CRII: RI: Methods for Learning and Recovering Partially Embedded Logical Representations for Question Answering

CRII：RI：学习和恢复用于问答的部分嵌入逻辑表示的方法

• 批准号: 1656998
• 负责人: Yoav Artzi
• 金额: $ 17.5万
• 依托单位: Cornell University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2017
• 资助国家: 美国
• 起止时间: 2017-08-15 至 2020-07-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1656998&HistoricalAwards=false
• 关键词: CRII; RI; Methods; Learning; Recovering

Providing effective access to non-experts to the ever-increasing amount of publicly available information is a challenging open problem. While search has been the dominant mode of access, it does not support complex queries, and provides a poor interface for natural language interaction with the growing number of virtual and embodied agents. The goal of this project is to develop representations and learning methods to enable systems that can respond accurately to complex natural language questions. This work will advance the field of natural language processing and have impact through the development of algorithms, linguistic representations, and applications, including natural language question answering interfaces for large knowledge bases. A common approach to question answering, commonly known as semantic parsing, is to map questions to expressive logical representations. This is a challenging task that requires deriving the meaning of words, and combining them following the compositional structure of the sentence. Despite increasing research attention, building systems capable of such understanding requires significant expertise, and state-of-the-art systems are limited by the coverage of existing manually-curated knowledge bases, largely failing to benefit from unstructured text. This project proposes an approach that will (a) significantly reduce the engineering effort and expertise required to build question answering systems, (b) generalize beyond curated data to learn to answer complex factoid questions without a knowledge base, and (c) lay the foundations for a new general approach to recover semantic meaning. The key to this approach is the integration of logical and embedded representations of meaning. It is expected that mapping sentences to representations that combine logical and embedded elements will greatly reduce the amount of representation engineering required, enable complex sentence-level reasoning, and allow effective learning from raw text without access to a structured knowledge base.

如何让非专家有效地获取数量不断增加的公开信息，是一个具有挑战性的公开问题。虽然搜索一直是主要的访问模式，但它不支持复杂的查询，并且为与越来越多的虚拟和具体代理的自然语言交互提供了一个很差的接口。该项目的目标是开发表示和学习方法，使系统能够准确地响应复杂的自然语言问题。这项工作将推动自然语言处理领域的发展，并通过算法，语言表示和应用程序的开发产生影响，包括大型知识库的自然语言问答界面。一种常见的问答方法，通常称为语义解析，是将问题映射到表达性逻辑表示。这是一项具有挑战性的任务，需要推导单词的含义，并根据句子的组成结构将它们组合起来。尽管越来越多的研究关注，但构建能够理解这种理解的系统需要大量的专业知识，而最先进的系统受到现有手动管理的知识库的覆盖范围的限制，在很大程度上无法从非结构化文本中受益。该项目提出了一种方法，该方法将（a）显着减少构建问答系统所需的工程工作和专业知识，（B）超越精选数据进行概括，以学习在没有知识库的情况下回答复杂的事实问题，以及（c）为恢复语义含义的新通用方法奠定基础。这种方法的关键是整合逻辑和嵌入的意义表示。预计将句子映射到联合收割机逻辑和嵌入元素的表示将大大减少所需的表示工程量，实现复杂的推理级推理，并允许在不访问结构化知识库的情况下从原始文本进行有效学习。

项目成果

Situated Mapping of Sequential Instructions to Actions with Single-step Reward Observation

• DOI: 10.18653/v1/p18-1193
• 发表时间: 2018-05
• 作者: Alane Suhr;Yoav Artzi

Learning to Map Context-Dependent Sentences to Executable Formal Queries

• DOI: 10.18653/v1/n18-1203
• 发表时间: 2018-04
• 期刊: ArXiv
• 作者: Alane Suhr;Srini Iyer;Yoav Artzi

What is Learned in Visually Grounded Neural Syntax Acquisition

视觉神经语法习得中学到了什么

• DOI: 10.18653/v1/2020.acl-main.234
• 发表时间: 2020
• 期刊: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
• 作者: Kojima, Noriyuki;Averbuch-Elor, Hadar;Rush, Alexander;Artzi, Yoav
• 通讯作者: Artzi, Yoav

A Corpus for Reasoning about Natural Language Grounded in Photographs

• DOI: 10.18653/v1/p19-1644
• 发表时间: 2018-11
• 期刊: ArXiv
• 作者: Alane Suhr;Stephanie Zhou;Iris Zhang;Huajun Bai;Yoav Artzi