Sciweavers

FINTAL
2006
13 years 8 months ago
A Computational Implementation of Internally Headed Relative Clause Constructions
The so-called Internally Headed Relative Clause (IHRC) construction found in the head-final languages Korean and Japanese has received little attention from computational perspecti...
Jong-Bok Kim, Peter Sells, Jaehyung Yang
FINTAL
2006
13 years 8 months ago
Analysis of EU Languages Through Text Compression
In this article, we are studying the differences between the European languages using statistical and unsupervised methods. The analysis is conducted in different levels of languag...
Kimmo Kettunen, Markus Sadeniemi, Tiina Lindh-Knuu...
FINTAL
2006
13 years 8 months ago
Improving Statistical Word Alignments with Morpho-syntactic Transformations
Abstract. This paper presents a wide range of statistical word alignment experiments incorporating morphosyntactic information. By means of parallel corpus transformations accordin...
Adrià de Gispert, Deepa Gupta, Maja Popovic...
FINTAL
2006
13 years 8 months ago
Regular Approximation of Link Grammar
We present a regular approximation of Link Grammar, a dependency-type formalism with context-free expressive power, as a first step toward a finite-state joint inference system. Th...
Filip Ginter, Sampo Pyysalo, Jorma Boberg, Tapio S...
FINTAL
2006
13 years 8 months ago
Morphological Lexicon Extraction from Raw Text Data
The tool extract enables the automatic extraction of lemma-paradigm pairs from raw text data. The tool uses search patterns that consist of regular expressions and propositional lo...
Markus Forsberg, Harald Hammarström, Aarne Ra...
FINTAL
2006
13 years 8 months ago
Language Independent Answer Prediction from the Web
This work presents a strategy that aims to extract and rank predicted answers from the web based on the eigenvalues of a specially designed matrix. This matrix models the strength ...
Alejandro Figueroa, Günter Neumann
FINTAL
2006
13 years 8 months ago
Evaluation of Alignment Methods for HTML Parallel Text
The Internet constitutes a potential huge store of parallel text that may be collected to be exploited by many applications such as multilingual information retrieval, machine tran...
Enrique Sánchez Villamil, Susana Santos-Ant...
FINTAL
2006
13 years 8 months ago
Ord i Dag: Mining Norwegian Daily Newswire
We present Ord i Dag, a new service that displays today's most important keywords. These are extracted fully automatically from Norwegian online newspapers. Describing the com...
Unni Cathrine Eiken, Anja Therese Liseth, Hans Fri...