Constraint-Based Sentence Compression: An Integer Programming Approach

By James Clarke, Mirella Lapata. 2006

77 citations recorded by the source corpus.

The ability to compress sentences while preserving their grammaticality and most of their meaning has recently received much attention. Our work views sentence compression as an optimisation problem. We develop an integer programming formulation and infer globally optimal compressions in the face of linguistically motivated constraints. We show that such a formulation allows for relatively simple and knowledge-lean compression models that do not require parallel corpora or large-scale resources. The proposed approach yields results comparable and in some cases superior to state-of-the-art.

Subfields: Artificial Intelligence, Summarization, Mathematical Optimization

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Summarization

In Mathematical Optimization

Citations in the corpus

Global joint models for coreference resolution and named entity classification (2009, methodology): “…named entity classification Table 2: Recall (R), precision (P), and f -score (F) using muc, b 3 , and ceaf on the entire ace corpus for the basic coreference system, the cascade systems, and the corresponding oracle systems. and Yih (2004), Barzilay and Lapata (2006), and Clarke and Lapata (2006).”
A Constrained Latent Variable Model for Coreference Resolution (2013, background): “…approach to coreference (Ng and Cardie, 2002; Bengtson and Roth, 2008), and (b) the injection of domain knowledge-based constraints for structured prediction (Roth and Yih, 2004; Clarke and Lapata, 2006; Chang et al., 2012b; Ganchev et al., 2010; Koo et al., 2010; Pascal and Baldridge, 2009).”
Generalizing Image Captions for Image-Text Parallel Corpus (2013, methodology): “4 Alternatively, one can ﬁnd an approximate solution using Integer Linear Programming (e.g., Clarke and Lapata (2006), Clarke and Lapata (2007), Martins and Smith (2009)).”
A Study of Global Inference Algorithms in Multi-document Summarization (2007, methodology): “This includes applications to relation and entity classification [21], sentence compression [4], temporal link analysis [3], as well as syntactic and semantic parsing [19, 20].”
Multi-Task Learning for Sequence Tagging: An Empirical Study (2018, background): “For sentence compression ( COM ), we identify which words to keep in a compressed version of sentences from the 1996 English Broadcast News Speech (HUB4) (Graff, 1997), created by (Clarke and Lapata, 2006) 4 .”
Collective Generation of Natural Image Descriptions (2012, unknown): “We employ Integer Linear Programming (ILP) as an optimization framework that has been used successfully in other generation tasks (e.g., Clarke and Lapata (2006), Mar-tins and Smith (2009), Woodsend and Lapata (2010)).”