Search For:

Displaying 1-5 out of 5 total
An Experimental Study of Graph Connectivity for Unsupervised Word Sense Disambiguation
Found in: IEEE Transactions on Pattern Analysis and Machine Intelligence
By Roberto Navigli, Mirella Lapata
Issue Date:April 2010
pp. 678-692
Word sense disambiguation (WSD), the task of identifying the intended meanings (senses) of words in context, has been a long-standing research objective for natural language processing. In this paper, we are concerned with graph-based algorithms for large-...
 
Natural Language Processing and the Web
Found in: IEEE Intelligent Systems
By Dragomir Radev, Mirella Lapata
Issue Date:September 2008
pp. 16-17
This special issue focuses on applications that innovatively use the Web and Web-scale document collections to create useful resources or applications that let end users navigate the Web more easily. This article is part of a special issue on Natural Langu...
   
An abstractive approach to sentence compression
Found in: ACM Transactions on Intelligent Systems and Technology (TIST)
By Mirella Lapata, Trevor Cohn
Issue Date:June 2013
pp. 1-35
In this article we generalize the sentence compression task. Rather than simply shorten a sentence by deleting words or constituents, as in previous work, we rewrite it using additional operations such as substitution, reordering, and insertion. We present...
     
Visualizing timelines: evolutionary summarization via iterative reinforcement between text and image streams
Found in: Proceedings of the 21st ACM international conference on Information and knowledge management (CIKM '12)
By Mirella Lapata, Pu-Jen Cheng, Rui Yan, Wayne Xin Zhao, Xiaojun Wan, Xiaoming Li
Issue Date:October 2012
pp. 275-284
We present a novel graph-based framework for timeline summarization, the task of creating different summaries for different timestamps but for the same topic. Our work extends timeline summarization to a multimodal setting and creates timelines that are bo...
     
Broad coverage paragraph segmentation across languages and domains
Found in: ACM Transactions on Speech and Language Processing (TSLP)
By Caroline Sporleder, Mirella Lapata
Issue Date:July 2006
pp. 1-35
This article considers the problem of automatic paragraph segmentation. The task is relevant for speech-to-text applications whose output transcipts do not usually contain punctuation or paragraph indentation and are naturally difficult to read and process...
     
 1