Antecedent Selection for Sluicing: Structure and Content

Sluicing is an elliptical process where the majority of a question can go unpronounced as long as there is a salient antecedent in previous discourse. This paper considers the task of antecedent selection: finding the correct antecedent for a given case of sluicing. We argue that both syntactic and discourse relationships are important in antecedent selection, and we construct linguistically sophisticated features that describe the relevant relationships. We also define features that describe the relation of the content of the antecedent and the sluice type. We develop a linear model which achieves accuracy of 72.4%, a substantial improvement over a strong manually constructed baseline. Feature analysis confirms that both syntactic and discourse features are important in antecedent selection.

[1]  Jason Merchant,et al.  The syntax of silence : sluicing, islands, and identity in ellipsis , 1999 .

[2]  Martin van den Berg,et al.  A discourse perspective on verb phrase anaphora , 1994 .

[3]  Ivan A. Sag,et al.  Deletion And Logical Form , 1976 .

[4]  Pascal Denis,et al.  Specialized Models and Ranking for Coreference Resolution , 2008, EMNLP.

[5]  Mats Rooth,et al.  Structural Ambiguity and Lexical Relations , 1991, ACL.

[6]  Johan Bos,et al.  An annotated corpus for the analysis of VP ellipsis , 2011, Lang. Resour. Evaluation.

[7]  Daniel Hardt,et al.  An Empirical Approach to VP Ellipsis , 1997, CL.

[8]  Dan Roth,et al.  Understanding the Value of Features for Coreference Resolution , 2008, EMNLP.

[9]  Ken Litkowski,et al.  The Preposition Project , 2021, ArXiv.

[10]  Jonathan Ginzburg,et al.  Interrogative Investigations: The Form, Meaning, and Use of English Interrogatives , 2001 .

[11]  Graeme Hirst,et al.  Interpreting Anaphoric Shell Nouns using Antecedents of Cataphoric Shell Nouns as Training Data , 2013, EMNLP.

[12]  Jonathan Ginzburg,et al.  Automatic Bare Sluice Disambiguation in Dialogue , 2005 .

[13]  Henry Beecher,et al.  Pragmatic Inference in the Interpretation of Sluiced Prepositional Phrases , 2008 .

[14]  A. Lobeck.  Ellipsis: Functional Heads, Licensing, and Identification , 1995 .

[15]  Hwee Tou Ng,et al.  A Machine Learning Approach to Coreference Resolution of Noun Phrases , 2001, CL.

[16]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[17]  Jonathan Ginzburg,et al.  SHARDS: Fragment Resolution in Dialogue , 2008 .

[18]  Jonathan Ginzburg,et al.  Classifying Non-Sentential Utterances in Dialogue: A Machine Learning Approach , 2007, CL.

[19]  D. Hardt.  Dynamic Interpretation of Verb Phrase Ellipsis , 1999 .

[20]  William A. Ladusaw,et al.  Sluicing and logical form , 1995 .

[21]  Daniel Hardt,et al.  Ellipsis and the Structure of Discourse , 2004, J. Semant..

[22]  Sara Cantor.  Ungrammatical double-island sluicing as a diagnostic of left-branch positioning , 2013 .

[23]  S. Anderbois.  The semantics of sluicing: Beyond truth conditions , 2014 .

[24]  Graeme Hirst,et al.  Resolving "This-issue" Anaphora , 2012, EMNLP-CoNLL.

[25]  Stuart M. Shieber,et al.  Ellipsis and higher-order unification , 1991 .

[26]  Pranav Anand,et al.  Annotating the Implicit Content of Sluices , 2015, LAW@NAACL-HLT.