CAREER: Neural Transcript Summarization and Induction of Document Structure
职业:神经转录摘要和文档结构归纳
基本信息
- 批准号:2143792
- 负责人:
- 金额:$ 49.43万
- 依托单位:
- 依托单位国家:美国
- 项目类别:Continuing Grant
- 财政年份:2022
- 资助国家:美国
- 起止时间:2022-06-15 至 2022-11-30
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
The exploding reach and power of audio and video, combined with accurate captioning, is broadening access to large collections of transcripts. Automatic transcript summarization enables the production of textual summaries from transcripts of audio and video recordings. It holds promise for numerous industries that have large collections of transcripts, ranging from telehealth and telemedicine, financial services, video conferencing, to podcast and livestream service providers. Whether one needs to share the minutes of a meeting or quickly take notes of a livestream recording, using a transcript summarization tool is a viable way to outsource the otherwise labor-intensive task of turning voice recordings into textual summaries. Though practitioners are eager to summarize transcripts of various sorts, they cannot deal with the complexities of spoken language. Without robust summarization technology, users can become overwhelmed by the amount of information available and fail to effectively pinpoint topics of importance.The research goal of this CAREER project is to provide a unified methodological framework for automatic transcript summarization through investigation of fundamental problems in summarization to improve the efficiency of content selection and production of transcript summaries. The proposed effort will harness the power of deep neural networks and linguistic structure prediction to induce document structure on transcripts and enable the production of comprehensive summaries. Specific objectives of the research plan are to (a) uncover the structure of informal, verbose transcripts of spontaneous speech, (b) produce comprehensive summaries to allow users to navigate the transcripts with ease, and (c) establish an evaluation protocol that combines intrinsic and extrinsic measures to assess the quality of transcript summaries. The project seeks to address fundamental challenges in transcript summarization to provide robust, universally accessible summarization solutions to field practitioners. The research plan will be fully integrated into a synergistic education plan to engage diverse student learners in exploration of summarization technology.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
音频和视频的爆炸性影响和力量,加上准确的字幕,正在扩大对大量文字记录的访问。自动成绩单摘要允许从音频和视频记录的成绩单中生成文本摘要。它为许多拥有大量记录的行业带来了希望,从远程医疗和远程医疗,金融服务,视频会议到播客和直播服务提供商。无论是需要分享会议记录还是快速记录直播录音,使用转录摘要工具都是一种可行的方式,可以将将语音记录转换为文本摘要的劳动密集型任务外包。虽然练习者渴望总结各种各样的文字记录,但他们无法处理口语的复杂性。如果没有强大的摘要技术,用户可能会被大量的信息淹没,无法有效地确定重要的主题。本CAREER项目的研究目标是通过研究摘要中的基本问题,为自动成绩单摘要提供一个统一的方法框架,以提高内容选择和成绩单摘要制作的效率。拟议的工作将利用深度神经网络和语言结构预测的力量,在成绩单上诱导文档结构,并生成全面的摘要。研究计划的具体目标是:(a)发现自发性言语的非正式、冗长的转录本的结构,(B)产生全面的摘要,使用户能够轻松地浏览转录本,以及(c)建立一个评估协议,结合内在和外在的措施来评估转录本摘要的质量。该项目旨在解决成绩单摘要中的基本挑战,为现场从业人员提供强大的,普遍可访问的摘要解决方案。该研究计划将被完全整合到一个协同教育计划中,以吸引不同的学生学习者探索摘要技术。该奖项反映了NSF的法定使命,并被认为值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估来支持。
项目成果
期刊论文数量(1)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Towards Abstractive Grounded Summarization of Podcast Transcripts
- DOI:10.48550/arxiv.2203.11425
- 发表时间:2022-03
- 期刊:
- 影响因子:0
- 作者:Kaiqiang Song;Chen Li;Xiaoyang Wang;Dong Yu;Fei Liu
- 通讯作者:Kaiqiang Song;Chen Li;Xiaoyang Wang;Dong Yu;Fei Liu
{{
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 }}
Fei Liu其他文献
Deformation Behavior between Hydraulic and Natural Fractures Using Fully Coupled Hydromechanical Model with XFEM
使用 XFEM 的全耦合流体力学模型研究水力裂缝和天然裂缝之间的变形行为
- DOI:
10.1155/2017/6373957 - 发表时间:
2017-06 - 期刊:
- 影响因子:0
- 作者:
Fei Liu;Zhifeng Luo;Yu Sang - 通讯作者:
