Towards strict sentence intersection: decoding and evaluation strategies

Authors:
Kapil Thadani;Kathleen McKeown
Affiliations:
Columbia University, New York, NY;Columbia University, New York, NY
Venue:
MTTG '11 Proceedings of the Workshop on Monolingual Text-To-Text Generation
Year:
2011

Citing 29
Cited 0

WordNet: a lexical database for English

Communications of the ACM
A systematic comparison of various statistical alignment models

Computational Linguistics
Cut and paste based text summarization

NAACL 2000 Proceedings of the 1st North American chapter of the Association for Computational Linguistics conference
BLEU: a method for automatic evaluation of machine translation

ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
A categorial variation database for English

NAACL '03 Proceedings of the 2003 Conference of the North American Chapter of the Association for Computational Linguistics on Human Language Technology - Volume 1
Sentence Fusion for Multidocument News Summarization

Computational Linguistics
Supervised and unsupervised learning for sentence compression

ACL '05 Proceedings of the 43rd Annual Meeting on Association for Computational Linguistics
Semantic taxonomy induction from heterogenous evidence

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
Stochastic language generation using WIDL-expressions and its application in machine translation and summarization

ACL-44 Proceedings of the 21st International Conference on Computational Linguistics and the 44th annual meeting of the Association for Computational Linguistics
A formal model for information selection in multi-sentence text extraction

COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Automatic evaluation of machine translation quality using n-gram co-occurrence statistics

HLT '02 Proceedings of the second international conference on Human Language Technology Research
Query-based sentence fusion is better defined and leads to more preferred results than generic sentence fusion

HLT-Short '08 Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics on Human Language Technologies: Short Papers
A framework for identifying textual redundancy

COLING '08 Proceedings of the 22nd International Conference on Computational Linguistics - Volume 1
Sentence fusion via dependency graph compression

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
Cheap and fast---but is it good?: evaluating non-expert annotations for natural language tasks

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
A phrase-based alignment model for natural language inference

EMNLP '08 Proceedings of the Conference on Empirical Methods in Natural Language Processing
MICA: a probabilistic dependency parser based on tree insertion grammars application note

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Tree linearization in English: improving language model based approaches

NAACL-Short '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Companion Volume: Short Papers
Global inference for sentence compression an integer linear programming approach

Journal of Artificial Intelligence Research
Sentence compression as tree transduction

Journal of Artificial Intelligence Research
Concise integer linear programming formulations for dependency parsing

ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 1 - Volume 1
Dependency tree based sentence compression

INLG '08 Proceedings of the Fifth International Natural Language Generation Conference
Time-efficient creation of an accurate sentence fusion corpus

HLT '10 Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Creating a bi-lingual entailment corpus through translations with Mechanical Turk: $100 for a 10-day rush

CSLDAMT '10 Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk
Error driven paraphrase annotation using Mechanical Turk

CSLDAMT '10 Proceedings of the NAACL HLT 2010 Workshop on Creating Speech and Language Data with Amazon's Mechanical Turk
Title generation with quasi-synchronous grammar

EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
On the limits of sentence compression by deletion

Empirical methods in natural language generation
Optimal and syntactically-informed decoding for monolingual phrase-based alignment

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers - Volume 2
The PASCAL recognising textual entailment challenge

MLCW'05 Proceedings of the First international conference on Machine Learning Challenges: evaluating Predictive Uncertainty Visual Object Classification, and Recognizing Textual Entailment

Quantified Score

Hi-index	0.00

Visualization

Abstract

We examine the task of strict sentence intersection: a variant of sentence fusion in which the output must only contain the information present in all input sentences and nothing more. Our proposed approach involves alignment and generalization over the input sentences to produce a generation lattice; we then compare a standard search-based approach for decoding an intersection from this lattice to an integer linear program that preserves aligned content while minimizing the disfluency in interleaving text segments. In addition, we introduce novel evaluation strategies for intersection problems that employ entailment-style judgments for determining the validity of system-generated intersections. Our experiments show that the proposed models produce valid intersections a majority of the time and that the segmented decoder yields advantages over the search-based approach.