We present a novel framework for answering complex questions that relies on question decomposition. Complex questions are decomposed by a procedure that operates on a Markov chain...
Sanda M. Harabagiu, V. Finley Lacatusu, Andrew Hic...
This paper addresses the problem of identifying likely topics of texts by their position in the text. It describes the automated training and evaluation of an Optimal Position Pol...
One of the key tasks for analyzing conversational data is segmenting it into coherent topic segments. However, most models of topic segmentation ignore the social aspect of conver...
Viet-An Nguyen, Jordan L. Boyd-Graber, Philip Resn...
Topic representation mismatch is a key problem in topic-oriented summarization for the specified topic is usually too short to understand/interpret. This paper proposes a novel ad...
Theme network is a semantic network of document specific themes. So far Natural Language Processing (NLP) research patronized much of topic based summarizer system, unable to captu...