Unsupervised Sentence Enhancement for Automatic Summarization

Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 775–786, October 25-29, 2014, Doha, Qatar. c⃝2014 Association for Computational Linguistics Unsupervised Sentence Enhancement for Automatic Summarization Jackie Chi Kit Cheung University of Toronto 10 King’s College Rd., Room 3302 Toronto, ON, Canada M5S 3G4 jcheung@cs.toronto.edu Gerald Penn University of Toronto 10 King’s College Rd., Room 3302 Toronto, ON, Canada M5S 3G4 gpenn@cs.toronto.edu Abstract We present sentence enhancement as a novel technique for text-to-text genera- tion in abstractive summarization. Com- pared to extraction or previous approaches to sentence fusion, sentence enhancement increases the range of possible summary sentences by allowing the combination of dependency subtrees from any sentence from the source text. Our experiments in- dicate that our approach yields summary sentences that are competitive with a sen- tence fusion baseline in terms of con- tent quality, but better in terms of gram- maticality, and that the benefit of sen- tence enhancement relies crucially on an event coreference resolution algorithm us- ing distributional semantics. We also consider how text-to-text generation ap- proaches to summarization can be ex- tended beyond the source text by exam- ining how human summary writers incor- porate source-text-external elements into their summary sentences. 1 Introduction Sentence fusion is the technique of merging sev- eral input sentences into one output sentence while retaining the important content (Barzilay and McKeown, 2005; Filippova and Strube, 2008; Thadani and McKeown, 2013). For example, the input sentences in Figure 1 may be fused into one output sentence. As a text-to-text generation technique, sentence fusion is attractive because it provides an avenue for moving beyond sentence extraction in auto- matic summarization, while not requiring deep se- Input: Bil Mar Foods Co., a meat processor owned by Sara Lee, announced a recall of certain lots of hot dogs and packaged meat. Input: The outbreak led to the recall on Tues- day of 15 million pounds of hot dogs and cold cuts produced at the Bil Mar Foods plant. Output: The outbreak led to the recall on Tues- day of lots of hot dogs and packaged meats produced at the Bil Mar Foods plant. Figure 1: An example of fusing two input sen- tences into an output sentence. The sections of the input sentences that are retained in the output are shown in bold. mantic analysis beyond, say, a dependency parser and lexical semantic resources. The overall trajectory pursued in the field can be characterized as a move away from local con- texts relying heavily on the original source text to- wards more global contexts involving reformula- tion of the text. Whereas sentence extraction and sentence compression (Knight and Marcu, 2000, for example) involve taking one sentence and per- haps removing parts of it, traditional sentence fu- sion involves reformulating a small number of rel- atively similar sentences in order to take the union or intersection of the information present therein. In this paper, we move further along this path in the following ways. First, we present sen- tence enhancement …

Content truncated to 500 words