Sciweavers

25 search results - page 4 / 5
» cicling 2008
Sort
View
CICLING
2008
Springer
13 years 7 months ago
Non-interactive OCR Post-correction for Giga-Scale Digitization Projects
This paper proposes a non-interactive system for reducing the level of OCR-induced typographical variation in large text collections, contemporary and historical. Text-Induced Corp...
Martin Reynaert
CICLING
2008
Springer
13 years 7 months ago
Deep Lexical Semantics
In the project we describe, we have taken a basic core of about 5000 synsets in WordNet that are the most frequently used, and we have categorized these into sixteen broad categori...
Jerry R. Hobbs
CICLING
2008
Springer
13 years 7 months ago
Analysis of Joint Inference Strategies for the Semantic Role Labeling of Spanish and Catalan
This paper analyzes two joint inference approaches for semantic role labeling: re-ranking of candidate semantic frames generated by one local model and combination of two distinct ...
Mihai Surdeanu, Roser Morante, Lluís M&agra...
CICLING
2008
Springer
13 years 7 months ago
A Probabilistic Model for Guessing Base Forms of New Words by Analogy
Language software applications encounter new words, e.g., acronyms, technical terminology, loan words, names or compounds of such words. Looking at English, one might assume that t...
Krister Lindén
CICLING
2008
Springer
13 years 7 months ago
Dynamic Translation Memory: Using Statistical Machine Translation to Improve Translation Memory Fuzzy Matches
Abstract. Professional translators of technical documents often use Translation Memory (TM) systems in order to capitalize on the repetitions frequently observed in these documents...
Ergun Biçici, Marc Dymetman