Semantic Frame Labeling with Target-based Neural Model

This paper explores the automatic learning of distributed representations of the target’s context for semantic frame labeling with target-based neural model. We constrain the whole sentence as the model’s input without feature extraction from the sentence. This is different from many previous works in which local feature extraction of the targets is widely used. This constraint makes the task harder, especially with long sentences, but also makes our model easily applicable to a range of resources and other similar tasks. We evaluate our model on several resources and get the state-of-the-art result on subtask 2 of SemEval 2015 task 15. Finally, we extend the task to word-sense disambiguation task and we also achieve a strong result in comparison to state-of-the-art work.

[1]  Hwee Tou Ng,et al.  It Makes Sense: A Wide-Coverage Word Sense Disambiguation System for Free Text , 2010, ACL.

[2]  Martha Palmer,et al.  SemEval-2007 Task-17: English Lexical Sample, SRL and All Words , 2007, Fourth International Workshop on Semantic Evaluations (SemEval-2007).

[3]  Adam Kilgarriff,et al.  SemEval-2015 Task 15: A CPA dictionary-entry-building task , 2015, *SEMEVAL.

[4]  Ari Rappoport,et al.  A Supervised Algorithm for Verb Disambiguation into VerbNet Classes , 2008, COLING.

[5]  Vít Baisa,et al.  Automatic classification of patterns from the Pattern Dictionary of English Verbs , 2014 .

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

[7]  Daniel Gildea,et al.  The Proposition Bank: An Annotated Corpus of Semantic Roles , 2005, CL.

[8]  Martha Palmer,et al.  Verbnet: a broad-coverage, comprehensive verb lexicon , 2005 .

[9]  Matthew Honnibal,et al.  Identifying FrameNet Frames for Verbs from a Real-Text Corpus , 2005, ALTA.

[10]  Dong Yu,et al.  An End-to-end Approach to Learning Semantic Frames with Feedforward Neural Network , 2016, SRW@HLT-NAACL.

[11]  Patrick Hanks.  How people use words to make meanings : Semantic types meet valencies , 2012 .

[12]  Francesco Elia.  Syntactic and semantic classification of verb arguments using dependency-based and rich semantic features , 2016, ArXiv.

[13]  Dong Yu,et al.  BLCUNLP: Corpus Pattern Analysis for Verbs Based on Dependency Chain , 2015, SemEval@NAACL-HLT.

[14]  Jason Weston,et al.  Semantic Frame Identification with Distributed Word Representations , 2014, ACL.

[15]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[16]  Ignacio Iacobacci,et al.  Embeddings for Word Sense Disambiguation: An Evaluation Study , 2016, ACL.

[17]  Gina-Anne Levow,et al.  CMILLS: Adapting Semantic Role Labeling Features to Dependency Parsing , 2015, SemEval@NAACL-HLT.

[18]  Martha Palmer,et al.  Combining Lexical Resources: Mapping Between PropBank and VerbNet , 2006 .

[19]  Vít Baisa,et al.  Disambiguating Verbs by Collocation: Corpus Lexicography meets Natural Language Processing , 2014, LREC.

[20]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.