SGER: Exploiting Alternative Packagings of Source Meaning in Statistical Machine Translation

SGER:在统计机器翻译中利用源含义的替代包装

基本信息

  • 批准号:
    0838801
  • 负责人:
  • 金额:
    --
  • 依托单位:
  • 依托单位国家:
    美国
  • 项目类别:
    Continuing Grant
  • 财政年份:
    2008
  • 资助国家:
    美国
  • 起止时间:
    2008-09-01 至 2010-08-31
  • 项目状态:
    已结题

项目摘要

SGER: Exploiting Alternative Packagings of Source Meaning in Statistical Machine TranslationCurrent approaches in statistical machine translation (MT) miss a keyfact: the source language sentence is not the only way the author's meaning could have been expressed. The idea that the source sentence is just one of various ``packagings'' of underlying meaning was, of course, one familiar motivation for interlingual approaches to translation; however, interlingual semantic representations have generally been abandoned as notoriously difficult to define, and equally difficult to obtain accurately with broad coverage once defined. In this project, we are revisiting the idea of "packagings" of meaning, but exploring it in practical ways consistent with current practice in statistical MT. Unlike semantic transfer or interlingualapproaches, we encode alternatives as source paraphrase lattices, a representation that allows us to exploit generalizations about the source language while still maintaining the surface-to-surface orientation that characterizes the statistical state of the art. Our exploratory work focuses on capturing syntactic and semantic variation using Lexicalized Well Founded Grammars (LWFG), a recent formalism that balances expressiveness with practical and provable learnability results. We are quantifying and characterizing the information available in source paraphrase lattices, assessing the value of shallow paraphrasing, and exploring the relative promise of deeper techniques for source paraphase generation using LWFG and other constraint-based grammatical frameworks. The ability to capturegeneralizations via source paraphrase may open new possibilities in the translation of minority and endangered languages, which lack training corpora on the scale necessary to support standard statistical MT techniques.
SGER:在统计机器翻译中利用源语言意义的替代包装目前的统计机器翻译(MT)方法忽略了一个关键事实:源语言句子并不是表达作者意义的唯一方式。 源句只是潜在意义的各种“包装”之一的想法当然是语际翻译方法的一个常见动机;然而,语际语义表征通常被放弃,因为难以定义,并且一旦定义就很难准确获得广泛的覆盖范围。 在这个项目中,我们正在重新审视意义的“包装”的概念,但探索它的实际方法与统计机器翻译的当前实践相一致。 与语义迁移或语际方法不同,我们将替代方案编码为源释义格,这种表示使我们能够利用源语言的概括,同时仍然保持表征统计技术状态的表面到表面的方向。我们的探索性工作侧重于使用词汇化良好基础语法(LWFG)捕获句法和语义变化,最近的一种形式主义,平衡了表达能力与实际和可证明的可学习性结果。 我们正在量化和表征源释义格中可用的信息,评估浅层释义的价值,并探索使用LWFG和其他基于约束的语法框架进行源释义生成的更深层次技术的相对前景。 通过源释义捕捉概括的能力可能会在少数民族和濒危语言的翻译中开辟新的可能性,这些语言缺乏支持标准统计MT技术所需的规模的训练语料库。

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 }}

Philip Resnik其他文献

A multi-modal approach for identifying schizophrenia using cross-modal attention
使用跨模式注意力识别精神分裂症的多模式方法
  • DOI:
    10.48550/arxiv.2309.15136
  • 发表时间:
    2023
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Gowtham Premananth;Yashish M. Siriwardena;Philip Resnik;Carol Y. Espy
  • 通讯作者:
    Carol Y. Espy
Computationally Scalable and Clinically Sound: Laying the Groundwork to Use Machine Learning Techniques for Social Media and Language Data in Predicting Psychiatric Symptoms
  • DOI:
    10.1016/j.biopsych.2022.02.146
  • 发表时间:
    2022-05-01
  • 期刊:
  • 影响因子:
  • 作者:
    Deanna Kelly;Glen Coppersmith;John Dickerson;Carol Espy-Wilson;Hanna Michel;Philip Resnik
  • 通讯作者:
    Philip Resnik
Using Intrinsic and Extrinsic Metrics to Evaluate Accuracy and Facilitation in Computer-assisted Coding
使用内在和外在指标来评估计算机辅助编码的准确性和便利性
  • DOI:
  • 发表时间:
    2006
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Philip Resnik;Michael Niv;Michael Nossal;Gregory Schnitzer;Jean Stoner;Andrew Kapit;Richard Toren
  • 通讯作者:
    Richard Toren
A Psycholinguistics-Inspired Method to Counter IP Theft using Fake Documents
一种受心理语言学启发的方法,利用虚假文档来打击知识产权盗窃
  • DOI:
  • 发表时间:
    2024
  • 期刊:
  • 影响因子:
    2.5
  • 作者:
    Natalia Denisenko;Youzhi Zhang;Chiara Pulice;Shohini Bhattasali;Sushil Jajodia;Philip Resnik;V. S. Subrahmanian
  • 通讯作者:
    V. S. Subrahmanian
Selection and information: a class-based approach to lexical relationships
  • DOI:
  • 发表时间:
    1993-01
  • 期刊:
  • 影响因子:
    0
  • 作者:
    Philip Resnik
  • 通讯作者:
    Philip Resnik

