Aligning Formal Meaning Representations with Surface Strings for Wide-Coverage Text Generation

Statistical natural language generation from abstract meaning representations presupposes large corpora consisting of text‐meaning pairs. Even though such corpora exist nowadays, or could be constructed using robust semantic parsing, the simple alignment between text and meaning representation is too coarse for developing robust (statistical) NLG systems. By reformatting semantic representations as graphs, fine-grained alignment can be obtained. Given a precise alignment at the word level, the complete surface form of a meaning representations can be deduced using a simple declarative rule.

[1]  S. Abney.  Linguistic Issues in Language Technology LiLT , 2011 .

[2]  Johan Bos,et al.  Wide-Coverage Semantic Analysis with Boxer , 2008, STEP.

[3]  Johan Bos,et al.  Towards Generating Text from Discourse Representation Structures , 2011, ENLG.

[4]  Leo Wanner,et al.  Towards a Surface Realization-Oriented Corpus Annotation , 2012, INLG.

[5]  Kei Yoshimoto,et al.  Banking Meaning Representations from Treebanks , 2012 .

[6]  Phong Le,et al.  Learning Compositional Semantics for Open Domain Semantic Parsing , 2012, COLING.

[7]  Johan Bos,et al.  Verbmobil Interface Terms (VITs) , 2000 .

[8]  Dan Flickinger,et al.  Translation using Minimal Recursion Semantics , 1995, TMI.

[9]  Michael White,et al.  Towards broad coverage surface realization with CCG , 2007, MTSUMMIT.

[10]  Leo Wanner,et al.  Broad Coverage Multilingual Deep Sentence Generation with a Stochastic Multi-Level Realizer , 2010, COLING.

[11]  Controlling Logical Scope in Text Generation , 1999 .

[12]  Uwe Reyle,et al.  Dealing with Ambiguities by Underspecification: Construction, Representation and Deduction , 1993, J. Semant..

[13]  I. I. N. Kamp.  Combining Montague Semantics and Discourse Representation , 1996 .

[14]  Paul Piwek,et al.  What is NLG? , 2002, INLG.

[15]  Ian Horrocks,et al.  A Description Logic with Transitive and Inverse Roles and Role Hierarchies , 1999, J. Log. Comput..

[16]  Leo Wanner,et al.  The Surface Realisation Task: Recent Developments and Future Plans , 2012, INLG.

[17]  James F. Allen,et al.  Deep Semantic Analysis of Text , 2008, STEP.

[18]  Christiane Fellbaum,et al.  Book Reviews: WordNet: An Electronic Lexical Database , 1999, CL.

[19]  Rob A. van der Sandt,et al.  Presupposition Projection as Anaphora Resolution , 1992, J. Semant..

[20]  Stuart M. Shieber,et al.  A Uniform Architecture for Parsing and Generation , 1988, COLING.

[21]  Johan Bos,et al.  Developing a large semantically annotated corpus , 2012, LREC.

[22]  Ehud Reiter,et al.  Book Reviews: Building Natural Language Generation Systems , 2000, CL.

[23]  Josef van Genabith,et al.  Dependency-Based N-Gram Models for General Purpose Sentence Realisation , 2008, COLING.