Institute of Information Science, Academia Sinica

Events

Print

Press Ctrl+P to print from browser

Statistical Language Modeling - Retrieval, Summarization and Beyond

:::

Statistical Language Modeling - Retrieval, Summarization and Beyond

  • LecturerDr. Kuan-Yu Chen (Institute of Information Science, Academia Sinica)
    Host: Tyng-Luh Liu
  • Time2016-05-20 (Fri.) 10:00 ~ 12:00
  • LocationAuditorium 106 at IIS new Building
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 the context of information retrieval, language modeling 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 talk will present a continuation of such a general line of research and introduces a principled framework which can unify the relationships among several widely-used query modeling formulations. While the bag-of-words assumption makes LM a clean and efficient method for sentence selecting, it is an oversimplification of the problem of extractive speech summarization. In view of such phenomena, the talk will introduce a novel recurrent neural network language modeling framework for the formulation of the sentence models. On top of the celebrated word embedding methods, the talk will present a novel method for learning the word representations, which not only inherits the advantages of classic word embedding methods but also offers a clearer and more rigorous interpretation of the learned word representations.