The Influence of Argument Structure on Semantic Role Assignment

We present a data and error analysis for semantic role labelling. In a first experiment, we build a generic statistical model for semantic role assignment in the FrameNet paradigm and show that there is a high variance in performance across frames. The main hypothesis of our paper is that this variance is to a large extent a result of differences in the underlying argument structure of the predicates in different frames. In a second experiment, we show that frame uniformity, which measures argument structure variation, correlates well with the performance figures, effectively explaining the variance.

[1]  Mitchell P. Marcus,et al.  Adding Semantic Annotation to the Penn TreeBank , 1998 .

[2]  Rob Malouf,et al.  A Comparison of Algorithms for Maximum Entropy Parameter Estimation , 2002, CoNLL.

[3]  A. Frank.  Generalisations over Corpus-induced Frame Assignment Rules , 2004 .

[4]  Katrin Erk,et al.  Semantic role labelling with similarity-based generalization using EM-based clustering , 2004, SENSEVAL@ACL.

[5]  Josef Ruppenhofer,et al.  FrameNet: Theory and Practice , 2003 .

[6]  Jeffrey Gruber.  Studies in lexical relations , 1965 .

[7]  John B. Lowe,et al.  The Berkeley FrameNet Project , 1998, ACL.

[8]  Charles J. Fillmore,et al.  Frames and the semantics of understanding , 1985 .

[9]  Roger Levy,et al.  A Generative Model for Semantic Role Labeling , 2003, ECML.

[10]  Ray Jackendoff,et al.  Semantic Interpretation in Generative Grammar , 1972 .

[11]  Manfred Pinkal,et al.  Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic Annotation , 2003, ACL.

[12]  Daniel Gildea,et al.  Automatic Labeling of Semantic Roles , 2000, ACL.

[13]  Frank Keller,et al.  Using the Web to Obtain Frequencies for Unseen Bigrams , 2003, CL.

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

[15]  Ali S. Hadi,et al.  Finding Groups in Data: An Introduction to Chster Analysis , 1991 .

[16]  Thorsten Brants,et al.  TnT – A Statistical Part-of-Speech Tagger , 2000, ANLP.

[17]  Michael Collins,et al.  Three Generative, Lexicalised Models for Statistical Parsing , 1997, ACL.

[18]  Beth Levin,et al.  English Verb Classes and Alternations: A Preliminary Investigation , 1993 .

[19]  Helmut Schmidt,et al.  Probabilistic part-of-speech tagging using decision trees , 1994 .

[20]  Namhee Kwon,et al.  Maximum Entropy Models for FrameNet Classification , 2003, EMNLP.

[21]  Lillian Lee,et al.  Measures of Distributional Similarity , 1999, ACL.