Philip Resnik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('Philip Resnik', 18)}}的其他基金

RI: Small: Modeling Co-Decisions: A Computational Framework Using Language and Metadata
RI:小型:共同决策建模:使用语言和元数据的计算框架
  • 批准号:
    2008761
  • 财政年份:
    2020
  • 资助金额:
    --
  • 项目类别:
    Standard Grant
RAPID: Advanced Topic Modeling Methods to Analyze Text Responses in COVID-19 Survey Data
RAPID:用于分析 COVID-19 调查数据中文本响应的高级主题建模方法
  • 批准号:
    2031736
  • 财政年份:
    2020
  • 资助金额:
    --
  • 项目类别:
    Standard Grant
SoCS: Collaborative Research: Data Driven, Computational Models for Discovery and Analysis of Framing
SoCS:协作研究:用于框架发现和分析的数据驱动计算模型
  • 批准号:
    1211153
  • 财政年份:
    2012
  • 资助金额:
    --
  • 项目类别:
    Standard Grant
Collaborative Proposal-Using the Web as a Corpus for Empirical Linguistic Research
协作提案-使用网络作为实证语言学研究的语料库
  • 批准号:
    0113641
  • 财政年份:
    2001
  • 资助金额:
    --
  • 项目类别:
    Standard Grant
Workshop: Student Research in Computational Linguistics, at the ACL'2000 Conference
研讨会:计算语言学学生研究,ACL2000 会议
  • 批准号:
    0097529
  • 财政年份:
    2000
  • 资助金额:
    --
  • 项目类别:
    Standard Grant

相似海外基金

Exploiting the polysaccharide breakdown capacity of the human gut microbiome to develop environmentally sustainable dishwashing solutions
利用人类肠道微生物群的多糖分解能力来开发环境可持续的洗碗解决方案
  • 批准号:
    2896097
  • 财政年份:
    2027
  • 资助金额:
    --
  • 项目类别:
    Studentship
Exploiting DNS in 3D Design
在 3D 设计中利用 DNS
  • 批准号:
    2777188
  • 财政年份:
    2026
  • 资助金额:
    --
  • 项目类别:
    Studentship
Exploiting JWST to Unveil Our Icy Universe
利用 JWST 揭示我们的冰冷宇宙
  • 批准号:
    2906887
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Studentship
PriorCircuit:Circuit mechanisms for computing and exploiting statistical structures in sensory decision making
PriorCircuit:在感官决策中计算和利用统计结构的电路机制
  • 批准号:
    EP/Z000599/1
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Research Grant
New directions in piezoelectric phononic integrated circuits: exploiting field confinement (SOUNDMASTER)
压电声子集成电路的新方向:利用场限制(SOUNDMASTER)
  • 批准号:
    EP/Z000688/1
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Research Grant
Exploiting protein import to interrogate energy transduction through the bacterial cell envelope
利用蛋白质输入来询问通过细菌细胞包膜的能量转导
  • 批准号:
    BB/X016366/1
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Research Grant
Exploiting Controlled Environments for the Development of Optimised Cannabis Sativa Phenotypes for Pharmaceutical Applications - CE-CannPharm
利用受控环境开发用于制药应用的优化大麻表型 - CE-CannPharm
  • 批准号:
    BB/Z514470/1
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Research Grant
CAREER: Solving Estimation Problems of Networked Interacting Dynamical Systems Via Exploiting Low Dimensional Structures: Mathematical Foundations, Algorithms and Applications
职业:通过利用低维结构解决网络交互动力系统的估计问题:数学基础、算法和应用
  • 批准号:
    2340631
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Continuing Grant
ActBio: Exploiting the Parallels between Active Matter and Mechanobiology
ActBio:利用活性物质与机械生物学之间的相似之处
  • 批准号:
    EP/Y033981/1
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Research Grant
CAREER: Structure Exploiting Multi-Agent Reinforcement Learning for Large Scale Networked Systems: Locality and Beyond
职业:为大规模网络系统利用多智能体强化学习的结构:局部性及其他
  • 批准号:
    2339112
  • 财政年份:
    2024
  • 资助金额:
    --
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了