Papers by Aitor Soroa
Does Corpus Quality Really Matter for Low-Resource Languages? (2022.emnlp-main)
Copied to clipboard
| Challenge: | Existing work on multilingual pre-training has relied on automatically filtered versions of CommonCrawl. |
| Approach: | They propose to use tailored crawling to identify and scrape websites with high-quality content to improve representation learning in Basque. |
| Outcome: | The proposed corpus, called EusCrawl, has a much higher quality according to native annotators than the Basque portion of popular multilingual corpora like CC100 and mC4. |
Analyzing the Limitations of Cross-lingual Word Embedding Mappings (P19-1)
Copied to clipboard
| Challenge: | Existing methods for cross-lingual word embeddings have limited results . existing methods require little or no cross-linguistic signal to work . |
| Approach: | They compare offline mapping methods to an extension of skip-gram that jointly learns both embedding spaces. |
| Outcome: | The proposed method yields more isomorphic embeddings, is less sensitive to hubness, and achieves stronger results in bilingual lexicon induction. |
Principled Paraphrase Generation with Parallel Corpora (2022.acl-long)
Copied to clipboard
| Challenge: | a popular method for paraphrase generation is round-trip machine translation (MT). |
| Approach: | They propose a method that formalizes the implicit similarity function and relaxes it by requiring the entire translation distribution to match . they propose MT can be used to generate paraphrases by decoding back to the source without having to generate pivot translations. |
| Outcome: | The proposed approach is more principled and efficient than round-trip machine translation (MT) and offers an adjustable parameter to control the fidelity-diversity trade-off. |
Machine Translation for Low-Resource Languages through Monolingual Data and LLM: A Case Study of English-to-Basque (2026.eacl-srw)
Copied to clipboard
| Challenge: | Existing LLMs do not translate well from English to Basque, but they yield an acceptable performance in the reverse direction. |
| Approach: | They propose to use a Basque monolingual corpora to train an LLM-based MT system . they use 'sovereignty fine tuning' to generate parallel corporata, and then use preference optimization . |
| Outcome: | The proposed system improves translation quality in English-to-Basque direction while requiring limited data for low-resource languages. |
Do Multilingual Language Models Think Better in English? (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing studies show that translation-test improves performance of multilingual models by translating the input into English using an external machine translation system. |
| Approach: | They propose a new approach that leverages the few-shot translation capabilities of multilingual language models. |
| Outcome: | The proposed approach outperforms direct inference on 5 tasks. |
Conversational Question Answering in Low Resource Scenarios: A Dataset and Case Study for Basque (2020.lrec-1)
Copied to clipboard
| Challenge: | Existing datasets for conversational question answering systems are expensive and limited in resources . a dataset of thousands of dialogues and tens of thousands question answering turns is available for free . |
| Approach: | They aim to test the performance of Conversational Question Answering systems in non-English languages . they use a dataset built on top of Wikipedia sections about popular people and organizations . |
| Outcome: | The results show that the system can handle low-resource conditions comparable to English . the results also show that dialogue history models are not directly transferable to another language . |
Spot The Bot: A Robust and Efficient Framework for the Evaluation of Conversational Dialogue Systems (2020.emnlp-main)
Copied to clipboard
Jan Deriu, Don Tuggener, Pius von Däniken, Jon Ander Campos, Alvaro Rodrigo, Thiziri Belkacem, Aitor Soroa, Eneko Agirre, Mark Cieliebak
| Challenge: | Lack of time efficient and reliable evalu-ation methods is hampering the development of conversational dialogue systems (chatbots). |
| Approach: | They propose a framework that replaces human-bot conversations with conversations between bots and an annotation tool that ranks chatbots based on their ability to mimic human behaviour. |
| Outcome: | The proposed evaluation framework replaces human-bot conversations with bot conversations and allows for frequent evaluations of chatbots during their evaluation cycle. |
Scaling Laws for BERT in Low-Resource Settings (2023.findings-acl)
Copied to clipboard
| Challenge: | Large language models require huge training corpora, which is unobtainable for most NLP practitioners. |
| Approach: | They propose power-law formulas that relate model size, corpora size and computation power to find the optimal settings in advance given a fixed budget. |
| Outcome: | The proposed models perform better on MLM and NLU tasks on four languages of different linguistic characteristics. |
BasqueGLUE: A Natural Language Understanding Benchmark for Basque (2022.lrec-1)
Copied to clipboard
| Challenge: | Natural Language Understanding (NLU) benchmarks are costly to develop and language-dependent . basqueGLUE is the first benchmark for Basque, a less-resourced language . |
