Search Results for author: Ximena Gutierrez-Vasques

Found 7 papers, 1 papers with code

Interpretability for Morphological Inflection: from Character-level Predictions to Subword-level Rules

no code implementations EACL 2021 Tatyana Ruzsics, Olga Sozinova, Ximena Gutierrez-Vasques, Tanja Samardzic

We apply our methodology to analyze the model{'}s decisions on three typologically-different languages and find that a) our pattern extraction method applied to cross-attention weights uncovers variation in form of inflection morphemes, b) pattern extraction from self-attention shows triggers for such variation, c) both types of patterns are closely aligned with grammar inflection classes and class assignment criteria, for all three languages.

Morphological Inflection

From characters to words: the turning point of BPE merges

no code implementations EACL 2021 Ximena Gutierrez-Vasques, Christian Bentz, Olga Sozinova, Tanja Samardzic

The distributions of orthographic word types are very different across languages due to typological characteristics, different writing traditions and potentially other factors.

Tokenization

Comparing morphological complexity of Spanish, Otomi and Nahuatl

no code implementations WS 2018 Ximena Gutierrez-Vasques, Victor Mijangos

We use two small parallel corpora for comparing the morphological complexity of Spanish, Otomi and Nahuatl.

Axolotl: a Web Accessible Parallel Corpus for Spanish-Nahuatl

no code implementations LREC 2016 Ximena Gutierrez-Vasques, Gerardo Sierra, Isaac Hern Pompa, ez

This paper describes the project called Axolotl which comprises a Spanish-Nahuatl parallel corpus and its search interface.

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