PhD Thesis – Ixa Group. Language Technology.

PhD Thesis: Corpus based metrics for measuring distances between languages (José Ramom Pichel, 2020-10-29)

Kepa Sarasola — Tue, 27 Oct 2020 18:42:20 +0000

Title: Medidas de distância entre línguas baseadas em corpus. Aplicação à linguística histórica do galego, poruguês, espanhol e inglês
/ Corpus based metrics for measuring distances between languages. Application to historical linguistics of Galician, Portuguese, Spanish and English.

Where: Teleconference,
……….https://eu.bbcollab.com/guest/5b757d040d024f7b91deaaaffe3bec03
……….Faculty of informatics (UPV/EHU) Ada Lovelace room
Date: October 29, 2020, Thursday, 18:30
Author: José Ramom Pichel
Supervisors: Iñaki Alegria & Pablo Gamallo
Languages: Portuguese, mainly

Abstract:

As dúvidas sobre a classificação filogenética histórica e actual do galego e as hesitações na identificação au-
tomática da língua e na construção e concepção de tradutores automáticos, sugerem que o cálculo automático da distância entre o galego, o português e o espanhol, a partir de textos escritos reais, e um desafio interessante.

1. Pode a distância entre línguas ser medida automaticamente com base em corpus?
2. Que papel desempenha a ortografia na distância entre as línguas?
3. É possível traduzir esta distância numa única métrica robusta?
4. A distância calculada com essa métrica verifica as hipóteses dos linguistas?
Adiciona novos dados sobre hipóteses minoritárias ou controversas?
5. Será que a distância entre períodos históricos da mesma língua muda? Como?
6. A distância entre línguas muda historicamente ou é sempre a mesma?
E se mudar, esta distância entre línguas é linear?
7. Será que a distância histórica entre variantes reconhecidas da mesma língua muda?

Related publications to his PhD work:

Jose R. Pichel, Pablo Gamallo, Iñaki Alegria, Marco Neves (2020) A Methodology to Measure the Diachronic Language Distance between Three Languages Based on PerplexityJournal of Quantitative Linguistics.
José Ramom Pichel, Pablo Gamallo, Marco Neves & Iñaki Alegria (2020) Distância diacrónica automática entre variantes diatópicas do português e do espanhol Linguamática, Vol. 12 N. 1, 117–126 ISSN: 1647–0818
José Ramom Pichel, Pablo Gamallo, Iñaki Alegria (2019) Measuring diachronic language distance using perplexity. Application to English, Portuguese and Spanish. Natural Language Engeenering.
Pablo Gamallo José Ramom Pichel and Iñaki Alegria (2020) Measuring Language Distance of Isolated European Languages MDPI Information 2020, 11(4), 181 doi:10.3390/info11040181
José Ramom Pichel, Pablo Gamallo, Iñaki Alegria (2019) Cross-lingual Diachronic Distance: Application to Portuguese and Spanish Procesamiento del Lenguaje Natural, Revista no 63, septiembre de 2019, pp. 77-84
P. Gamallo, J.R. Pichel, I. Alegria. 2017. From language identification to language distance. Physica A: Statistical Mechanics and Its Applications 484, 152-162.

HAP/LAP Master Theses (2020-09-21 and 22)

Kepa Sarasola — Wed, 16 Sep 2020 09:14:06 +0000

The following master theses will be presented next week.
Date: September 21 and 22
Place: Ada Lovelace room

Day/ Time	Student	Supervisor	Title
Sep. 21 15:00	Garcia Montero, Eneritz	Arantza del Pozo-Echezarreta Itziar Gonzalez-Dios	Coping with Data Scarcity: First Steps towards Word Expansion for a Chatbot in the Urban transportation Domain
Sep 21 15:45	Lima Lopez, Salvador	Montse Cuadros Olatz Pérez de Viñaspre	Towards Orthographic and Grammatical Clinical Text Correction: a First Approach
Sep 21 16:30	Toporkov, Olia	Rodrigo Agerri	Studying the Role of Morphological Information for Contextual Lemmatization in Highly Inflected Languages

