Statistical sentence condensation using ambiguity packing and stochastic disambiguation methods for Lexical-Functional Grammar

Abstract

We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. Our system incorporates a linguistic parser/generator for LFG, a transfer component for parse reduction operating on packed parse forests, and a maximum-entropy model for stochastic output selection. Furthermore, we propose the use of standard parser evaluation methods for automatically evaluating the summarization quality of sentence condensation systems. An experimental evaluation of summarization quality shows a close correlation between the automatic parse-based evaluation and a manual evaluation of generated strings. Overall summarization quality of the proposed system is state-of-the-art, with guaranteed grammaticality of the system output due to the use of a constraint-based parser/generator. Recent work in statistical text summarization has put forward systems that do not merely extract and concatenate sentences, but learn how to generate new sentences from Summary, T ext tuples. Depending on the chosen task, such systems either generate single-sentence "headlines" for multi-sentence text (Witbrock and Mittal, 1999), or they provide a sentence condensation module designed for combination with sentence extraction systems (Knight and Marcu, 2000;Jing, 2000). The challenge for such systems is to guarantee the grammaticality and summarization quality of the system output, i.e. the generated sentences need to be syntactically wellformed and need to retain the most salient information of the original document. For example a sentence extraction system might choose a sentence like:Edmonton,

Improving sentence compression by learning to predict gaze

“…Most recent approaches to sentence compression make use of syntactic analysis, either by operating directly on trees (Riezler et al, 2003;Nomoto, 2007;Filippova and Strube, 2008;Cohn and Lapata, 2008;Cohn and Lapata, 2009) or by incorporating syntactic information in their model (McDonald, 2006;Clarke and Lapata, 2008). Recently, however, Filippova et al (2015) presented an approach to sentence compression using LSTMs with word embeddings, but without syntactic features.…”

Using Tweets to Help Sentence Compression for News Highlights Generation

“…This method achieved a higher F-score (Riezler et al, 2003) than other systems on the Edinburgh corpus (Clarke and Lapata, 2006). We will introduce the baseline in this part and describe our extended model that leverages tweet information in the next subsection.…”

An abstractive approach to sentence compression

“…Improvements upon this model include Markovization [Galley and McKeown 2007] and the addition of specialized rules to model syntactically complex expressions [Turner and Charniak 2005]. Discriminative approaches include decisiontree learning [Knight and Marcu 2002], maximum entropy [Riezler et al 2003], support vector machines [Nguyen et al 2004], large margin learning [McDonald 2006;Cohn and Lapata 2009], and minimum classification error learning [Hirao et al 2009]. …”