Alejandro Molina

Discourse segmentation for sentence compression

Earlier studies have raised the possibility of summarizing at the level of the sentence. This simplification should help in adapting textual content in a limited space. Therefore, sentence compression is an important resource for automatic summarization systems. However, there are few studies that consider sentence-level discourse segmentation for compression task; to our knowledge, none in Spanish. In this paper, we study the relationship between discourse segmentation and compression for sentences in Spanish. We use a discourse segmenter and observe to what extent the passages deleted by annotators fit in discourse structures detected by the system. The main idea is to verify whether the automatic discourse segmentation can serve as a basis in the identification of segments to be eliminated in the sentence compression task. We show that discourse segmentation could be a first solid step towards a sentence compression system.

Discursive sentence compression

This paper presents a method for automatic summarization by deleting intra-sentence discourse segments. First, each sentence is divided into elementary discourse units and, then, less informative segments are deleted. To analyze the results, we have set up an annotation campaign, thanks to which we have found interesting aspects regarding the elimination of discourse segments as an alternative to sentence compression task. Results show that the degree of disagreement in determining the optimal compressed sentence is high and increases with the complexity of the sentence. However, there is some agreement on the decision to delete discourse segments. The informativeness of each segment is calculated using textual energy, a method that has shown good results in automatic summarization.

Web Exploitation for Definition Extraction

We present a system to extract definitions from a term using the Web. Definitions are organized according to a typology and its context. The structural and functional design is described; emphasizing its relevant components: the extractor of definitional context to candidates using the Yahoo!’s BOSS API; the extractor of definitional contexts and a clustering module based on textual energy as a measure of similarity.

A Turing Test to Evaluate a Complex Summarization Task

This paper deals with a new strategy to evaluate a Natural Language Processing NLP complex task using the Turing test. Automatic summarization based on sentence compression requires to asses informativeness and modify inner sentence structures. This is much more intrinsically related with real rephrasing than plain sentence extraction and ranking paradigm so new evaluation methods are needed. We propose a novel imitation game to evaluate Automatic Summarization by Compression ASC. Rationale of this Turing-like evaluation could be applied to many other NLP complex tasks like Machine translation or Text Generation. We show that a state of the art ASC system can pass such a test and simulate a human summary in 60% of the cases.

Analysis and Transformation of Textual Energy Distribution

In this paper we revisit the Textual Energy model. We deal with the two major disadvantages of the Textual Energy: the asymmetry of the distribution and the unbounded ness of the maximum value. Although this model has been successfully used in several NLP tasks like summarization, clustering and sentence compression, no correction of these problems has been proposed until now. Concerning the maximum value, we analyze the computation of Textual Energy matrix and we conclude that energy values are dominated by the lexical richness in quadratic growth of the vocabulary size. Using the Box-Cox transformation, we show empirical evidence that a log transformation could correct both problems.