CAREER: Capturing Content and Linguistic Quality in Automatic Extractive and Abstractive Summarization

职业:在自动提取和抽象摘要中捕获内容和语言质量

基本信息

  • 批准号:
    0953445
  • 负责人:
  • 金额:
    $ 54.99万
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2010
  • 资助国家:
    美国
  • 起止时间:
    2010-02-01 至 2017-01-31
  • 项目状态:
    已结题

项目摘要

This CAREER proposal deals with the development of novel systems for automatic summarization which incorporate both linguistic and content quality considerations in their operation. The main motivation for the work is that even the best current systems do not take the characteristics of the input into account during their operation, they cannot estimate how successful they perform content selection, and completely ignore issues of linguistic quality of the output.Improvement of linguistic quality of summaries requires a combination and relative assessment of a wide range of text quality factors:discourse relations, topic/entity/word coherence, form of referring expressions, vocabulary. Tools for automatic extraction of such models from the input text, including automatic discourse analysis of explicit and implicit discourse relations, are developed as part of the project. The resulting models of linguistic quality will have broader impact on a whole range of text producing applications including questions answering, machine translation, automatic essay grading and computer-assisted writing tutoring.Improvement of content quality requires taking into account characteristics of the input. In particular, we develop measures of input difficulty, which enable systems to automatically predict if they can produce a good quality summary for a given input and permit for change of summarization strategy when necessary. Specialized summarization strategies for input types where current system performance is known to be suboptimal are also elaborated.Text quality and summarization are research topics with cross-disciplinary appeal. The PI will offer project-based courses at the undergraduate and graduate level which have the potential to attract young people to the field of computer science.
这个职业生涯的建议涉及到自动摘要的新系统的开发,其中包括在其操作的语言和内容质量的考虑。 这项工作的主要动机是,即使是目前最好的系统在运行过程中也没有考虑到输入的特征,它们无法估计它们执行内容选择的成功程度,并且完全忽略了输出的语言质量问题。摘要的语言质量的改进需要对广泛的文本质量因素进行组合和相对评估:语篇关系、话题/实体/词汇连贯、指称表达形式、词汇。作为该项目的一部分,开发了从输入文本中自动提取这种模型的工具,包括对显式和隐式话语关系的自动话语分析。由此产生的语言质量模型将对整个文本生成应用程序产生更广泛的影响,包括问答,机器翻译,自动论文评分和计算机辅助写作辅导。内容质量的提高需要考虑输入的特征。特别是,我们开发的措施,输入难度,使系统能够自动预测,如果他们可以产生一个良好的质量摘要为给定的输入,并允许在必要时改变总结策略。专门的摘要输入类型,目前的系统性能是次优的策略也阐述。文本质量和摘要是跨学科的研究课题。PI将在本科和研究生阶段提供基于项目的课程,有可能吸引年轻人进入计算机科学领域。

项目成果

期刊论文数量(0)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)

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

{{ 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 }}

Ani Nenkova其他文献

A Tableau Method for Graded Intersections of Modalities: A Case for Concept Languages

Ani Nenkova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('Ani Nenkova', 18)}}的其他基金

CHS: Medium: Collaborative Reearch: Bio-behavioral data analytics to enable personalized training of veterans for the future workforce
CHS:中:协作研究:生物行为数据分析,为未来的劳动力提供退伍军人的个性化培训
  • 批准号:
    1955721
  • 财政年份:
    2020
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
EAGER: Predicting Domain-level Reading Comprehension Difficulty to Support Adult Learning
EAGER:预测领域级阅读理解难度以支持成人学习
  • 批准号:
    1748771
  • 财政年份:
    2017
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
NAACL-HLT 2012 Student Workshop
NAACL-HLT 2012 学生研讨会
  • 批准号:
    1220521
  • 财政年份:
    2012
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
CI-P: Collaborative Research: Summarizing Opinion and Speaker Attitude in Speech
CI-P:协作研究:总结观点和演讲者在演讲中的态度
  • 批准号:
    1059257
  • 财政年份:
    2011
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
RI-Medium: Collaborative Research : Corpus-based Studies of Lexical, Acoustic, And Discourse Entrainment in Spoken Dialogue
RI-Medium:协作研究:基于语料库的口语对话中的词汇、声学和话语夹带研究
  • 批准号:
    0803159
  • 财政年份:
    2008
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant

相似海外基金

Capturing Oceanic Submesoscales, Stirring and Mixing with Sound and Simulations
通过声音和模拟捕捉海洋亚尺度、搅拌和混合
  • 批准号:
    EP/Y014693/1
  • 财政年份:
    2024
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Research Grant
2DSPEC - Simulating two-dimensional electronic spectroscopy: Capturing the complexities of photo-induced excitedstate molecular processes
2DSPEC - 模拟二维电子光谱:捕获光诱导激发态分子过程的复杂性
  • 批准号:
    EP/Y037383/1
  • 财政年份:
    2024
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Fellowship
CAREER: Capturing the translation of wave climate to coastal change on rocky shorelines across scales
职业:在不同尺度的岩石海岸线上捕捉波浪气候对沿海变化的转化
  • 批准号:
    2339542
  • 财政年份:
    2024
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Continuing Grant
CAREER: Towards Environment-Aware Adaptive Safety for Learning-Enabled Multiagent Systems with Application to Target Drone Capturing
职业:为支持学习的多智能体系统实现环境感知的自适应安全,并应用于目标无人机捕获
  • 批准号:
    2336189
  • 财政年份:
    2024
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Continuing Grant
Capturing Oceanic Submesoscales, Stirring, and Mixing with Sound and Simulations
通过声音和模拟捕捉海洋亚尺度、搅拌和混合
  • 批准号:
    MR/X035611/1
  • 财政年份:
    2024
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Fellowship
FMSG: Bio: RAMP-Bio-CAFe: Routing Advanced Manufacturing of BioPolymer(s): Capturing Agri-feedstocks in Cell free Factories
FMSG:生物:RAMP-Bio-CAFe:生物聚合物的先进制造路线:在无细胞工厂中捕获农业原料
  • 批准号:
    2328291
  • 财政年份:
    2023
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
Collaborative Research: BPE Track 2: Disability DCL - Capturing Narratives that Characterize Neurodivergent Strengths and Weaknesses
合作研究:BPE 轨道 2:残疾 DCL - 捕捉表征神经分歧优势和劣势的叙述
  • 批准号:
    2306831
  • 财政年份:
    2023
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
Collaborative Research: BPE Track 2: Disability DCL - Capturing Narratives that Characterize Neurodivergent Strengths and Weaknesses
合作研究:BPE 轨道 2:残疾 DCL - 捕捉表征神经分歧优势和劣势的叙述
  • 批准号:
    2306830
  • 财政年份:
    2023
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Standard Grant
Capturing forgotten voices: Syrian adolescents' experiences of displacement and humanitarian action in Jordan and Lebanon.
捕捉被遗忘的声音:叙利亚青少年在约旦和黎巴嫩的流离失所经历和人道主义行动。
  • 批准号:
    2885591
  • 财政年份:
    2023
  • 资助金额:
    $ 54.99万
  • 项目类别:
    Studentship
Capturing, quantifying, and understanding combinatorial effects in small molecule signaling
捕获、量化和理解小分子信号传导中的组合效应
  • 批准号:
    10684528
  • 财政年份:
    2023
  • 资助金额:
    $ 54.99万
  • 项目类别:
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了