Improving Chinese Semantic Role Labeling using High-quality Surface and Deep Case Frames

This paper presents a method for applying automatically acquired knowledge to semantic role labeling (SRL). We use a large amount of automatically extracted knowledge to improve the performance of SRL. We present two varieties of knowledge, which we call surface case frames and deep case frames. Although the surface case frames are compiled from syntactic parses and can be used as rich syntactic knowledge, they have limited capability for resolving semantic ambiguity. To compensate the deficiency of the surface case frames, we compile deep case frames from automatic semantic roles. We also consider quality management for both types of knowledge in order to get rid of the noise brought from the automatic analyses. The experimental results show that Chinese SRL can be improved using automatically acquired knowledge and the quality management shows a positive effect on this task.

[1]  Collin F. Baker,et al.  Building a Large Lexical Databank Which Provides Deep Semantics , 2001, PACLIC.

[2]  Ding Liu,et al.  Semantic Role Features for Machine Translation , 2010, COLING.

[3]  Eneko Agirre,et al.  Generalizing over Lexical Features: Selectional Preferences for Semantic Role Classification , 2009, ACL/IJCNLP.

[4]  Daisuke Kawahara,et al.  A Fully-Lexicalized Probabilistic Model for Japanese Syntactic and Case Structure Analysis (Special Issue : "Collection of Best Annual Papers" Organized for the 20th Anniversary of the Association for Natural Language Processing) , 2006 .

[5]  Pierre Nugues,et al.  Multilingual Semantic Role Labeling , 2009, CoNLL Shared Task.

[6]  Xiaolong Wang,et al.  A Joint Syntactic and Semantic Dependency Parsing System based on Maximum Entropy Models , 2009, CoNLL Shared Task.

[7]  Diego Molla Aliod,et al.  Indexing on Semantic Roles for Question Answering , 2008, COLING 2008.

[8]  Martha Palmer,et al.  From TreeBank to PropBank , 2002, LREC.

[9]  Marie-Francine Moens,et al.  Semi-supervised Semantic Role Labeling Using the Latent Words Language Model , 2009, EMNLP.

[10]  Oren Etzioni,et al.  Semantic Role Labeling for Open Information Extraction , 2010, HLT-NAACL 2010.

[11]  Yoshua Bengio,et al.  A Neural Probabilistic Language Model , 2003, J. Mach. Learn. Res..

[12]  Roser Morante,et al.  Joint Memory-Based Learning of Syntactic and Semantic Dependencies in Multiple Languages , 2009, CoNLL Shared Task.

[13]  Martha Palmer,et al.  Inducing Example-based Semantic Frames from a Massive Amount of Verb Uses , 2014, EACL.

[14]  Daisuke Kawahara,et al.  A Framework for Compiling High Quality Knowledge Resources From Raw Corpora , 2014, LREC.

[15]  Hai Zhao,et al.  Multilingual Dependency Learning: A Huge Feature Engineering Method to Semantic Dependency Parsing , 2009, CoNLL Shared Task.

[16]  Xavier Carreras,et al.  Simple Semi-supervised Dependency Parsing , 2008, ACL.

[17]  Eugene Charniak,et al.  Reranking and Self-Training for Parser Adaptation , 2006, ACL.

[18]  Daisuke Kawahara,et al.  High Quality Dependency Selection from Automatic Parses , 2013, IJCNLP.

[19]  Jason Weston,et al.  Natural Language Processing (Almost) from Scratch , 2011, J. Mach. Learn. Res..