Global Inference for Summarization Using Integer Linear Programming
使用整数线性规划进行全局归纳推理
基本信息
- 批准号:EP/F055765/1
- 负责人:
- 金额:$ 34.38万
- 依托单位:
- 依托单位国家:英国
- 项目类别:Research Grant
- 财政年份:2009
- 资助国家:英国
- 起止时间:2009 至 无数据
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Summarization is the process of condensing a source text into a shorter version while preserving its information content. The applications of summarization are many and varied. From quick access to news and scientific articles to systems that aid physicians in gathering patient information and meeting browsers. Humans summarize on a daily basis and effortlessly (e.g., by describing the contents of a lecture, a meeting or a movie), but producing high quality summaries automatically remains a challenge. The difficulty lies primarily in the nature of the task which is complex, must satisfy many constraints (e.g., summary length, informativeness, coherence, grammaticality) and ultimately requires large-scale text understanding. Since robust text understanding is beyond the capabilities of current NLP technology, most work today focuses on extractive summarization. The idea here is to create a summary simply by identifying and subsequently concatenating the most important sentences in a document. Without a great deal of linguistic analysis, it is possible to create summaries for a wide range of documents, independently of style, text type, and subject matter. Unfortunately, extracts are often documents of low readability and text quality. In this project we will develop novel models for single-document summarization that break away from the sentence extraction paradigm. We will model summarization as an optimisation problem and use integer linear programming (ILP) for finding a summary that is best for the application, task, or user at hand. The ILP formulation is advantageous for two reasons. First, it allows us to explicitly encode the constraints our output summaries must meet. Secondly, ILP is a well studied optimization problem with efficient algorithms for finding a globally optimal solution in the presence of many conflicting constraints. This proposal aims to shift the summarization paradigm by developing novel and unified models based on the ILP framework that are able to identify what is important in a document and express it appropriately. The success of this research will make significant and far-reaching impact on summarization and related areas (e.g., information retrieval) that could not be brought about by incrementally extending conventional models.
摘要是将源文本压缩成较短的版本,同时保留其信息内容的过程。摘要的应用是多种多样的。从快速访问新闻和科学文章到帮助医生收集患者信息和满足浏览器的系统。人类每天都会毫不费力地总结(例如,通过描述讲座、会议或电影的内容),但是自动生成高质量的摘要仍然是一个挑战。困难主要在于任务的性质是复杂的,必须满足许多限制(例如,摘要长度、信息量、连贯性、语法性),并最终需要大规模的文本理解。由于强大的文本理解超出了当前NLP技术的能力,因此今天的大多数工作都集中在提取摘要上。这里的想法是通过识别并随后连接文档中最重要的句子来创建摘要。不需要大量的语言分析,就可以为各种文档创建摘要,而不受风格、文本类型和主题的影响。不幸的是,摘录通常是可读性和文本质量较低的文档。在这个项目中,我们将开发新的单文档摘要模型,脱离句子提取范式。我们将把摘要建模为一个优化问题,并使用整数线性规划(ILP)来找到最适合当前应用程序、任务或用户的摘要。ILP制剂由于两个原因是有利的。首先,它允许我们显式地编码输出摘要必须满足的约束。其次,ILP是一个研究得很好的优化问题,具有在存在许多冲突约束的情况下找到全局最优解的有效算法。该提案旨在通过开发基于ILP框架的新颖且统一的模型来改变摘要范式,该模型能够识别文档中的重要内容并适当地表达。本研究的成功将对文摘及相关领域(如,信息检索),这是通过逐步扩展传统模型无法实现的。
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)
Discourse Constraints for Document Compression
- DOI:10.1162/coli_a_00004
- 发表时间:2010-09
- 期刊:
- 影响因子:9.3
- 作者:J. Clarke;Mirella Lapata
- 通讯作者:J. Clarke;Mirella Lapata
Multiple Aspect Summarization Using Integer Linear Programming
- DOI:
- 发表时间:2012-07
- 期刊:
- 影响因子:0
- 作者:K. Woodsend;Mirella Lapata
- 通讯作者:K. Woodsend;Mirella Lapata
Learning to Simplify Sentences with Quasi-Synchronous Grammar and Integer Programming
- DOI:
- 发表时间:2011-07
- 期刊:
- 影响因子:0
- 作者:K. Woodsend;Mirella Lapata
- 通讯作者:K. Woodsend;Mirella Lapata
Text Rewriting Improves Semantic Role Labeling
- DOI:10.1613/jair.4431
- 发表时间:2014-09
- 期刊:
- 影响因子:0
- 作者:K. Woodsend;Mirella Lapata
- 通讯作者:K. Woodsend;Mirella Lapata
Title Generation with Quasi-Synchronous Grammar
- DOI:
- 发表时间:2010-10
- 期刊:
- 影响因子:6.6
