Collaborative Research: RI: Small: NL(V)P: Natural Language (Variety) Processing

合作研究：RI：小型：NL(V)P：自然语言（品种）处理

• 批准号: 2125201
• 负责人: Yulia Tsvetkov
• 金额: $ 16.59万
• 依托单位: University of Washington
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2125201&HistoricalAwards=false
• 关键词: Collaborative; Research; RI; Small; NL

No language is a monolith. Languages vary richly across countries, regions, social classes, and other factors. Despite recent advances in natural language processing (NLP) technology for translating between languages, answering questions, or engaging in simple conversations, current approaches have largely focused only on "standard" varieties of languages. By ignoring other varieties, treating them essentially as statistical noise, current technologies neglect the millions of people who speak these varieties. This project is creating ways to enable language technologies such as translation and question-answering systems, both to process and to generate fine-grained language varieties. The team will develop computational methods to automatically recognize features of different language varieties and then create approaches for integrating such linguistic information into the models powering language technologies. Additionally, the team will design methods to adapt models into varieties for which minimal training data may be available. The resulting suite of general methods will benefit diverse communities and less-privileged populations that speak underserved languages and varieties.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.

没有一种语言是铁板一块。语言因国家、地区、社会阶层和其他因素而千差万别。尽管自然语言处理（NLP）技术在语言之间的翻译，回答问题或参与简单对话方面取得了最新进展，但目前的方法主要集中在“标准”语言种类上。通过忽略其他变体，将它们基本上视为统计噪音，当前的技术忽视了数百万讲这些变体的人。该项目正在创造方法，使语言技术，如翻译和问答系统，既处理和生成细粒度的语言品种。该团队将开发计算方法来自动识别不同语言变体的特征，然后创建将这些语言信息整合到支持语言技术的模型中的方法。此外，该团队还将设计方法，以使模型适应最少训练数据可用的品种。由此产生的一套通用方法将使不同的社区和讲服务不足的语言和品种的弱势群体受益。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey

• DOI: 10.48550/arxiv.2210.07700
• 发表时间: 2022-10
• 作者: Sachin Kumar;Vidhisha Balachandran;Lucille Njoo;Antonios Anastasopoulos;Yulia Tsvetkov

LEXPLAIN: Improving Model Explanations via Lexicon Supervision

• DOI: 10.18653/v1/2023.starsem-1.19
• 发表时间: 2023
• 作者: Orevaoghene Ahia;Hila Gonen;Vidhisha Balachandran;Yulia Tsvetkov;Noah A. Smith

KALM: Knowledge-Aware Integration of Local, Document, and Global Contexts for Long Document Understanding

• DOI: 10.48550/arxiv.2210.04105
• 发表时间: 2022-10
• 作者: Shangbin Feng;Zhaoxuan Tan;Wenqian Zhang;Zhenyu Lei;Yulia Tsvetkov

Examining risks of racial biases in NLP tools for child protective services

• DOI: 10.1145/3593013.3594094
• 发表时间: 2023-05
• 期刊: Proceedings of the 2023 ACM Conference on Fairness, Accountability, and Transparency
• 作者: Anjalie Field;Amanda Coston;Nupoor Gandhi;A. Chouldechova;Emily Putnam-Hornstein;David Steier;Yulia Tsvetkov

Machine Translation into Low-resource Language Varieties

• DOI: 10.18653/v1/2021.acl-short.16
• 发表时间: 2021-06
• 期刊: ArXiv
• 作者: Sachin Kumar;Antonios Anastasopoulos;S. Wintner;Yulia Tsvetkov