COLING
2010
12 years 12 months ago
2010
In practical applications, decoding speed is very important. Modern structured learning technique adopts template based method to extract millions of features. Complicated templat...
COLING
2010
12 years 12 months ago
2010
During face-to-face conversation, people naturally integrate speech, gestures and higher level language interpretations to predict the right time to start talking or to give backc...
COLING
2010
12 years 12 months ago
2010
Although much work in NLP has focused on simply determining what a document means, we also must know whether or not to believe it. Fact-finding algorithms attempt to identify the ...
COLING
2010
12 years 12 months ago
2010
This paper1 presents an empirical approach to mining parallel corpora. Conventional approaches use a readily available collection of comparable, nonparallel corpora to extract par...
COLING
2010
12 years 12 months ago
2010
We evaluate two dependency parsers, MSTParser and MaltParser, with respect to their capacity to recover unbounded dependencies in English, a type of evaluation that has been appli...
COLING
2010
12 years 12 months ago
2010
Sense annotation and lexicon building are costly affairs demanding prudent investment of resources. Recent work on multilingual WSD has shown that it is possible to leverage the a...
COLING
2010
12 years 12 months ago
2010
This paper analyzes the contribution of semantic roles to TimeML event recognition and classification. For that purpose, an approach using conditional random fields with a variety...
COLING
2010
12 years 12 months ago
2010
Cross Document Coreference (CDC) is the task of constructing the coreference chain for mentions of a person across a set of documents. This work offers a holistic view of using do...
COLING
2010
12 years 12 months ago
2010
We propose semantic role features for a Tree-to-String transducer to model the reordering/deletion of source-side semantic roles. These semantic features, as well as the Tree-to-S...
COLING
2010
12 years 12 months ago
2010
We present a framework where auxiliary MT systems are used to provide lexical predictions to a main SMT system. In this work, predictions are obtained by means of pivoting via aux...