Dependency tree based sentence compression

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.

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

“…P (l|h) is the conditional probability of label l given head h. Note that here we use the formula in (Filippova and Altun, 2013) for w inf o (e), which was shown to be more effective for sentence compression than the original formula in (Filippova and Strube, 2008). The optimization problem can be solved under the tree structure and length constraints by integer linear programming 1 .…”

“…Due to space limit, we refer readers to (Filippova and Strube, 2008) for a detailed description of the baseline method.…”

Single Document Summarization based on Nested Tree Structure

“…We allowed our model to extract a subtree that did not include the root word (See the sentence with an asterisk * in Figure 1). The method of Filippova and Strube (2008) allows the model to extract non-rooted subtrees in sentence compression tasks that compress a single sentence with a given compression ratio. However, it is not trivial to apply their method to text summarization because no compression ratio is given to sentences.…”