CRII: RI: Learning a Timely Semantic Resource from Social Media Data

CRII：RI：从社交媒体数据中学习及时的语义资源

• 批准号: 2038457
• 负责人: Wei Xu
• 金额: $ 5.3万
• 依托单位: Georgia Tech Research Corporation
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-08-01 至 2021-05-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2038457&HistoricalAwards=false
• 关键词: CRII; RI; Learning; Timely; Semantic

One key challenge in text mining and natural language processing research is that a single meaning can be expressed in many different ways, i.e., paraphrases. There has been steady progress towards large paraphrase resources, and a significant increase in its applications: from information retrieval, information extraction, and natural language generation to IBM's Watson, Google's Knowledge Graph, and many more. This research aims to create better paraphrase acquisition techniques and larger scale semantic resources, which could be of great use in various natural language processing tasks and social media data analytics in social science, national security, and other related fields. One example of potential applications is text simplification, which automatically rephrases complex texts into simpler language for children or people with reading disabilities.The technical innovation of this study focuses on joint modeling of word- and phrase-level alignments between sentence pairs to address the challenges of extracting semantic knowledge from informal data sources (such as social media), which exist in very large quantities rather than just formal sources, such as newswire as per previous work. The model design extends multiple instance learning via two methods, a graphical model and neural network, and can flexibly permit the exploration of different assumptions and models the importance of words or phrases. The modeling advancements can be generalized to other natural language understanding tasks, which require analyzing sentences based on word-level composition or word meaning in a given context, and natural language generation tasks that benefit from learning what words and phrases to remove or rephrase.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.

文本挖掘和自然语言处理研究的一个关键挑战是单一含义可以用多种不同的方式表达，即释义。大型释义资源取得了稳步进展，其应用也显着增加：从信息检索、信息提取、自然语言生成到 IBM 的 Watson、Google 的知识图谱等等。本研究旨在创建更好的释义获取技术和更大规模的语义资源，这在社会科学、国家安全和其他相关领域的各种自然语言处理任务和社交媒体数据分析中具有很大的用途。潜在应用的一个例子是文本简化，它可以自动将复杂的文本重新表述为儿童或有阅读障碍的人更简单的语言。这项研究的技术创新侧重于句子对之间的单词和短语级对齐的联合建模，以应对挑战从非正式数据源（例如社交媒体）中提取语义知识，这些数据存在大量而不仅仅是正式来源，例如根据之前的工作的新闻专线。该模型设计通过图形模型和神经网络两种方法扩展了多实例学习，并且可以灵活地允许探索不同的假设并对单词或短语的重要性进行建模。建模的进步可以推广到其他自然语言理解任务，这些任务需要根据给定上下文中的单词级组成或单词含义来分析句子，以及受益于学习要删除或改写哪些单词和短语的自然语言生成任务。该奖项反映了 NSF 的法定使命，并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，被认为值得支持。

项目成果

A Word-Complexity Lexicon and A Neural Readability Ranking Model for Lexical Simplification

词复杂度词典和词汇简化的神经可读性排序模型

• DOI: 10.18653/v1/d18-1410
• 发表时间: 2018-01
• 期刊: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing
• 作者: Maddela, Mounica;Xu, Wei
• 通讯作者: Xu, Wei

Neural semi-Markov CRF for Monolingual Word Alignment

用于单语词对齐的神经半马尔可夫条件随机场

• DOI: 10.18653/v1/2021.acl-long.531
• 发表时间: 2021-08
• 期刊: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing
• 作者: Lan, Wuwei;Jiang, Chao;Xu, Wei
• 通讯作者: Xu, Wei

Multi-task Pairwise Neural Ranking for Hashtag Segmentation

用于标签分割的多任务成对神经排名

• DOI: 10.18653/v1/p19-1242
• 发表时间: 2019-07
• 期刊: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics
• 作者: Maddela, Mounica;Xu, Wei;Preoţiuc
• 通讯作者: Preoţiuc

Neural Network Models for Paraphrase Identification, Semantic Textual Similarity, Natural Language Inference, and Question Answering

用于释义识别、语义文本相似性、自然语言推理和问答的神经网络模型

• 发表时间: 2018-08
• 期刊: Proceedings of the 27th International Conference on Computational Linguistics
• 作者: Lan, Wuwei;Xu, Wei.
• 通讯作者: Xu, Wei.

Neural CRF Model for Sentence Alignment in Text Simplification

文本简化中句子对齐的神经 CRF 模型

• DOI: 10.18653/v1/2020.acl-main.709
• 发表时间: 2020-01
• 期刊: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
• 作者: Jiang, Chao;Maddela, Mounica;Lan, Wuwei;Zhong, Yang;Xu, Wei
• 通讯作者: Xu, Wei