Yu Sang
Fabrication of Patterned Boron Carbide Nanowires and Their Electrical, Field Emission and Flexible Properties
图案化碳化硼纳米线的制备及其电学、场发射和柔性性能
- DOI:
- 发表时间:
2012 - 期刊:
- 影响因子:9.9
- 作者:
H. J. Gao;Fei Liu;Q. Luo;Y. Tian;Q. Zou;C. Li;C. M. Shen;S. Z. Deng;C. Z. Gu - 通讯作者:
C. Z. Gu
Measurement on dipole antenna with light polarized nano-material(PNM) textile reflector
光偏振纳米材料(PNM)织物反射器偶极子天线的测量
- DOI:
10.1109/mwsym.2009.5165885 - 发表时间:
2009 - 期刊:
- 影响因子:0
- 作者:
Fei Liu;Wen;Zhijun Zhang;Zhenghe Feng;Yaqin Chen;Hui Zhang - 通讯作者:
Hui Zhang
A Key Distribution and Management Scheme for Clustered Ad Hoc Sensor Networks
- DOI:
- 发表时间:
2013 - 期刊:
- 影响因子:0
- 作者:
Fei Liu - 通讯作者:
Fei Liu
Characterization of basin-scale aquifer heterogeneity using transient hydraulic tomography with aquifer responses induced by groundwater exploitation reduction
利用瞬态水力层析成像技术表征盆地尺度含水层异质性以及地下水开采减少引起的含水层响应
- DOI:
10.1016/j.jhydrol.2020.125137 - 发表时间:
2020-09 - 期刊:
- 影响因子:6.4
- 作者:
Fei Liu;Tian-Chyi Jim Yeh;Yu-Li Wang;Yonghong Hao;Jet-Chau Wen;Wenke Wang - 通讯作者:
Wenke Wang
Fei Liu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('Fei Liu', 18)}}的其他基金
RI: Small: Towards Abstractive Summarization That Preserves the Original Meaning
RI:小:走向保留原意的抽象概括
- 批准号:
2303678 - 财政年份:2022
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
CAREER: Neural Transcript Summarization and Induction of Document Structure
职业:神经转录摘要和文档结构归纳
- 批准号:
2303655 - 财政年份:2022
- 资助金额:
$ 49.43万 - 项目类别:
Continuing Grant
RI: Small: Towards Abstractive Summarization That Preserves the Original Meaning
RI:小:走向保留原意的抽象概括
- 批准号:
1909603 - 财政年份:2019
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
相似国自然基金
Neural Process模型的多样化高保真技术研究
- 批准号:62306326
- 批准年份:2023
- 资助金额:30 万元
- 项目类别:青年科学基金项目
相似海外基金
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:
$ 49.43万 - 项目类别:
Studentship
DMS-EPSRC: Asymptotic Analysis of Online Training Algorithms in Machine Learning: Recurrent, Graphical, and Deep Neural Networks
DMS-EPSRC:机器学习中在线训练算法的渐近分析:循环、图形和深度神经网络
- 批准号:
EP/Y029089/1 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Research Grant
MCA Pilot PUI: From glomeruli to pollination: vertical integration of neural encoding through ecologically-relevant behavior
MCA Pilot PUI:从肾小球到授粉:通过生态相关行为进行神经编码的垂直整合
- 批准号:
2322310 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Continuing Grant
Flexible fMRI-Compatible Neural Probes with Organic Semiconductor based Multi-modal Sensors for Closed Loop Neuromodulation
灵活的 fMRI 兼容神经探针,带有基于有机半导体的多模态传感器,用于闭环神经调节
- 批准号:
2336525 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
CAREER: Data-Enabled Neural Multi-Step Predictive Control (DeMuSPc): a Learning-Based Predictive and Adaptive Control Approach for Complex Nonlinear Systems
职业:数据支持的神经多步预测控制(DeMuSPc):一种用于复杂非线性系统的基于学习的预测和自适应控制方法
- 批准号:
2338749 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333881 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
Collaborative Research: Spintronics Enabled Stochastic Spiking Neural Networks with Temporal Information Encoding
合作研究:自旋电子学支持具有时间信息编码的随机尖峰神经网络
- 批准号:
2333882 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
EAGER: Search-Accelerated Markov Chain Monte Carlo Algorithms for Bayesian Neural Networks and Trillion-Dimensional Problems
EAGER:贝叶斯神经网络和万亿维问题的搜索加速马尔可夫链蒙特卡罗算法
- 批准号:
2404989 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant
CAREER: Early-life social environments drive behavioral and neural mechanisms of development
职业:早期社会环境驱动行为和神经机制的发展
- 批准号:
2341006 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Continuing Grant
CRII: RI: Deep neural network pruning for fast and reliable visual detection in self-driving vehicles
CRII:RI:深度神经网络修剪,用于自动驾驶车辆中快速可靠的视觉检测
- 批准号:
2412285 - 财政年份:2024
- 资助金额:
$ 49.43万 - 项目类别:
Standard Grant