Search Results for author: Yerai Doval

Found 9 papers, 5 papers with code

Cross-Lingual Word Embeddings for Turkic Languages

1 code implementation LREC 2020 Elmurod Kuriyozov, Yerai Doval, Carlos Gómez-Rodríguez

Our experiments confirm that the obtained bilingual dictionaries outperform previously-available ones, and that word embeddings from a low-resource language can benefit from resource-rich closely-related languages when they are aligned together.

Cross-Lingual Word Embeddings Sentiment Analysis +1

Towards robust word embeddings for noisy texts

1 code implementation25 Nov 2019 Yerai Doval, Jesús Vilares, Carlos Gómez-Rodríguez

Research on word embeddings has mainly focused on improving their performance on standard corpora, disregarding the difficulties posed by noisy texts in the form of tweets and other types of non-standard writing from social media.

Word Embeddings

Meemi: A Simple Method for Post-processing and Integrating Cross-lingual Word Embeddings

1 code implementation16 Oct 2019 Yerai Doval, Jose Camacho-Collados, Luis Espinosa-Anke, Steven Schockaert

While monolingual word embeddings encode information about words in the context of a particular language, cross-lingual embeddings define a multilingual space where word embeddings from two or more languages are integrated together.

Cross-Lingual Natural Language Inference Cross-Lingual Word Embeddings +3

On the Robustness of Unsupervised and Semi-supervised Cross-lingual Word Embedding Learning

no code implementations LREC 2020 Yerai Doval, Jose Camacho-Collados, Luis Espinosa-Anke, Steven Schockaert

Cross-lingual word embeddings are vector representations of words in different languages where words with similar meaning are represented by similar vectors, regardless of the language.

Cross-Lingual Word Embeddings Word Embeddings

Comparing Neural- and N-Gram-Based Language Models for Word Segmentation

no code implementations3 Dec 2018 Yerai Doval, Carlos Gómez-Rodríguez

The resulting system analyzes the text input with no word boundaries one token at a time, which can be a character or a byte, and uses the information gathered by the language model to determine if a boundary must be placed in the current position or not.

Language Modelling

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