Collaborative Research: RI: Medium: From Acoustic Signal to Morphosyntactic Analysis in One End-to-End Neural System

合作研究：RI：媒介：从声学信号到端到端神经系统中的形态句法分析

• 批准号: 2211951
• 负责人: Lorraine Levin
• 金额: $ 89.8万
• 依托单位: Carnegie-Mellon University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-01 至 2026-07-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2211951&HistoricalAwards=false
• 关键词: Collaborative; Research; RI; Medium; Acoustic

There are approximately 7,000 languages in the world today, but this number is declining precipitously.Even many languages that currently have thousands upon thousands of speakers are likely to fall outof use within a generation. For the speakers of these languages, this represents a tragic loss of culturaland linguistic heritage, which are important anchors of their social identity. Each language also carriesirreplaceable data about language as a phenomenon of human behavior—the limits of its variation andthe patterns in its structure and development. Linguists and language activists are currently working toquickly and comprehensively document as many languages as possible. In the unfortunate event that alanguage fades from use, documentation ensures that its data will remain available for future cultural orscientific analysis. This project partially automates the process of language documentation using toolsfrom Natural Language Processing and Machine Learning. It differs from similar projects in using oneintegrated system to process the sounds of speech and the structure of words, instead of using two ormore separate components. With the collaboration of native speaker scholars, the researchers are applyingtheir methodology to four languages: Highland Puebla Nahuatl, Yoloxóchitl Mixtec, San Pedro AmuzgosAmuzgo, and North Slope Iñupiaq.The proposed research will dramatically transform the landscape of automatic morphosyntactic andmorphophonological analysis by introducing an end-to-end system that consumes speech as an input andproduces interlinear annotations as an output. The research team proposes to build an end-to-end system,a single neural net that, with small amounts of labeled data produced by native speaker linguists, candirectly convert recorded speech to analyzed text, producing four outputs: (1) surface transcription, (2)morphological segmentation of surface forms, (3) an underlying or canonical form for each morpheme,and (4) a gloss or standardized label for each morpheme. The proposed single end-to-end neural networkrepresents the first attempt to integrate the four aforementioned tasks into a single neural network, avoidingthe error-propagation problems that have plagued earlier attempts at creating a pipeline and mitigating thecomplexity of the technology for end-users. The researchers also propose innovative ways to incorporate linguisticknowledge into neural networks, including the use of differentiable weighted finite-state transducers,which are independently motivated by an iterative self-training architecture. This approach to iterative self training,in its own right, will represent an advance in machine learning — a new algorithm for upweightingwords and morphemes. The research also makes significant contributions to computational morphology.It includes a simple but expressive modification to existing schemes for segmentation and glossing, specificallyfor the representation of discontinuous morphemes. Furthermore, the proposal extends popularapproaches to morphological analysis (e.g., UniMorph) by systematically addressing derivation as well asinflection. This proposal addresses glossing of reduplication and noun-incorporation, which earlier workhas not.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.

当今世界上大约有7,000种语言，但是这个数字正好在下降。几千语言在一代人的一代人中可能会失去数千句话。对于这些语言的演讲者来说，这代表了文化和语言遗产的悲惨丧失，这是其社会认同的重要锚点。每种语言还携带有关语言作为人类行为现象的可替代数据，这是其变异的局限性以及其结构和发展中的模式。语言学家和语言活动家目前正在快速，全面地记录尽可能多的语言。在不幸的情况下，流动从使用中逐渐消失，文档可确保其数据仍可用于未来的文化或学科分析。该项目通过自然语言处理和机器学习中的工具部分自动化语言文档的过程。在使用一个集成系统来处理语音和单词结构的情况下，它与类似项目不同，而不是使用两个或更多单独的组件。通过以母语为母语的学者的合作，研究人员将其方法应用于四种语言：高地Puebla Nahuatl，YoloxóchitlMixtec，San Pedro Amuzgosamuzgo和NorthSlopeIñupiaq。提议的研究将通过以下方式进行自动分析，以启动自动分析，以进行自动分析。作为输入并产生与输出的中间性注释。 The research team proposals to build an end-to-end system,a single neutral net that, with small amounts of labeled data produced by native speaker linguists, candirectly convert recorded speech to analyzed text, producing four outputs: (1) surface transcription, (2)morphological segmentation of surface forms, (3) an underlying or canonical form for each morpheme, and (4) a gloss or standardized label for each morpheme.提出的单一端到端神经元网络表达者首次尝试将四个先前的任务集成到一个单个神经元网络中，避免了错误传播问题，这些问题困扰着早期尝试创建管道并减轻最终用户技术复杂性的尝试。研究人员还提出了将语言学纳入神经网络的创新方法，包括使用可区分的加权有限态传感器，这些换能器是由迭代自我训练架构独立动机的。这种迭代自我训练的方法本身将代表机器学习的进步，这是一种用于上升文字和词素的新算法。这项研究还为计算形态做出了重大贡献。它包括对现有方案进行分割和掩盖方案的简单但表达性的修改，此外，该提案通过系统地解决派生和膨胀来扩展流行的形态分析方法（例如，Unimorph）。该提案涉及重复和名词结构化的掩盖，这不是更早的工作。该奖项反映了NSF的法定任务，并通过使用基金会的知识分子优点和更广泛的影响审查标准来评估被认为是宝贵的支持。

项目成果

Syntax and Semantics Meet in the “Middle”: Probing the Syntax-Semantics Interface of LMs Through Agentivity

语法和语义在“中间”相遇：通过主体性探索 LM 的语法-语义接口

• DOI: 10.18653/v1/2023.starsem-1.14
• 发表时间: 2023
• 期刊: Proceedings of the 12th Joint Conference on Lexical and Computational Semantics (*SEM 2023
• 作者: Tjuatja, Lindia;Liu, Emmy;Levin, Lori;Neubig, Graham
• 通讯作者: Neubig, Graham

SigMoreFun Submission to the SIGMORPHON Shared Task on Interlinear Glossing

• DOI: 10.18653/v1/2023.sigmorphon-1.22
• 发表时间: 2023
• 作者: Taiqi He;Lindia Tjuatja;Nathaniel R. Robinson;Shinji Watanabe;David R. Mortensen;Graham Neubig;Lori Levin

Generalized Glossing Guidelines: An Explicit, Human- and Machine-Readable, Item-and-Process Convention for Morphological Annotation

通用注释指南：用于形态注释的明确的、人类和机器可读的项目和进程约定

• DOI: 10.18653/v1/2023.sigmorphon-1.7
• 发表时间: 2023
• 期刊: and Morphology
• 作者: Mortensen, David R.;Gulsen, Ela;He, Taiqi;Robinson, Nathaniel;Amith, Jonathan;Tjuatja, Lindia;Levin, Lori
• 通讯作者: Levin, Lori