CAREER: Developing an Underspecified Representation for Temporal Information in Text

职业:开发文本中时间信息的未指定表示

基本信息

  • 批准号:
    1652742
  • 负责人:
  • 金额:
    $ 49.94万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2017
  • 资助国家:
    美国
  • 起止时间:
    2017-03-15 至 2024-02-29
  • 项目状态:
    已结题

项目摘要

Despite the recent advances in automated processing of natural language, approaching general human-level understanding of text in many cases still remains challenging. This CAREER project addresses one such challenge, automatically extracting and understanding the order and timing of events described in natural language text narratives. It develops a computational framework for representing and extracting temporal information conveyed in text, with the end goal to enable realistic temporal reasoning from text. It also engages student involvement in computer science research early on, and in particular is designed to attract female students to pursue careers in computer science and related areas.As distinct from existing approaches, the proposed research assumes underspecification to be an integral property of temporal representation, supported by the notion of a coarse-grained event cluster. It takes advantage of the micro-structure of narrative text by identifying event clusters and their narrative anchors which, together with default event times and durations, serve to organize the underspecified representation of the timeline. It also addresses knowledge gaps in the current state-of-the-art in by developing three key components. First, a novel representational scheme is employed to facilitate simple, intuitive choices for the annotators that minimize cognitive effort and reduce annotation error. Question answering serves as the target application, with a focus on reading-comprehension questions that require temporal reasoning beyond understanding simple factoids. Second, novel methods for intrinsic evaluation of annotation consistency are used to address problems with existing evaluation methods, which often produce varied results depending on specific strategies for crediting temporal relations inferred through transitive closure over the temporal relation graph. The proposed methods rely on representing temporal relations as partially ordered sets and use linear extensions of these partial orders in order to evaluate inter-annotator agreement and system performance. Finally, a new class of neural network-based models is explored that aim to recover partial order graphs over anchored event clusters. These models use external memory components for cumulative discourse representation, and allow joint training for identifying coreferent event mentions, grouping the recovered events into roughly-simultaneous event clusters, and establishing typed links between them. The models incorporate a representation for default event order and timing, as well as argument structure for events and quantitative inference over temporal expressions.
尽管最近在自然语言的自动化处理方面取得了进展,但在许多情况下,接近一般人类水平的文本理解仍然具有挑战性。 这个CAREER项目解决了这样一个挑战,自动提取和理解自然语言文本叙述中描述的事件的顺序和时间。 它开发了一个计算框架,用于表示和提取文本中传达的时间信息,最终目标是从文本中实现逼真的时间推理。 它还从事学生参与计算机科学研究的早期,特别是旨在吸引女学生追求计算机科学和相关areas.As不同于现有的方法,拟议的研究假设欠规范是一个不可分割的属性的时间表示,支持的概念粗粒度的事件集群。 它利用叙事文本的微观结构,通过识别事件集群及其叙事锚,连同默认的事件时间和持续时间,用于组织未指定的时间轴的表示。 它还通过开发三个关键组成部分来解决目前最先进技术中的知识差距。 首先,一个新的代表性计划,以方便简单,直观的选择,最大限度地减少认知努力,减少注释错误的注释。 问答作为目标应用程序,重点关注阅读理解问题,这些问题需要时间推理,而不仅仅是理解简单的事实。 第二,新的注释一致性的内在评价方法被用来解决与现有的评价方法,这往往会产生不同的结果,这取决于特定的策略,通过时间关系图上的传递闭包推断出的时间关系。 所提出的方法依赖于表示时间关系的偏序集,并使用这些偏序的线性扩展,以评估注释者之间的协议和系统性能。 最后,一类新的基于神经网络的模型进行了探讨,旨在恢复偏序图锚定事件集群。 这些模型使用外部记忆组件的累积话语表示,并允许联合训练识别coreferent事件提到,分组恢复的事件大致同时的事件集群,并建立它们之间的类型链接。 该模型结合了默认事件顺序和时间的表示,以及事件的参数结构和时间表达式的定量推理。

