Extracting and Using Discourse Structure to Resolve Anaphoric Dependencies: Combining Logico-Semantics and Statistical Approaches

该项目通过捕获子句之间的重要依赖关系，扩展了开放域报纸文本的自然语言理解系统的分析深度。研究的重点是两个相互依存的任务：（1）确定语篇结构和（2）确定回指表达与其先行词之间的指称联系。 该项目利用了语篇结构的形式理论，即分段语篇表征理论（SDRT）。 SDRT认为，任务（1）和（2）强烈互动：话语结构可以排除许多可能的回指依赖，而解决回指链接可以告知话语关系和段的确定。 这个项目测试这一假设在一个有限的设置为一组有限的话语关系。 Baldridge的概率语篇结构分析器（PDiSP）是处理任务（1）的主要工具，而基于最大熵的回指解析器（AR）处理任务（2）。 该项目包括对语篇结构和照应依赖关系的注释，以帮助指导和培训工具。 与这两种工具相关的特征，如谓词论元结构、时态和体，都来自于广泛覆盖的语法分析器。 词汇信息由OntoClean从Wordnet“sanitized”中提取。 第一阶段的项目调查任务（1）和（2）的相互依赖性，通过使用的PDiSP中的照应词为基础的功能，然后在AR的话语结构的可及性为基础的功能。然后将结果与基线模型以及不具有这些特征的运行AR和PDiSP进行比较。 该项目开发的软件和附加说明的材料将提供给社区。

This project extends the depth of analysis of natural language understanding systems for open-domain newspaper texts by capturing important dependencies between clauses. Two co-dependent tasks are the focus of the study: (1) the determination of discourse structure and (2) the identification of referential links between anaphoric expressions and their antecedents. This project utilizes the formal theory of discourse structure known as Segmented Discourse Representation Theory (SDRT). SDRT claims that tasks (1) and (2) strongly interact: discourse structure can rule out many possible anaphoric dependencies, while resolved anaphoric links can inform the determination of discourse relations and segments. This project tests this hypothesis in a limited setting for a restricted set of discourse relations. Baldridge's Probabilistic Discourse Structure Parser (PDiSP) is the principal tool for addressing task (1), while a Maximum Entropy based Anaphor Resolver (AR) handles task (2). The project involves annotation for discourse structure and anaphoric dependencies to help guide and train the tools. Features relevant to both tools, like predicate argument structure, tense and aspect, are drawn from wide-coverage sentential parsers. Lexical information are drawn from Wordnet ''sanitized'' by OntoClean. The first phase of the project investigates the interdependency of tasks (1) and (2) by using anaphora-based features in the PDiSP and then features based on discourse structure accessibility in the AR. The results are then compared to base line models and to running AR and PDiSP without those features. Both software and annotated materials developed in the project will be made available to the community.