Aggregation via Set Partitioning for Natural Language Generation

The role of aggregation in natural language generation is to combine two or more linguistic structures into a single sentence. The task is crucial for generating concise and readable texts. We present an efficient algorithm for automatically learning aggregation rules from a text and its related database. The algorithm treats aggregation as a set partitioning problem and uses a global inference procedure to find an optimal solution. Our experiments show that this approach yields substantial improvements over a clustering-based model which relies exclusively on local information.

[1]  Edward H. Hovy,et al.  Unresolved issues in paragraph planning , 1990 .

[2]  Clarisse Sieckenius de Souza,et al.  Getting the message across in RST-based text generation , 1990 .

[3]  Ronald L. Rivest,et al.  Introduction to Algorithms , 1990 .

[4]  Eduard H. Hovy,et al.  Aggregation in Natural Language Generation , 1993, EWNLG.

[5]  John Wilkinson,et al.  Aggregation in Natural Language Generation: Another Look , 1995 .

[6]  James Shaw Clause Aggregation Using Linguistic Knowledge , 1998, INLG.

[7]  A. Yeung Cognitive Load and Learner Expertise: Split-Attention and Redundancy Effects in Reading Comprehension Tasks With Vocabulary Definitions , 1999 .

[8]  Chris Mellish,et al.  Capturing the Interaction between Aggregation and Text Planning in Two Generation Systems , 2000, INLG.

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

[10]  Marilyn A. Walker,et al.  SPoT: A Trainable Sentence Planner , 2001, NAACL.

[11]  Dan Roth,et al.  Semantic Role Labeling Via Integer Linear Programming Inference , 2004, COLING.

[12]  Dan Roth,et al.  A Linear Programming Formulation for Global Inference in Natural Language Tasks , 2004, CoNLL.

[13]  Davide Fossati,et al.  Aggregation Improves Learning: Experiments in Natural Language Generation for Intelligent Tutoring Systems , 2005, ACL.

[14]  Michael Strube,et al.  Beyond the Pipeline: Discrete Optimization in NLP , 2005, CoNLL.

[15]  Mirella Lapata,et al.  Collective Content Selection for Concept-to-Text Generation , 2005, HLT.

[16]  M. Reape,et al.  Just what is aggregation anyway ? , 2007 .