LREC
2008
2008
Building a Bilingual Representation of the Roget Thesaurus for French to English Machine Translation
13 years 7 months ago
This paper describes a solution to lexical transfer as a trade-off between a dictionary and an ontology. It shows its association to a translation tool based on morpho-syntactical...
LREC
2008
13 years 7 months ago
2008
Many of the beliefs that one uses to reason about everyday entities and events are neither strictly true or even logically consistent. Rather, people appear to rely on a large bod...
LREC
2008
13 years 7 months ago
2008
The number and sizes of parallel corpora keep growing, which makes it necessary to have automatic methods of processing them: combining, checking and improving corpora quality, et...
LREC
2008
13 years 7 months ago
2008
The paper describes a method of word phonosemantics estimation. We treat phonosemantics as a subconscious emotional perception of word sounding independent on the word meaning. Th...
LREC
2008
13 years 7 months ago
2008
We propose in this paper an automatic evaluation procedure based on a metric which could provide summary evaluation without human assistance. Our system includes two metrics, whic...
LREC
2008
13 years 7 months ago
2008
This paper deals with the relationship between weblog content and time. With the proposed temporal mutual information, we analyze the collocations in time dimension, and the inter...
LREC
2008
13 years 7 months ago
2008
LREC
2008
13 years 7 months ago
2008
The paper describes the treatment of some specific syntactic constructions in two treebanks of Latin according to a common set of annotation guidelines. Both projects work within ...
LREC
2008
13 years 7 months ago
2008
In the field of ontology mapping, multilingual ontology mapping is an issue that is not well explored. This paper proposes a framework for mapping of multilingual Description Logi...
LREC
2008
13 years 7 months ago
2008
This paper describes the creation of a state-of-the-art answer type detection system capable of recognizing more than 200 different expected answer types with greater than 85% pre...