Leveraging effective query modeling techniques for speech recognition and summarization
Journal
EMNLP 2014 - 2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Pages
1474-1480
Date Issued
2014
Author(s)
Abstract
Statistical language modeling (LM) that purports to quantify the acceptability of a given piece of text has long been an interesting yet challenging research area. In particular, language modeling for information retrieval (IR) has enjoyed remarkable empirical success; one emerging stream of the LM approach for IR is to employ the pseudo-relevance feedback process to enhance the representation of an input query so as to improve retrieval effectiveness. This paper presents a continuation of such a general line of research and the main contribution is threefold. First, we propose a principled framework which can unify the relationships among several widely-used query modeling formulations. Second, on top of the successfully developed framework, we propose an extended query modeling formulation by incorporating critical query- specific information cues to guide the model estimation. Third, we further adopt and formalize such a framework to the speech recognition and summarization tasks. A series of empirical experiments reveal the feasibility of such an LM framework and the performance merits of the deduced models on these two tasks. © 2014 Association for Computational Linguistics.
Other Subjects
Computational linguistics; Computer hardware description languages; Modeling languages; Natural language processing systems; Empirical experiments; Language model; Model estimation; Pseudo relevance feedback; Query model; Retrieval effectiveness; Specific information; Statistical language modeling; Speech recognition
Type
conference paper