Dependency tree based sentence compression
Katja Filippova,Michael Strube +1 more
- 12 Jun 2008
- pp 25-32
TL;DR: A novel unsupervised method for sentence compression which relies on a dependency tree representation and shortens sentences by removing subtrees and it is demonstrated that the choice of the parser affects the performance of the system.
read more
Abstract: We present a novel unsupervised method for sentence compression which relies on a dependency tree representation and shortens sentences by removing subtrees. An automatic evaluation shows that our method obtains result comparable or superior to the state of the art. We demonstrate that the choice of the parser affects the performance of the system. We also apply the method to German and report the results of an evaluation with humans.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
Optimizing Statistical Machine Translation for Text Simplification
TL;DR: This work is the first to design automatic metrics that are effective for tuning and evaluating simplification systems, which will facilitate iterative development for this task.
Problems in Current Text Simplification Research: New Data Can Help
TL;DR: This opinion paper argues that focusing on Wikipedia limits simplification research, and introduces a new simplification dataset that is a significant improvement over Simple Wikipedia, and presents a novel quantitative-comparative approach to study the quality of simplification data resources.
•Proceedings Article
A Monolingual Tree-based Translation Model for Sentence Simplification
Zhemin Zhu,Delphine Bernhard,Iryna Gurevych +2 more
- 23 Aug 2010
TL;DR: A Tree-based Simplification Model (TSM) is proposed, which, to the knowledge, is the first statistical simplification model covering splitting, dropping, reordering and substitution integrally.
482
Encode, Tag, Realize: High-Precision Text Editing
Eric Malmi,Sebastian Krause,Sascha Rothe,Daniil Mirylenka,Aliaksei Severyn +4 more
- 03 Sep 2019
TL;DR: LaserTagger is proposed - a sequence tagging approach that casts text generation as a text editing task, and it is shown that at inference time tagging can be more than two orders of magnitude faster than comparable seq2seq models, making it more attractive for running in a live environment.
•Proceedings Article
Multi-Sentence Compression: Finding Shortest Paths in Word Graphs
Katja Filippova
- 23 Aug 2010
TL;DR: Despite its simplicity, the proposed multi-sentence compression method is capable of generating grammatical and informative summaries as its experiments with English and Spanish data demonstrate.
References
Accurate Unlexicalized Parsing
Dan Klein,Christopher D. Manning +1 more
- 07 Jul 2003
TL;DR: It is demonstrated that an unlexicalized PCFG can parse much more accurately than previously shown, by making use of simple, linguistically motivated state splits, which break down false independence assumptions latent in a vanilla treebank grammar.
•Proceedings Article
Generating Typed Dependency Parses from Phrase Structure Parses
Marie-Catherine de Marneffe,Bill MacCartney,Christopher D. Manning +2 more
- 01 May 2006
TL;DR: A system for extracting typed dependency parses of English sentences from phrase structure parses that captures inherent relations occurring in corpus texts that can be critical in real-world applications is described.
Lexicalized Markov Grammars for Sentence Compression
Michel Galley,Kathleen R. McKeown +1 more
- 01 Apr 2007
TL;DR: A headdriven Markovization formulation of SCFG deletion rules is defined, which allows us to lexicalize probabilities of constituent deletions, and a robust approach for tree-to-tree alignment between arbitrary document-abstract parallel corpora is used.
Linguistically informed statistical models of constituent structure for ordering in sentence realization
Eric K. Ringger,Michael Gamon,Robert C. Moore,David Michael Rojas,Martine Smets,Simon Corston-Oliver +5 more
- 23 Aug 2004
TL;DR: It is found that a particular conditional model outperforms all others in sentence realization for French and German and is employed in an evaluation on unordered trees from the Penn TreeBank.
A statistical approach to automatic speech summarization
TL;DR: The experimental results indicate that the method proposed can effectively extract relatively important information and remove redundant and irrelevant information from English news broadcasts.
Related Papers (5)
Kevin Knight,Daniel Marcu +1 more
- 30 Jul 2000
Chin-Yew Lin
- 25 Jul 2004
Taylor Berg-Kirkpatrick,Daniel Gillick,Dan Klein +2 more
- 19 Jun 2011