Discourse Structure Analysis+Anaphora Resolution.ppt

Discourse Structure Analysis+Anaphora Resolution wanghf@pku.edu.cn Content Part I: Discourse analysis Part II: Reference Resolution Part III: Our work Part I: Discourse Analysis Coherence Two Theories on Discourse Structure Cohesion Two Examples Ex1: 比尔来自于美国。今天交通非常拥挤。长江贯穿中国的多个省市。因此，计算语言学是计算机科学与语言学的交叉。 4 correct sentences but collectively do not make sense Ex2: 这里的交通非常拥挤。张先生早上6：40之前就得出发去上班，常常会提前半小时到单位；如果稍晚一点，他就很可能迟到。 it makes sense Coherence Longman: a reasonable connection or relation between ideas, arguments, statements etc: An overall theme will help to give your essay coherence. [现汉]连贯/联贯：连接贯通。上下文意思要 ~ | 长江大桥把南北交通 ~ 起来 Discourse parsing Part I: Discourse Analysis Coherence Two Theories on Discourse Structure Cohesion How to Analyze DS? Mann and Thompson’s Rhetorical structure theory Grosz and Sidner’s Centering theory … Rhetorical structure theory One theory of discourse structure, based on identifying relations between parts of the text: Assumes that a text is divided hierarchically into units Defined 23 rhetorical relations Presentational relations: intentional Subject matter relations: informational Nucleus: central segment of text Satellite: more peripheral segment RST schemes RST relations Subject matter (informational) Elaboration Circumstance Solutionhood Volitional Cause Volitional Result Non-Volitional Cause Non-Volitional Result Purpose Condition Otherwise Interpretation Evaluation Restatement Summary Sequence Contrast Problems multiple interpretations how many relations? how relations are discovered (how to build the text tree)? Multiple interpretations 1. Come back at 5:00. 2. Then we can go to the hardware store before it closes. 3. This way we can finish the bookshelves tonight. Centering Theory explains why certain texts are more difficult to process than others explains why we use the pronouns the way we use them anchors a practical approach for anaphora resolution A smooth discourse a. Jeff1 helped Dick2 wash the car. b. He1 washed t