Finding Non-local Dependencies: Beyond Pattern Matching

We describe an algorithm for recovering non-local dependencies in syntactic dependency structures. The pattern-matching approach proposed by Johnson (2002) for a similar task for phrase structure trees is extended with machine learning techniques. The algorithm is essentially a classifier that predicts a non-local dependency given a connected fragment of a dependency structure and a set of structural features for this fragment. Evaluating the algorithm on the Penn Treebank shows an improvement of both precision and recall, compared to the results presented in (Johnson, 2002).

[1]  William Thompson,et al.  A declarative framework for building compositional dialog modules , 2000, INTERSPEECH.

[2]  J. Ross Quinlan,et al.  C4.5: Programs for Machine Learning , 1992 .

[3]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[4]  S. Buchholz,et al.  Memory-Based Grammatical Relation Finding , 2002 .

[5]  Jason Eisner,et al.  Three New Probabilistic Models for Dependency Parsing: An Exploration , 1996, COLING.

[6]  Michael Collins,et al.  Head-Driven Statistical Models for Natural Language Parsing , 2003, CL.

[7]  Bob Carpenter,et al.  The logic of typed feature structures , 1992 .

[8]  Walter Daelemans,et al.  TiMBL: Tilburg Memory-Based Learner, version 2.0, Reference guide , 1998 .

[9]  Eric H. C. Choi,et al.  MULTI-MODAL DIALOGUES AS NATURAL USER INTERFACE FOR AUTOMOBILE ENVIRONMENT , 2002 .

[10]  Mark Johnson,et al.  A Simple Pattern-matching Algorithm for Recovering Empty Nodes and their Antecedents , 2002, ACL.

[11]  Antonella De Angeli,et al.  Integration and synchronization of input modes during multimodal human-computer interaction , 1997, CHI.

[12]  Anurag Gupta A reference model for multimodal input interpretation , 2003, CHI Extended Abstracts.

[13]  Mark Steedman,et al.  Building Deep Dependency Structures using a Wide-Coverage CCG Parser , 2002, ACL.

[14]  Sharon L. Oviatt,et al.  Designing the User Interface for Multimodal Speech and Pen-Based Gesture Applications: State-of-the-Art Systems and Future Research Directions , 2000, Hum. Comput. Interact..

[15]  Ted Briscoe,et al.  Relational evaluation schemes , 2002 .