Sep 22 15:00	Susperregi Indakoetxea, Mari	Olatz Pérez de Viñaspre Ander Barrena	Muturretik muturrerako informazio erauzketa eleaniztuna eta hizkuntzen arteko terminoen lerrokatze neuronala
Sep. 22 15:45	Ortuondo Reyero, Aitor	German Rigau	Domain Disambiguation using Contextual Word Embeddings
Sep 22 16:30	Xu, Xiao	Martijn Wieling German Rigau	Multilingual Classification for Legal Prediction
Sep 22 17:15	Martinez Alvarez, Cristina	Aitor Soroa Rodrigo Agerri	BarceloQA: Building a Dataset for the Tourism Domain

PhD Thesis: Unsupervised Machine Translation (Mikel Artetxe, 2020/07/29)

Kepa Sarasola — Tue, 28 Jul 2020 13:37:29 +0000

Title: Unsupervised Machine Translation
/ Itzulpen automatiko gainbegiratu gabea

Non: Teleconference: https://eu.bbcollab.com/guest/b22b606d9ae74bc5b3e067821c897617
Faculty of informatics (UPV/EHU) Ada Lovelace room
Date: July 29, 2020, Wednesday, 11:00
Author: Mikel Artetxe Zurutuza
Supervisors: Eneko Agirre & Gorka Labaka
Languages: Basque (motivation, state of the art) and English (second half, papers, conclusions, ~11:30…)

https://github.com/artetxem

Abstract:

The advent of neural sequence-to-sequence models has led to impressive progress in machine translation, with large improvements in standard benchmarks and the first solid claims of human parity in certain settings. Nevertheless, existing systems require strong supervision in the form of parallel corpora, typically consisting of several million sentence pairs. Such a requirement greatly departs from the way in which humans acquire language, and poses a major practical problem for the vast majority of low-resource
language pairs.

The goal of this thesis is to remove the dependency on parallel data altogether, relying on nothing but monolingual corpora to train unsupervised machine translation systems. For that purpose, our approach first aligns separately trained word representations in
different languages based on their structural similarity, and uses them to initialize either a neural or a statistical machine translation system, which is further trained through back-translation.

Mikel Artetxe publications related to his PhD work:

Mikel Artetxe, Sebastian Ruder, Dani Yogatama, Gorka Labaka, Eneko Agirre (2020)
A Call for More Rigor in Unsupervised Cross-lingual Learning
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2019)
Bilingual Lexicon Induction through Unsupervised Machine Translation

Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5002-5007.
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2019)
An Effective Approach to Unsupervised Machine Translation
Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 194-203.
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2018)
Unsupervised Statistical Machine Translation
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3632–3642, Brussels, Belgium, October-November. Association for Computational Linguistics.
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2018)
A robust self-learning method for fully unsupervised cross-lingual mappings of word embeddings
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics
Mikel Artetxe, Gorka Labaka, Eneko Agirre, Kyunghyun Cho (2018)
Unsupervised Neural Machine Translation
Sixth International Conference on Learning Representations (ICLR 2018)
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2018)
Generalizing and Improving Bilingual Word Embedding Mappings with a Multi-Step Framework of Linear Transformations

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) pages 5012-5019.
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2017)
Learning bilingual word embeddings with (almost) no bilingual data
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics
Mikel Artetxe, Gorka Labaka, Eneko Agirre (2016)
Learning principled bilingual mappings of word embeddings while preserving monolingual invariance
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2289–2294. Austin, Texas. ISBN: 978-1-945626-25-8

Mitxelena Award for PhD theses 2018 to Olatz Perez-de-Viñaspre: Automatic medical term generation

Kepa Sarasola — Fri, 24 May 2019 12:04:04 +0000

Our colleague Olatz Perez de Viñaspre won last week the VI. Koldo MItxelena Award for PhD Theses organized by Euskaltzaindia (the Academy of Basque Language) and the University of the Basque Country.
CONGRATULATIONS Olatz!

This thesis faced the creation of computational tools to promote the use of Basque in helath services.

