COLING
2010
13 years 6 months ago
2010
Active learning has been applied to different NLP tasks, with the aim of limiting the amount of time and cost for human annotation. Most studies on active learning have only simul...
COLING
2010
13 years 6 months ago
2010
This paper considers the problem of document-level multi-way sentiment detection, proposing a hierarchical classifier algorithm that accounts for the inter-class similarity of tag...
COLING
2010
13 years 6 months ago
2010
We generalize the task of finding question paraphrases in a question repository to a novel formulation in which known questions are ranked based on their utility to a new, referen...
COLING
2010
13 years 6 months ago
2010
This paper addresses the problem of dynamic model parameter selection for loglinear model based statistical machine translation (SMT) systems. In this work, we propose a principle...
COLING
2010
13 years 6 months ago
2010
For sentiment analysis, lexicons play an important role in many related tasks. In this paper, aiming to build Chinese emotion lexicons for public use, we adopted a graph-based alg...
COLING
2010
13 years 6 months ago
2010
Text Understanding systems often commit to a single best interpretation of a sentence before analyzing subsequent text. This interpretation is chosen by resolving ambiguous altern...
COLING
2010
13 years 6 months ago
2010
Relations between entities in text have been widely researched in the natural language processing and informationextraction communities. The region connecting a pair of entities (...
COLING
2010
13 years 6 months ago
2010
Ambiguity of entity mentions and concept references is a challenge to mining text beyond surface-level keywords. We describe an effective method of disambiguating surface forms an...
COLING
2010
13 years 6 months ago
2010
Multi-word expressions constitute a significant portion of the lexicon of every natural language, and handling them correctly is mandatory for various NLP applications. Yet such e...
COLING
2010
13 years 6 months ago
2010
Supertagging is an important technique for deep syntactic analysis. A supertagger is usually trained independently of the parser using a sequence labeling method. This presents an...