的对话管理系统)



作者:Duygu Altinok

机构:4Com Innovation Center

摘要:Keeping the dialogue state in dialogue systems is a notoriously difficult task. We introduce an ontology-based dialogue manage(OntoDM), a dialogue manager that keeps the state of the conversation, provides a basis for anaphora resolution and drives the conversation via domain ontologies. The banking and finance area promises great potential for disambiguating the context via a rich set of products and specificity of proper nouns, named entities and verbs. We used ontologies both as a knowledge base and a basis for the dialogue manager; the knowledge base component and dialogue manager components coalesce in a sense. Domain knowledge is used to track Entities of Interest, i.e. nodes (classes) of the ontology which happen to be products and services. In this way we also introduced conversation memory and attention in a sense. We finely blended linguistic methods, domain-driven keyword ranking and domain ontologies to create ways of domain-driven conversation. Proposed framework is used in our in-house German language banking and finance chatbots. General challenges of German language processing and finance-banking domain chatbot language models and lexicons are also introduced. This work is still in progress, hence no success metrics have been introduced yet.

期刊:arXiv, 2018年4月13日

网址

http://www.zhuanzhi.ai/document/84d12f7e1fd1910373748ea1c5bde87f

5. Scalable Sentiment for Sequence-to-sequence Chatbot Response with Performance Analysis(基于可扩展情感序列到序列聊天机器人响应的性能分析)



作者:Chih-Wei Lee,Yau-Shian Wang,Tsung-Yuan Hsu,Kuan-Yu Chen,Hung-Yi Lee,Lin-shan Lee

机构:National Taiwan University

摘要:Conventional seq2seq chatbot models only try to find the sentences with the highest probabilities conditioned on the input sequences, without considering the sentiment of the output sentences. Some research works trying to modify the sentiment of the output sequences were reported. In this paper, we propose five models to scale or adjust the sentiment of the chatbot response: persona-based model, reinforcement learning, plug and play model, sentiment transformation network and cycleGAN, all based on the conventional seq2seq model. We also develop two evaluation metrics to estimate if the responses are reasonable given the input. These metrics together with other two popularly used metrics were used to analyze the performance of the five proposed models on different aspects, and reinforcement learning and cycleGAN were shown to be very attractive. The evaluation metrics were also found to be well correlated with human evaluation.

期刊:arXiv, 2018年4月7日

网址

http://www.zhuanzhi.ai/document/4d8fffd30b46c6945ea8bc2682c2527b

6. On Chatbots Exhibiting Goal-Directed Autonomy in Dynamic Environments(动态环境中聊天机器人如何展示面向目标的自主性)



作者:Biplav Srivastava

机构:IBM Research

摘要:Conversation interfaces (CIs), or chatbots, are a popular form of intelligent agents that engage humans in task-oriented or informal conversation. In this position paper and demonstration, we argue that chatbots working in dynamic environments, like with sensor data, can not only serve as a promising platform to research issues at the intersection of learning, reasoning, representation and execution for goal-directed autonomy; but also handle non-trivial business applications. We explore the underlying issues in the context of Water Advisor, a preliminary multi-modal conversation system that can access and explain water quality data.

期刊:arXiv, 2018年3月27日

网址

http://www.zhuanzhi.ai/document/441588db5c34c07e5584affd0c319b24

-END-

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:2018-05-12

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

  • 重磅!一文彻底读懂智能对话系统!当前研究综述和未来趋势

    作者:蒙 康 编辑:王抒伟 笔者在最近的研究中发现了一篇非常好的有关对话系统的论文,《A Survey on Dialogue Systems:Recent...

    机器学习算法工程师
  • 机器人聊天的秘密|硬创公开课

    语义理解简单来说,就是让计算机听懂用户说了什么,然后可以进一步回答用户的问题或与用户对话。这类技术在现实场景中的应用有大家比较熟知的微软小冰与百度度秘。锤子手机...

    AI研习社
  • 万字长文科普:人工智能是什么?它又是如何工作的呢?

    关于 “AI 的定义” 这一问题,不同的人有不同的答案。 普通人可能会把 AI 和机器人联系起来,认为 AI 是能够独立行动和思考的人类终结者。但是对于 AI ...

    deephub
  • 苏州大学张民教授两小时讲座精华摘录:自然语言处理方法与应用

    2018 中国人工智能大会(CCAI 2018)于 7 月 28 日-29 日于深圳召开。「过去未去,未来已来」,李德毅院士在 CCAI 2018 开幕式上对人...

