Sciweavers

TAL
2010
Springer
12 years 11 months ago
Transliteration as Alignment vs. Transliteration as Generation for Crosslingual Information Retrieval
Crosslingual Information Retrieval (CLIR) usually requires query translation and, due to named entities in the case of IR, query translation requires a good transliteration system ...
Anil Kumar Singh, Sethuramalingam Subramaniam, Tar...
TAL
2010
Springer
12 years 11 months ago
A Formal Ontology for a Computational Approach of Time and Aspect
This paper provides a linguistic semantic analysis of time and aspect in natural languages. On the basis of topological concepts, notions are introduced like the basic aspectual op...
Aurelien Arena, Jean-Pierre Desclés
TAL
2010
Springer
13 years 2 months ago
Semi-automatic Endogenous Enrichment of Collaboratively Constructed Lexical Resources: Piggybacking onto Wiktionary
The lack of large-scale, freely available and durable lexical resources, and the consequences for NLP, is widely acknowledged but the attempts to cope with usual bottlenecks preven...
Franck Sajous, Emmanuel Navarro, Bruno Gaume, Laur...
TAL
2010
Springer
13 years 2 months ago
The Effect of Semi-supervised Learning on Parsing Long Distance Dependencies in German and Swedish
This paper shows how the best data-driven dependency parsers available today [1] can be improved by learning from unlabeled data. We focus on German and Swedish and show that label...
Anders Søgaard, Christian Rishøj
TAL
2010
Springer
13 years 2 months ago
Passage Retrieval in Log Files: An Approach Based on Query Enrichment
Abstract. The question answering systems are considered the next generation of search engines. This paper focuses on the first step of this process, which is to search for relevant...
Hassan Saneifar, Stéphane Bonniol, Anne Lau...
TAL
2010
Springer
13 years 2 months ago
Summarization as Feature Selection for Document Categorization on Small Datasets
Abstract. Most common feature selection techniques for document categorization are supervised and require lots of training data in order to accurately capture the descriptive and d...
Emmanuel Anguiano-Hernández, Luis Villase&n...
TAL
2010
Springer
13 years 2 months ago
Automated Email Answering by Text Pattern Matching
Answering email by standard answers is a common practice at contact centers. Our research assists this process by creating reply messages that contain one or several standard answe...
Eriks Sneiders
TAL
2010
Springer
13 years 2 months ago
Robust Semi-supervised and Ensemble-Based Methods in Word Sense Disambiguation
Mihalcea [1] discusses self-training and co-training in the context of word sense disambiguation and shows that parameter optimization on individual words was important to obtain g...
Anders Søgaard, Anders Johannsen
TAL
2010
Springer
13 years 2 months ago
Clustering E-Mails for the Swedish Social Insurance Agency - What Part of the E-Mail Thread Gives the Best Quality?
We need to analyse a large number of e-mails sent by the citizens to the customer services department of a governmental organisation based in Sweden. To carry out this analysis we ...
Hercules Dalianis, Magnus Rosell, Eriks Sneiders
TAL
2010
Springer
13 years 2 months ago
Automatic Learning of Discourse Relations in Swedish Using Cue Phrases
Abstract. This paper describes experiments to extract discourse relations holding between two text spans in Swedish. We considered three relation types: cause-explanation-evidence ...
Stefan Karlsson, Pierre Nugues