- 作者:K. Woodsend;Yansong Feng;Mirella Lapata
- 通讯作者:K. Woodsend;Yansong Feng;Mirella Lapata
{{
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 }}
Mirella Lapata其他文献
Explorer Incremental Bayesian Category Learning from Natural Language
探索者增量贝叶斯类别从自然语言学习
- DOI:
- 发表时间:
2015 - 期刊:
- 影响因子:0
- 作者:
Lea Frermann;Mirella Lapata - 通讯作者:
Mirella Lapata
A comparison of parsing technologies for the biomedical domain
生物医学领域解析技术比较
- DOI:
- 发表时间:
2005 - 期刊:
- 影响因子:2.5
- 作者:
Claire Grover;A. Lascarides;Mirella Lapata - 通讯作者:
Mirella Lapata
Correct Program : Instantiation Execution Denotation : 0 Spurious Programs : Inconsistent Program
正确的程序:实例化执行表示:0 虚假程序:不一致的程序
- DOI:
- 发表时间:
2019 - 期刊:
- 影响因子:0
- 作者:
Bailin Wang;Ivan Titov;Mirella Lapata - 通讯作者:
Mirella Lapata
Understanding visual scenes
理解视觉场景
- DOI:
10.1017/s1351324918000104 - 发表时间:
2018 - 期刊:
- 影响因子:2.5
- 作者:
Carina Silberer;Jasper R. R. Uijlings;Mirella Lapata - 通讯作者:
Mirella Lapata
The 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference, 19-24 June, 2011, Portland, Oregon, USA - Student Session
第 49 届计算语言学协会年会:人类语言技术,会议记录,2011 年 6 月 19-24 日,美国俄勒冈州波特兰 - 学生会议
- DOI:
- 发表时间:
2011 - 期刊:
- 影响因子:0
- 作者:
Joel Lang;Mirella Lapata - 通讯作者:
Mirella Lapata
Mirella Lapata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('Mirella Lapata', 18)}}的其他基金
Readers: Evaluation and Development of Reading Systems
读者:阅读系统的评估和开发
- 批准号:
EP/K017845/1 - 财政年份:2013
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
A Unified Model of Compositional and Distributional Semantics: Theory and Applications
组合语义和分布语义的统一模型:理论与应用
- 批准号:
EP/I037415/1 - 财政年份:2013
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
Application-based Text-to-Text Generation
基于应用程序的文本到文本生成
- 批准号:
GR/T04557/01 - 财政年份:2006
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
相似海外基金
CAREER: Game Theoretic Models for Robust Cyber-Physical Interactions: Inference and Design under Uncertainty
职业:稳健的网络物理交互的博弈论模型:不确定性下的推理和设计
- 批准号:
2336840 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Continuing Grant
Spectral embedding methods and subsequent inference tasks on dynamic multiplex graphs
动态多路复用图上的谱嵌入方法和后续推理任务
- 批准号:
EP/Y002113/1 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
Probabilistic Inference Based Utility Evaluation and Path Generation for Active Autonomous Exploration of USVs in Unknown Confined Marine Environments
基于概率推理的效用评估和路径生成,用于未知受限海洋环境中 USV 主动自主探索
- 批准号:
EP/Y000862/1 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
CAREER: Statistical foundations of particle tracking and trajectory inference
职业:粒子跟踪和轨迹推断的统计基础
- 批准号:
2339829 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Continuing Grant
Collaborative Research: SHF: Small: Efficient and Scalable Privacy-Preserving Neural Network Inference based on Ciphertext-Ciphertext Fully Homomorphic Encryption
合作研究:SHF:小型:基于密文-密文全同态加密的高效、可扩展的隐私保护神经网络推理
- 批准号:
2412357 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Standard Grant
CAREER: Efficient Large Language Model Inference Through Codesign: Adaptable Software Partitioning and FPGA-based Distributed Hardware
职业:通过协同设计进行高效的大型语言模型推理:适应性软件分区和基于 FPGA 的分布式硬件
- 批准号:
2339084 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Continuing Grant
AI4PhotMod - Artificial Intelligence for parameter inference in Photosynthesis Models
AI4PhotMod - 用于光合作用模型中参数推断的人工智能
- 批准号:
BB/Y51388X/1 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Research Grant
CSR: Small: Latency-controlled Reduction of Data Center Expenses for Handling Bursty ML Inference Requests
CSR:小:通过延迟控制减少数据中心处理突发 ML 推理请求的费用
- 批准号:
2336886 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Standard Grant
CAREER: Statistical Inference in Observational Studies -- Theory, Methods, and Beyond
职业:观察研究中的统计推断——理论、方法及其他
- 批准号:
2338760 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Continuing Grant
STATISTICAL AND COMPUTATIONAL THRESHOLDS IN SPIN GLASSES AND GRAPH INFERENCE PROBLEMS
自旋玻璃和图推理问题的统计和计算阈值
- 批准号:
2347177 - 财政年份:2024
- 资助金额:
$ 34.38万 - 项目类别:
Standard Grant