| Approach: | They propose a benchmark for Basque, a less-resourced language, using existing datasets. |
| Outcome: | The proposed benchmarks take into account a wide and diverse set of NLU tasks that require some form of language understanding beyond the detection of superficial clues. |
PoeLM: A Meter- and Rhyme-Controllable Language Model for Unsupervised Poetry Generation (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for generating formal verse poetry use existing poems for supervision, which are difficult to obtain for most languages and poetic forms. |
| Approach: | They propose an unsupervised approach to generate formal verse poetry without supervision . they use control codes to describe meter and rhyme scheme constraints, and train a transformer language model . |
| Outcome: | The proposed method generates poems that follow any given meter and rhyme scheme without training . it is comparable to those written by humans and generates comparable quality poems . |
DoQA - Accessing Domain-Specific FAQs via Conversational QA (2020.acl-main)
Copied to clipboard
| Challenge: | a dataset of 2,437 dialogues and 10,917 QA pairs is used to access domain-specific FAQ information. |
| Approach: | They present a dataset with 2,437 dialogues and 10,917 QA pairs for FAQs . they use the Wizard of Oz method with crowdsourcing to create dialogues using the original post and the original reply. |
| Outcome: | The proposed system can access domain-specific FAQ information without training data. |
Give your Text Representation Models some Love: the Case for Basque (2020.lrec-1)
Copied to clipboard
Rodrigo Agerri, Iñaki San Vicente, Jon Ander Campos, Ander Barrena, Xabier Saralegi, Aitor Soroa, Eneko Agirre
| Challenge: | Word embeddings and pre-trained language models are expensive to train and are often used by small companies and research groups to build their own. |
| Approach: | They propose to use word embeddings and pre-trained language models to build rich representations of text and improve NLP tasks. |
| Outcome: | The proposed models perform better than publicly available versions in downstream NLP tasks for Basque. |
A LLM-based Ranking Method for the Evaluation of Automatic Counter-Narrative Generation (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Existing methods for evaluating CNs are expensive, time-consuming, and subjective, but lack a universal truth and the lack of a 'universal truth' . |
| Approach: | They propose a model ranking pipeline based on pairwise comparisons of generated CNs from different models organized in a tournament-style format to improve the evaluation process. |
| Outcome: | The proposed method achieves a high correlation with human preference, with a score of 0.88, and compares chat, instruct, and base models, exploring their strengths and limitations. |
Beyond Offline Mapping: Learning Cross-lingual Word Embeddings through Context Anchoring (2021.acl-long)
Copied to clipboard
| Challenge: | Recent research on cross-lingual word embeddings has been dominated by unsupervised mapping approaches that align monolingual embedders. |
| Approach: | They propose an unsupervised mapping approach that fixes fixed embeddings and learns new ones for the source language that are aligned with them. |
| Outcome: | The proposed method outperforms conventional mapping methods on bilingual lexicon induction and obtains competitive results in the downstream XNLI task. |
XNLIeu: a dataset for cross-lingual NLI in Basque (2024.naacl-long)
Copied to clipboard
| Challenge: | XNLI is a popular benchmark used to evaluate cross-lingual Natural Language Understanding (NLU) in languages such as English, Basque and other low-resource languages. |
| Approach: | They expand XNLI to include Basque, a low-resource language that can benefit from transfer-learning approaches. |
| Outcome: | The proposed dataset includes Basque, a low-resource language that can benefit from transfer-learning approaches. |
Improving Conversational Question Answering Systems after Deployment using Feedback-Weighted Learning (2020.coling-main)
Copied to clipboard
| Challenge: | In most applications, users are not able to provide the correct answer to the system, but they are able provide binary (correct, incorrect) feedback. |
| Approach: | They propose feedback-weighted learning based on importance sampling to improve upon an initial supervised system using binary user feedback. |
| Outcome: | The proposed method improves on an initial supervised system, getting close to a fully-supervised system that has access to the same labeled examples in in-domain experiments (QuAC) and matching in out-of-domain experiment (DoQA). |
Instructing Large Language Models for Low-Resource Languages: A Systematic Study for Basque (2025.emnlp-main)
Copied to clipboard
Oscar Sainz, Naiara Perez, Julen Etxaniz, Joseba Fernandez de Landa, Itziar Aldabe, Iker García-Ferrero, Aimar Zabala, Ekhi Azurmendi, German Rigau, Eneko Agirre, Mikel Artetxe, Aitor Soroa
| Challenge: | Instructing language models with user intent requires large instruction datasets limited to a limited set of languages. |
| Approach: | They propose to use existing LLMs and synthetically generated instructions to train models with user intent. |
| Outcome: | The proposed model outperforms base non-instructed models on Basque without Basque instructions. |