A Formal Model for Information Selection in Multi-Sentence Text Extraction

A Formal Model for Information Selection in Multi-Sentence Text Extraction Elena Filatova Department of Computer Science Columbia University New York, NY 10027, USA filatova@cs.columbia.edu Vasileios Hatzivassiloglou Center for Computational Learning Systems Columbia University New York, NY 10027, USA vh@cs.columbia.edu Abstract Selecting important information while account- ing for repetitions is a hard task for both sum- marization and question answering. We pro- pose a formal model that represents a collec- tion of documents in a two-dimensional space of textual and conceptual units with an asso- ciated mapping between these two dimensions. This representation is then used to describe the task of selecting textual units for a summary or answer as a formal optimization task. We pro- vide approximation algorithms and empirically validate the performance of the proposed model when used with two very different sets of fea- tures, words and atomic events. 1 Introduction Many natural language processing tasks involve the collection and assembling of pieces of informa- tion from multiple sources, such as different doc- uments or different parts of a document. Text sum- marization clearly entails selecting the most salient information (whether generically or for a specific task) and putting it together in a coherent sum- mary. Question answering research has recently started examining the production of multi-sentence answers, where multiple pieces of information are included in the final output. When the answer or summary consists of mul- tiple separately extracted (or constructed) phrases, sentences, or paragraphs, additional factors influ- ence the selection process. Obviously, each of the selected text snippets should individually be impor- tant. However, when many of the competing pas- sages are included in the final output, the issue of information overlap between the parts of the output comes up, and a mechanism for addressing redun- dancy is needed. Current approaches in both sum- marization and long answer generation are primar- ily oriented towards making good decisions for each potential part of the output, rather than examining whether these parts overlap. Most current methods adopt a statistical framework, without full semantic analysis of the selected content passages; this makes the comparison of content across multiple selected text passages hard, and necessarily approximated by the textual similarity of those passages. Thus, most current summarization or long- answer question-answering systems employ two levels of analysis: a content level, where every tex- tual unit is scored according to the concepts or fea- tures it covers, and a textual level, when, before being added to the final output, the textual units deemed to be important are compared to each other and only those that are not too similar to other can- didates are included in the final answer or summary. This comparison can be performed purely on the ba- sis of text similarity, or on the basis of shared fea- tures that may be the same as the features used to select the candidate text units in the first place. In this paper, we propose a formal model for in- tegrating these two tasks, simultaneously perform- ing the selection of …

Content truncated to 500 words