A Parse-and-Trim Approach with Information Significance for Chinese Sentence Compression

In this paper, we propose an event-based approach for Chinese sentence compression without using any training corpus. We enhance the linguistically-motivated heuristics by exploiting event word significance and event information density. This is shown to improve the preservation of important information and the tolerance of POS and parsing errors, which are more common in Chinese than English. The heuristics are only required to determine possibly removable constituents instead of selecting specific constituents for removal, and thus are easier to develop and port to other languages and domains. The experimental results show that around 72% of our automatic compressions are grammatically and semantically correct, preserving around 69% of the most important information on average.

• Publication year

  2009

• Venue

  Unknown venue

• Publication date

  2009-08-06

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.3115/1708155.1708164
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Who, What, When, Where, Why? Comparing Multiple Approaches to the Cross-Lingual 5W Task

  2009cited by this paper
• Self-Training PCFG Grammars with Latent Annotations Across Languages

  2009cited by this paper
• Large Margin Synchronous Generation and its Application to Sentence Compression

  2007cited by this paper
• Lexicalized Markov Grammars for Sentence Compression

  2007cited by this paper
• Extractive Summarization using Inter- and Intra- Event Relevance

  2006cited by this paper
• Models for Sentence Compression: A Comparison across Domains, Training Requirements and Evaluation Measures

  2006cited by this paper
• Supervised and Unsupervised Learning for Sentence Compression

  2005cited by this paper
• Speech Summarization: An Approach through Word Extraction and a Method for Evaluation

  2004cited by this paper
• Probabilistic Sentence Reduction Using Support Vector Machines

  2004cited by this paper
• Hedge Trimmer: A Parse-and-Trim Approach to Headline Generation

  2003influential reference
• The Columbia Multi-Document Summarizer for DUC 2002

  2002cited by this paper
• Summarization beyond sentence extraction: A probabilistic approach to sentence compression

  2002influential reference
• Sentence Reduction for Automatic Text Summarization

  2000cited by this paper

• Into the Dynamics of Interpersonal Relationships from Diachronic Documents: Text-Based Temporal Social Network Construction

  2023cites this paper
• From Lengthy to Lucid: A Systematic Literature Review on NLP Techniques for Taming Long Sentences

  2023cites this paper
• Assessing Word Importance Using Models Trained for Semantic Tasks

  2023cites this paper
• SOM-NCSCM : An Efficient Neural Chinese Sentence Compression Model Enhanced with Self-Organizing Map

  2021cites this paper
• Neural CRF Model for Sentence Alignment in Text Simplification

  2020cites this paper
• Neural CRF Sentence Alignment Model for Text Simplification

  2020cites this paper
• Chinese Sentence Compression Algorithm Based on Deep Analysis of Sentence Hierarchy in Multiple Application Scenarios

  2020cites this paper
• Research on Chinese Sentence Compression Automatic Evaluation Method based on Sentence Hierarchical Information Extraction

  2020cites this paper
• Extremely Low Resource Text simplification with Pre-trained Transformer Language Model

  2019cites this paper
• Lexical Substitution is Practical for Rare Word Simplification

  2018cites this paper
• Sentence simplification with core vocabulary

  2017cites this paper
• Problems in Current Text Simplification Research: New Data Can Help

  2015cites this paper
• Data-driven Approaches for Paraphrasing across Language Variations

  2014cites this paper