The winners of Mitxelena Awards 2018

Title: Automatic medical term generation fora low-resource language: translation of SNOMED CT into Basque (pdf)
Supervisors: Arantza Diaz de Ilarraza and Maite Oronoz
Publications in English:

Design of EuSnomed:
- Perez-de-Viñaspre O., and Oronoz M.Translating SNOMEDCT Terminology into a Minor Language.Proceedings ofthe 5th International Workshop on Health Text Mining and Infor-mation Analysis (Louhi), 38–45. Association for ComputationalLinguistics. Gothenburg, Sweden, 2014.
- Perez-de-Viñaspre O., and Oronoz M.An XML Based TBXFramework to Represent Multilingual SNOMED CT forTranslation.12th Mexican International Conference on Artifi-cial Intelligence, MICAI 2013. Lecture Notes in Artificial Intel-ligence, vol. 8265, 419–429. Springer, ISBN 978-3-642-45113-3.Mexico DF, Mexico. 2013
Sinple terms: lexical resources and neoclassical terms:
- Perez-de-Viñaspre O., Oronoz M., Agirrezabal M., and LersundiM.A finite state approach to translate SNOMED CTterms into Basque using medical prefixes and suffixes.Proceedings of the 11th International Conference on Finite StateMethods and Natural Language Processing, 99–103. St Andrews,Scotland, 2013.7
- Perez-de-Viñaspre O., and Oronoz M.SNOMED CT in a lan-guage isolate: an algorithm for a semiautomatic transla-tion.BMC medical informatics and decision making, volume 15,number 2, S5. BioMed Central. 2015.
Complex terms: nested terms and automatic translator:
- Perez-de-Viñaspre O., and Oronoz M.Osasun-zientzietako ter-minologiaren euskaratze automatikoaren ebaluazioa, os-asungintzako euskal komunitatea inplikatuz.II. IkerGazte,Nazioarteko Ikerketa Euskaraz. Udako Euskal Unibertsitatea. IruÃśea,Basque Country, 2017.
Other papers:
- Perez-de-Viñaspre O., Oronoz M., and Patrick J.Osasun-txostenelebidunak posible ote?I. IkerGazte, Nazioarteko Ikerketa Eu-skaraz, 730–738. Udako Euskal Unibertsitatea, ISBN 978-84-8438-539-4. Durango, Basque Country, 2015. IkerGazte Special Award.
- Perez-de-Viñaspre O., and Labaka G.IXA Biomedical TranslationSystem at WMT16 Biomedical Translation Task.Proceedingsof the First Conference on Machine Translation (WMT16), 477–482.Association for Computational Linguistics. Berlin, Germany, 2016

PhD Thesis: Computational Model for Semantic Textual Similarity (I. San Vicente, 2019/03/11)

Kepa Sarasola — Tue, 12 Mar 2019 19:41:56 +0000

Title: Multilingual Sentiment Analysis in Social Media
Author: Iñaki San Vicente
Supervisors: German Rigau / Rodrigo Agerri (Ixa Group)
Date: Mars 11, 2019, Monday

Abstract:

The main goal of this thesis was to research on Multilingual Sentiment Analysis in order to develop a social media monitor on specific topics. The most relevant contributions are listed below:

Improvement of the state of the art for Spanish polarity classification, and obtained the first position in the TASS shared task twice
Contribution to the state of the art in aspect based SA for English, and notable results on the Semeval 2015 aspect based SA shared task
Pioneering work for Basque in the SA field, specifically:
- Creating the first sentiment lexicons for Basque
- The first polarity annotated datasets for Basque.
- First resources for Basque microtext normalization.
EliXa, The first multilingual SA system including Basque.
Talaia, a real social media monitoring platform applying all the previous research.
A set of robust and open domain tools and resources that are freely available.