项目成果

期刊论文数量(6)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Context-Aware Neural Model for Temporal Information Extraction
  • DOI:
    10.18653/v1/p18-1049
  • 发表时间:
    2018-07
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yuanliang Meng;Anna Rumshisky
  • 通讯作者:
    Yuanliang Meng;Anna Rumshisky
Getting Closer to AI Complete Question Answering: A Set of Prerequisite Real Tasks
  • DOI:
    10.1609/aaai.v34i05.6398
  • 发表时间:
    2020-04
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Anna Rogers;Olga Kovaleva;Matthew Downey;Anna Rumshisky
  • 通讯作者:
    Anna Rogers;Olga Kovaleva;Matthew Downey;Anna Rumshisky
Down and Across: Introducing Crossword-Solving as a New NLP Benchmark
纵横交错:引入填字游戏作为新的 NLP 基准
Triad-based Neural Network for Coreference Resolution
  • DOI:
  • 发表时间:
    2018-08
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yuanliang Meng;Anna Rumshisky
  • 通讯作者:
    Yuanliang Meng;Anna Rumshisky
Temporal Information Extraction for Question Answering Using Syntactic Dependencies in an LSTM-based Architecture
  • DOI:
    10.18653/v1/d17-1092
  • 发表时间:
    2017-03
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Yuanliang Meng;Anna Rumshisky;Alexey Romanov
  • 通讯作者:
    Yuanliang Meng;Anna Rumshisky;Alexey Romanov
{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

数据更新时间:{{ journalArticles.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ monograph.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ sciAawards.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ conferencePapers.updateTime }}

{{ item.title }}
  • 作者:
    {{ item.author }}

数据更新时间:{{ patent.updateTime }}

Anna Rumshisky其他文献

Tracking the History of Knowledge Using Historical Editions of Encyclopedia
使用百科全书的历史版本追踪知识的历史
  • DOI:
  • 发表时间:
    2012
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Britannica M. Gronas;Anna Rumshisky;A. Gabrovski;S. Kovaka;H. Chen
  • 通讯作者:
    H. Chen
Complementary Roles of Inference and Language Models in QA
推理和语言模型在 QA 中的互补作用
  • DOI:
    10.18653/v1/2023.pandl-1.8
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Eric Brill;Susan Dumais;Tom B. Brown;Benjamin Mann;Nick Ryder;Jared D Subbiah;Prafulla Kaplan;A. Dhariwal;Danqi Chen;Adam Fisch;Jason Weston;J. Devlin;Ming;Kenton Lee;Tianyi Li;Mohammad Javad Hosseini;Sabine Weber;Mark Steedman. 2022a;Language Models;Are;Xi Victoria;Todor Lin;Mikel Mihaylov;Artetxe;Tianlu;Shuohui Wang;Daniel Chen;Myle Simig;Na;Yinhan Liu;Myle Ott;Naman Goyal;Jingfei Du;Mandar Joshi;Omer Levy;Mike Lewis;Nick McKenna;Liane Guillou;Mohammad Javad;Sander Bijl de Vroe;Mark Johnson;Yu Meng;Anna Rumshisky;Alexey Ro;Dan Moldovan;S. Harabagiu;Marius Pasca;Rada;Roxana Mihalcea;Richard Girju;Goodrum;Dat Ba Nguyen;Johannes Hoffart;Martin Theobald
  • 通讯作者:
    Martin Theobald
GLML: Annotating Argument Selection and Coercion
GLML:注释参数选择和强制
  • DOI:
    10.3115/1693756.1693774
  • 发表时间:
    2009
  • 期刊:
  • 影响因子:
    1.5
  • 作者:
    J. Pustejovsky;Jessica L. Moszkowicz;O. Batiukova;Anna Rumshisky
  • 通讯作者:
    Anna Rumshisky
Crowdsourcing Word Sense Definition
众包词义定义
  • DOI:
  • 发表时间:
    2011
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Anna Rumshisky
  • 通讯作者:
    Anna Rumshisky
Adversarial Text Generation Without Reinforcement Learning
无需强化学习的对抗性文本生成
  • DOI:
  • 发表时间:
    2018
  • 期刊:
  • 影响因子:
    0
  • 作者:
    David Donahue;Anna Rumshisky
  • 通讯作者:
    Anna Rumshisky

