CAREER: Reference Resolution for Natural Language Understanding

这是一个为期四年的持续奖励的第一年。构建健壮的系统来提取和解释信息，并从文本中总结和回答问题，其中一个主要障碍是需要识别代词或其他指称表达所指代的实体。该项目扩展了PI先前的工作，涉及开发一个经验参考解决系统，该系统依赖于与各种形式的参考相对应的几组启发式。特别是，该框架将被扩展以学习支持一致性检查的语义知识。这种增强将提供高精度的参考分辨率，并大大提高参考链接的召回率。研究将使用参考注释文本和宾夕法尼亚大学树库语料库进行评估。结果将是一个基于语料库的方法，用于代词和名义表达式的引用解析。首先，将捕获所有指代名词短语的语义。然后，通过用自举扩展经验环境，这种参考解析技术应该会导致一个强大的工具，能够在各种各样的文本中正确地解析参考。最后，该工具将被纳入信息提取系统和问答系统中，以衡量其对这些系统整体性能的贡献。拟议的研究与以前的参考解析方法不同，因为它提倡数据驱动技术，而不是依赖于语言的语言和认知方面的结合。初步结果所显示的直接实际结果应该是大幅度提高召回率。

This is the first year of funding of a 4-year continuing award. A major obstacle in building robust systemsthat extract and interpret information, and summarize and answer questions from texts, is the need to identify the entities referred to by pronouns or other referential expressions. This project extends the PI's prior work involving the development of an empirical reference resolution system that relies on several sets of heuristics that correspond to various forms of reference. In particular, the framework will be extended to learn semantic knowledge that supports consistency checks. This enhancement will provide high precision reference resolution and also enhance substantially the recall of referential links. The research will be evaluated using referenceannotated texts and the Penn Treebank corpora. The outcome will be a corpus-based method for reference resolution for both pronouns and nominal expressions. First, the semantics of all referential noun phrases will be captured. Then, by extending the empirical environment with bootstrapping, this reference resolution technique should lead to a powerful tool capable of resolving reference correctly in a large variety of texts. Finally, the tool will be incorporated both in an information extraction system and in a question/answering system, to measure its contribution to the overall performance of these systems. The proposed research departs from previous approaches to reference resolution, in that it promotes data-driven techniques instead of relying on combinations of linguistic and cognitive aspects of language. The immediate pragmatic outcome indicated by the preliminary results should be a substantial recall enhancement.