    AI科技评论
  • 【每周NLP论文推荐】 NLP中命名实体识别从机器学习到深度学习的代表性研究

    NER是自然语言处理中相对比较基础的任务,但却是非常重要的任务。在NLP中,大部分的任务都需要NER的能力,例如,聊天机器人中,需要NER来提取实体完成对用户输...

    用户1508658
  • KDD 2020 | 时间序列相关论文一览(附原文源码)

    ACM SIGKDD(Conference on Knowledge Discovery and Data Mining, KDD)是世界数据挖掘领域的最高级...

    VachelHu
  • AAAI2019录用论文选读

    AAAI Conference是由美国人工智能协会(the Association for the Advance of Artificial Intellig...

    马上科普尚尚
  • 回顾 | CVPR 2017完全指北:深度学习与计算机视觉融合的一年,未来又会是什么?

    机器之心(海外)原创 作者:QW、CZ 参与:王灏、Panda 当地时间 7 月 21 日到 16 日,夏威夷火奴鲁鲁迎来了 2017 年计算机视觉与模式识别会...

    机器之心
  • 三巨头共聚AAAI:Capsule没有错,LeCun看好自监督,Bengio谈注意力

    2 月 7 日,人工智能顶会 AAAI 2020(第 34 届 AAAI 大会)已于美国纽约正式拉开序幕,本届会议将持续到 2 月 12 日结束。受疫情影响,中...

    磐创AI
  • 人机对话技术研究进展与思考

    导读:本次分享的主题为人机对话技术研究进展与思考。主要梳理了我们团队近两年的工作,渴望可以通过这样的介绍,能给大家一个关于人机对话 ( 包括它的科学问题和应用技...

    DataFunTalk
  • 学界 | 顶会见闻系列:ICML 2018(上),表示学习、网络及关系学习

    AI 科技评论按:本篇属于「顶会见闻系列」。每年这么多精彩的人工智能/机器学习会议,没去现场的自然可惜,在现场的也容易看花眼。那么事后看看别的研究员的见闻总结,...

    AI科技评论
  • AI和机器学习的A~Z:综合术语表

    不知道是否知道......但人工智能存在很多误解。虽然有些人认为这意味着机器人会与人类进行互动,但其他人则认为这是一种超级智能,很快将会占领世界。好吧,这是非常...

    代码医生工作室
  • 强化学习之原理与应用

    强化学习特别是深度强化学习近年来取得了令人瞩目的成就,除了应用于模拟器和游戏领域,在工业领域也正取得长足的进步。百度是较早布局强化学习的公司之一。这篇文章系统地...

    用户1386409
  • 【趋势】Yoshua Bengio: 机器的梦可以让我们实现无监督学习

    【新智元导读】“让机器会做梦,从某种程度上来说,是人工智能发展的一个关键技能”,Bengio在接受O‘reilly的采访时说到。在这里,“做梦”代表的是想象的能...

    新智元
  • 7 Papers | 清华天机芯片;非侵入式脑机接口;ACL 2019论文

    1. 标题:Towards artificial general intelligence with hybrid Tianjic chip architect...

    机器之心
  • 三巨头共聚AAAI:Capsule没有错,LeCun看好自监督,Bengio谈注意力

    2 月 7 日,人工智能顶会 AAAI 2020(第 34 届 AAAI 大会)已于美国纽约正式拉开序幕,本届会议将持续到 2 月 12 日结束。受疫情影响,中...

    机器之心
  • 关于弱监督学习,这可能是目前最详尽的一篇科普文

    近年来,机器学习对现实世界的影响与日俱增。在很大程度上,这是由于各种各样的深度学习模型的出现,使得从业人员可以在不需要任何手动操作特征工程的情况下,就可以在对比...

    AI科技评论
  • 弱监督学习——这是目前最详尽的一篇科普文

    随着人工智能技术的研究迈过了初期的野蛮生长,走进深水区。如何充分利用人工标注信息、减小标注工作量、将人类经验与学习规则充分结合成为了急需解决的关键问题!本文结合...

    商业新知
  • 微软沈向洋等人长文:从Eliza到小冰,社交对话机器人的机遇和挑战

    机器之心

扫码关注云+社区

领取腾讯云代金券