Anna Rumshisky的其他文献

{{ item.title }}
{{ item.translation_title }}
  • DOI:
    {{ item.doi }}
  • 发表时间:
    {{ item.publish_year }}
  • 期刊:
  • 影响因子:
    {{ item.factor }}
  • 作者:
    {{ item.authors }}
  • 通讯作者:
    {{ item.author }}

{{ truncateString('Anna Rumshisky', 18)}}的其他基金

Collaborative Research: Machine Learning for Student Reasoning during Challenging Concept Questions
协作研究:机器学习在挑战性概念问题中帮助学生推理
  • 批准号:
    2226601
  • 财政年份:
    2023
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Standard Grant
Student Participant Support for Conversational Intelligence Summer School 2019
2019 年对话智能暑期学校学生参与者支持
  • 批准号:
    1933903
  • 财政年份:
    2019
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Standard Grant
EAGER: Exploring Cognitively Plausible Computational Models for Processing Human Language
EAGER:探索处理人类语言的认知合理计算模型
  • 批准号:
    1844740
  • 财政年份:
    2018
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Standard Grant

相似海外基金

Developing a 3D printed skin model using a Dextran - Collagen hydrogel to analyse the cellular and epigenetic effects of interleukin-17 inhibitors in
使用右旋糖酐-胶原蛋白水凝胶开发 3D 打印皮肤模型,以分析白细胞介素 17 抑制剂的细胞和表观遗传效应
  • 批准号:
    2890513
  • 财政年份:
    2027
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Studentship
Developing behavioural methods to assess pain in horses
开发评估马疼痛的行为方法
  • 批准号:
    2686844
  • 财政年份:
    2025
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Studentship
Developing eye models to improve eye treatments and contact/intraocular lens technologies
开发眼部模型以改善眼部治疗和隐形眼镜/人工晶状体技术
  • 批准号:
    2608661
  • 财政年份:
    2025
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Studentship
Flok Health: Developing a pocket physiotherapist to deliver personalised healthcare at population scale
Flok Health:开发袖珍物理治疗师以在人口规模上提供个性化医疗保健
  • 批准号:
    10100082
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Collaborative R&D
Developing systemic interventions for intimate partner financial abuse
制定针对亲密伴侣经济虐待的系统干预措施
  • 批准号:
    DP240101075
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Discovery Projects
NESP MaC Project 4.5– Developing an Integrated Pest Management Framework for Feral Pigs in Coastal Environments 2024-2026 (NAILSMA)
NESP MaC 项目 4.5 — 为 2024-2026 年沿海环境中的野猪制定综合害虫管理框架 (NAILSMA)
  • 批准号:
    global : ba1e00f0-9953-4c17-b990-ba7aed84ce07
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
Developing and Visualising a Retrieval-Augmented Deep Learning Model for Population Health Management
开发和可视化用于人口健康管理的检索增强深度学习模型
  • 批准号:
    2905946
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Studentship
Developing functionalised electrospun scaffolds to exploit neural stromal interactions in wound healing
开发功能化电纺支架以利用神经基质相互作用促进伤口愈合
  • 批准号:
    2910663
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Studentship
Developing a Census Based Generative Geodemographic Classification System
开发基于人口普查的生成地理人口分类系统
  • 批准号:
    ES/Z50273X/1
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Research Grant
Developing new tests and treatments to enable prevention of osteoarthritis.
开发新的测试和治疗方法以预防骨关节炎。
  • 批准号:
    MR/Y003470/1
  • 财政年份:
    2024
  • 资助金额:
    $ 49.94万
  • 项目类别:
    Fellowship
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了