权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Annotating Reference and Coreference In Dialogue Using Conversational Agents in games

在游戏中使用对话代理注释对话中的参考和共指

基本信息

批准号：
EP/W001632/1
负责人：
Massimo Poesio
金额：
$ 139.06万
依托单位：
Queen Mary University of London
依托单位国家：
英国
项目类别：
Research Grant
财政年份：
2022
资助国家：
英国
起止时间：
2022 至无数据
项目状态：
未结题

来源：
https://gtr.ukri.org/projects?ref=EP%2FW001632%2F1
关键词：
Annotating Reference Coreference Dialogue Using

项目摘要

The development of modern neural network architectures architectures such as the encoder/decoder model and the Transformer has brought about an explosion of interest in neural models for AI systems able to engage in conversations (aka conversational agents), reflected by a spike of published work, dedicated workshops, and industry-sponsored competitions and grants. While at first these models were applied to simple chatbots, the focus of research has been shifting towards conversational agents capable of engaging in more complex and task-oriented dialogue such as restaurant booking or question answering. But the results on these tasks show that while end-to-end architectures without dedicated models for semantic interpretation can work well for chatbots, conversational agents carrying out more complex tasks require greater ablity to handle such aspects of interpretation, and some form of modelling of context. Among the aspects of natural language interpretation that require more advanced architectures are COREFERENCE and REFERENCE. For an example of the importance of coreference in dialog, consider the following except from a real-life chat conversation, where both participants continually use anaphoric expressions such as BOTH, THEY, IT, etc to refer to previously introduced entities such as Google or Microsoft.A:Are you a fan of Google or Microsoft?B:Both are excellent technology they are helpful in many ways. For the security purpose both are super.A:I'm not a huge fan of Google, but I use it a lot because I have to. I think they are a monopoly in some sense.B:Google provides online related services and products, which includes search engine and cloud computing.A:Yeah, their services are good. I'm just not a fan of intrusive they can be on our personal livesEnriching conversational agents with the ability to carry out these forms of interpretation raises two issues. First, developing models for these tasks requires specific training data: most deep-learning architectures are trained on large amounts of freely available written text. Training a coreference resolver on written text and domain-adapting it to dialogue however has proven ineffective as coreference in dialogue involves different phenomena and is more involved than coreference in text. Second, the developed architectures require specific modules that enable them to interpret coreference and reference. Our group has pioneered the use of Games-With-A-Purpose (GWAPs) to collect data for NLP, resulting in the largest NLP dataset collected using GWAPs or indeed crowdsourcing. But there is a fundamental difference between conversation and written text: the latter is designed to be read by third parties, whereas research has shown that overhearers to a conversation only acquire a partial understanding of what was said.OUR PROPOSED SOLUTION to the problem of creating large annotated datasets of coreference and reference interpretation in conversation is to collect the judgments for anaphoric and referential information via GAMES IN WHICH CONVERSATIONAL AGENTS INTERACT WITH HUMAN PLAYERS AND EVOLVE BY ACQUIRING INFORMATION FROM THEM. This idea builds on recent work by Facebook and Microsoft, among others, that pioneered the use of conversational agents in games to collect data about dialogue, and of Hockenmaier and her lab. Our agents will be deployed in gaming platforms such as LIGHT and MINECRAFT in collaboration with these labs. But whereas in previous work conversational agents only interact with the aim to improve their end-to-end behavior, in the proposed project we will develop artificial agents able to improve their ability to interpret coreference and reference by collecting judgments about these interpretation aspects via CLARIFICATION QUESTIONS to the players at appropriate moments, which can also be used to annotate a dataset.

现代神经网络结构体系结构的发展，如编码器/解码器模型和转换器，已经带来了对能够参与对话(也称为对话代理)的人工智能系统的神经模型的兴趣的爆炸式增长，反映在发表的工作、专门的研讨会以及行业赞助的比赛和资助的激增。虽然最初这些模型被应用于简单的聊天机器人，但研究的重点已经转移到能够参与更复杂和面向任务的对话的代理，如餐厅预订或回答问题。但这些任务的结果表明，虽然没有专用语义解释模型的端到端体系结构可以很好地适用于聊天机器人，但执行更复杂任务的对话代理需要更强的能力来处理这些方面的解释，以及某种形式的上下文建模。自然语言解释需要更高级的体系结构，其中包括COREFERENCE和REFERENCE。关于对话中共指关系的重要性的一个例子，除了在现实生活中的聊天对话中，两个参与者都不断地使用诸如Both、They、IT等回指短语来指代以前介绍的实体，如Google或Microsoft。A：你是Google或Microsoft的粉丝吗？B：这两个都是优秀的技术，它们在许多方面都有帮助。出于安全考虑，两者都是超级的。答：我不是谷歌的超级粉丝，但我经常使用它，因为我必须这样做。我认为他们在某种意义上是垄断的。B：谷歌提供与在线相关的服务和产品，包括搜索引擎和云计算。A：是的，他们的服务很好。我只是不喜欢侵扰我们的人，他们可能会影响我们的个人生活。让谈话代理人有能力进行这些形式的解释会带来两个问题。首先，为这些任务开发模型需要特定的训练数据：大多数深度学习架构都是在大量免费可用的书面文本上进行训练的。然而，对书面文本和领域的共指解析器进行培训--使其适应对话--已被证明是无效的，因为对话中的共指涉及不同的现象，而且比文本中的共指更复杂。其次，开发的体系结构需要特定的模块，使它们能够解释共指和引用。我们的团队率先使用有目的的游戏(GWAP)为NLP收集数据，从而产生了使用GWAP或众包收集的最大的NLP数据集。但会话和书面文本之间有一个根本的区别：后者被设计为供第三方阅读，而研究表明，监听者对所说的话只能获得部分理解。我们提出的解决方案是通过游戏收集指代和指称信息的判断，在游戏中，会话主体与人类参与者交互，并通过从参与者那里获取信息来进化。这个想法是建立在Facebook和微软等公司最近的工作基础上的，这些工作开创了在游戏中使用对话代理来收集对话数据的先河，以及霍根迈尔和她的实验室。我们的代理将与这些实验室合作，部署在LIGH和MIWARTH等游戏平台上。但是，在以前的工作中，对话代理只是为了改善他们的端到端行为而进行交互，在拟议的项目中，我们将开发人工代理，通过在适当的时刻向玩家提出澄清问题来收集对这些解释方面的判断，从而提高他们解释共指和参照的能力，这些判断也可以用来注释数据集。