Search Results for author: I{\~n}aki Alegria

Found 15 papers, 0 papers with code

Verbal Multiword Expressions in Basque Corpora

no code implementations COLING 2018 Uxoa I{\~n}urrieta, Itziar Aduriz, Ainara Estarrona, Itziar Gonzalez-Dios, Antton Gurrutxaga, Ruben Urizar, I{\~n}aki Alegria

This paper presents a Basque corpus where Verbal Multiword Expressions (VMWEs) were annotated following universal guidelines.

Measuring language distance among historical varieties using perplexity. Application to European Portuguese.

no code implementations COLING 2018 Jose Ramom Pichel Campos, Pablo Gamallo, I{\~n}aki Alegria

In our approach, we used a perplexity-based measure to calculate language distance between all the historical periods of a specific language: European Portuguese.

Language Acquisition Language Identification

A Perplexity-Based Method for Similar Languages Discrimination

no code implementations WS 2017 Pablo Gamallo, Jose Ramom Pichel, I{\~n}aki Alegria

This article describes the system submitted by the Citius{\_}Ixa{\_}Imaxin team to the VarDial 2017 (DSL and GDI tasks).

Language Identification

Evaluating the Noisy Channel Model for the Normalization of Historical Texts: Basque, Spanish and Slovene

no code implementations LREC 2016 Izaskun Etxeberria, I{\~n}aki Alegria, Larraitz Uria, Mans Hulden

This paper presents a method for the normalization of historical texts using a combination of weighted finite-state transducers and language models.

Domain Adaptation in MT Using Titles in Wikipedia as a Parallel Corpus: Resources and Evaluation

no code implementations LREC 2016 Gorka Labaka, I{\~n}aki Alegria, Kepa Sarasola

This paper presents how an state-of-the-art SMT system is enriched by using an extra in-domain parallel corpora extracted from Wikipedia.

Domain Adaptation

Evaluating Translation Quality and CLIR Performance of Query Sessions

no code implementations LREC 2016 Xabier Saralegi, Eneko Agirre, I{\~n}aki Alegria

Translation quality improved in all three types (generalization, specification, and drifting), and CLIR improved for generalization and specification sessions, preserving the performance in drifting sessions.

Cross-Lingual Information Retrieval Translation

Measuring the compositionality of NV expressions in Basque by means of distributional similarity techniques

no code implementations LREC 2012 Antton Gurrutxaga, I{\~n}aki Alegria

Using our previous work with cooccurrence techniques as a baseline, the results point to improvements using the Indri index or Kullback-Leibler divergence, and a slight further improvement when used in combination with cooccurrence measures such as {\$}t{\$}-score, via rank-aggregation.

Cannot find the paper you are looking for? You can Submit a new open access paper.