A Language-Independent Anaphora Resolution System for Understanding Multilingual Texts

This paper describes a new discourse module within our multilingual NLP system. Because of its unique data-driven architecture, the discourse module is language-independent. Moreover, the use of hierarchically organized multiple knowledge sources makes the module robust and trainable using discourse-tagged corpora. Separating discourse phenomena from knowledge sources makes the discourse module easily extensible to additional phenomena. 1 I n t r o d u c t i o n This paper describes a new discourse module within our multilingual natural language processing system which has been used for understanding texts in English, Spanish and Japanese (el. [1, 2])) The following design principles underlie the discourse module: • Language-independence: No processing code depends on language-dependent facts. • Extensibility: It is easy to handle additional phenomena. • Robustness: The discourse module does its best even when its input is incomplete or wrong. • Trainability: The performance can be tuned for particular domains and applications. In the following, we first describe the architecture of the discourse module. Then, we discuss how its performance is evaluated and trained using discoursetagged corpora. Finally, we compare our approach to other research. 1 Our s y s t e m has been used in severa l d a t a e x t r a c t i o n t a sks a n d a p r o t o t y p e n lach ine t r a n s l a t i o n sys te ln . p e r f o . m . . . . ~ n t i ~ u 2 k c $ ~ " e d v . . . . . . . . . . . . . . . . . . . . . . . . . . r . . . . . . . . . . . . . . . . . . . . o . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . , l : ) i ~ ~ M o d u l e Figure 1: Discourse Architecture 2 D i s c o u r s e A r c h i t e c t u r e Our discourse module consists of two discourse processing submodules (the Discourse A dministralor and the Resolution Engine), and three discourse knowledge bases (the Discourse Knowledge Source KB, the Discourse Phenomenon KB, and the Discourse Domain KB). The Discourse Administrator is a development-time tool for defining the three discourse KB's. The Resolution Engine, on the other hand, is the run-time processing module which actually performs anaphora resolution using these discourse KB's. The Resolution Engine also has access to an external discourse data structure called the global discourse world, which is created by the top-level text processing controller. The global discourse world holds syntactic, semantic, rhetorical, and other information about the input text derived by other parts of the system. The architecture is shown in Figure i. 2.1 D i s c o u r s e D a t a S t r u c t u r e s There are four major discourse data types within the global discourse world: Discourse World (DW), [)is-