2 master-theses today (2019-02-25, 16:00)

Kepa Sarasola — Mon, 25 Feb 2019 08:55:46 +0000

Date: February 25th
Place: Ada Lovelace room

16:00
Izenburua / Title: Clinical report multi-label classification using the international classification of diseases (ICD-10)
Egilea / Author: Jorge Pérez
Tutoreak / Supervisors: Alicia Pérez & Arantza Casillas

16:45
Izenburua / Title: Building a dialogue system for question-answer forum websites (defence in Basque)
Egilea / Author: Jon Ander Campos
Tutoreak / Supervisors: Eneko Agirre & Arantxa Otegi

“Language Analysis and Processing” master theses (2018-06-26)

Kepa Sarasola — Tue, 17 Jul 2018 09:07:30 +0000

Four master theses have been presented in June:

15:00
Noisy Speech Recognition using Kaldi and Neural Architectures
Ikaslea/Student: Ander González Docasal
Zuzendariak/Supervisors: Vassilis Tsiaras, George P. Kafentzis, Yannis Stylianou

15:45
Unsupervised Methods to Predict Example Difficulty in Word Sense Annotation
Ikaslea/Student: Cristina Aceta Moreno
Zuzendariak/Supervisors: Oier Lopez de Lacalle, Eneko Agirre, Izaskun Aldezabal

16:30
To post‐edit or to translate… That is the question.
A case study of a recommender system for Quality Estimation of Machine Translation based on linguistic feature
Ikaslea/Student: Ona de Gilbert Bonet
Zuzendaria/Supervisor: Nora Aranberri

17:15
Basque‐to‐Spanish and Spanish‐to‐Basque Machine Translation for the health domain
Ikaslea/Student: Xabier Soto García
Zuzendariak/Supervisors: Gorka Labaka, Olatz Perez de Viñaspre
Zuzendarikidea/Co‐advisor: Maite Oronoz

HAP/LAP master theses (2017-09-26)

Kepa Sarasola — Tue, 26 Sep 2017 11:47:08 +0000

Master HAP/LAP — EMLCT master
Master thesis defences

15:00etan

Izenburua / Title: Automatic Generation of Named Entity Taggers Leveraging Parallel Corpora
Egilea / Author: Yi-Ling Chung (EMLCT)
Tutoreak / Supervirors: Rodrigo Agerri and German Rigau

15:45ean

Izenburua / Title: Dialect normalisation with deep learning-based automatic speech recognition
Egilea / Author: Mahsa Vafaie (EMLCT)
Tutoreak / Supervirors: Inma Hernaez, Josef Van Genabith

16:30etan

Izenburua / Title: Mapping of Electronic Health Records in Spanish to the Unified Medical Language System Metathesaurus
Egilea / Author: Naiara Perez (HAP/LAP)
Tutoreak / Supervirors: Montse Cuadros and German Riga

PhD Thesis: Computational Model for Semantic Textual Similarity (A. Gonzalez, 2017/07/07)

Kepa Sarasola — Thu, 06 Jul 2017 17:43:30 +0000

Title: Computational Model for Semantic Textual Similarity
Author: Aitor Gonzalez-Agirre
Supervisors: German Rigau i Claramunt / Eneko Agirre Bengoa (Ixa Group)
Date: July 7, 2017, Friday
Time: 11:00
Where: Faculty of Informatics, Ada Lovelace Room (UPV/EHU)

Abstract:

The goal is to advance on computational models of meaning and their evaluation. We define two tasks: Semantic Textual Similarity (STS) and Typed Similarity.

STS aims to measure the degree of semantic equivalence between two sentences. We have collected pairs of sentences to construct datasets for STS, a total of 15,436 pairs of sentences, being by far the largest collection of data for STS. We have designed, constructed and evaluated a new approach to combine knowledge-based and corpus-based methods using a cube.

Typed Similarity tries to identify the type of relation that holds between a pair of similar items in a digital library. Providing a reason why items are similar has applications in recommendation, personalization, and search. A range of types of similarity in this collection were identified and a set of 1,500 pairs of items from the collection were annotated using crowdsourcing.

We present systems that resolve the Typed Similarity task.

HAP/LAP master thesis (Noelia Migueles, 2017-06-27)

Kepa Sarasola — Tue, 27 Jun 2017 11:47:24 +0000

Today afternoon, June the 27th, Noelia Migueles will defend her master thesis.

Date: june 27th, 15:00
Place: Ada Lovelace room

Izenburua / Title: A Study Towards Spanish Abstract Meaning Representation

Egilea / Author: Noelia Migueles-Abraira

Tutoreak / Supervirors: Arantza Diaz de Ilarraza and Rodri Agerri