1 code implementation • EMNLP 2021 • Oscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, Eneko Agirre
In our experiments on TACRED we attain 63% F1 zero-shot, 69% with 16 examples per relation (17% points better than the best supervised system on the same conditions), and only 4 points short to the state-of-the-art (which uses 20 times more training data).
no code implementations • 9 Apr 2024 • Mikel Zubillaga, Oscar Sainz, Ainara Estarrona, Oier Lopez de Lacalle, Eneko Agirre
To perform the experiments we introduce EusIE, an event extraction dataset for Basque, which follows the Multilingual Event Extraction dataset (MEE).
1 code implementation • 1 Mar 2024 • Ander Salaberria, Gorka Azkune, Oier Lopez de Lacalle, Aitor Soroa, Eneko Agirre, Frank Keller
We hypothesize that this is because explicit spatial relations rarely appear in the image captions used to train these models.
1 code implementation • 27 Oct 2023 • Oscar Sainz, Jon Ander Campos, Iker García-Ferrero, Julen Etxaniz, Oier Lopez de Lacalle, Eneko Agirre
In this position paper, we argue that the classical evaluation on Natural Language Processing (NLP) tasks using annotated benchmarks is in trouble.
1 code implementation • 5 Oct 2023 • Oscar Sainz, Iker García-Ferrero, Rodrigo Agerri, Oier Lopez de Lacalle, German Rigau, Eneko Agirre
In this paper, we propose GoLLIE (Guideline-following Large Language Model for IE), a model able to improve zero-shot results on unseen IE tasks by virtue of being fine-tuned to comply with annotation guidelines.
Ranked #1 on Zero-shot Named Entity Recognition (NER) on HarveyNER (using extra training data)
1 code implementation • 2 Aug 2023 • Julen Etxaniz, Gorka Azkune, Aitor Soroa, Oier Lopez de Lacalle, Mikel Artetxe
In this work, we introduce a new approach called self-translate, which overcomes the need of an external translation system by leveraging the few-shot translation capabilities of multilingual language models.
Common Sense Reasoning Cross-Lingual Natural Language Inference +6
no code implementations • 7 Feb 2023 • Oscar Sainz, Oier Lopez de Lacalle, Eneko Agirre, German Rigau
Language Models are the core for almost any Natural Language Processing system nowadays.
1 code implementation • Findings (NAACL) 2022 • Oscar Sainz, Itziar Gonzalez-Dios, Oier Lopez de Lacalle, Bonan Min, Eneko Agirre
In this work we show that entailment is also effective in Event Argument Extraction (EAE), reducing the need of manual annotation to 50% and 20% in ACE and WikiEvents respectively, while achieving the same performance as with full training.
Ranked #1 on Event Argument Extraction on WikiEvents
2 code implementations • NAACL (ACL) 2022 • Oscar Sainz, Haoling Qiu, Oier Lopez de Lacalle, Eneko Agirre, Bonan Min
The current workflow for Information Extraction (IE) analysts involves the definition of the entities/relations of interest and a training corpus with annotated examples.
1 code implementation • 15 Sep 2021 • Ander Salaberria, Gorka Azkune, Oier Lopez de Lacalle, Aitor Soroa, Eneko Agirre
Our results on a visual question answering task which requires external knowledge (OK-VQA) show that our text-only model outperforms pretrained multimodal (image-text) models of comparable number of parameters.
1 code implementation • 8 Sep 2021 • Oscar Sainz, Oier Lopez de Lacalle, Gorka Labaka, Ander Barrena, Eneko Agirre
In our experiments on TACRED we attain 63% F1 zero-shot, 69% with 16 examples per relation (17% points better than the best supervised system on the same conditions), and only 4 points short to the state-of-the-art (which uses 20 times more training data).
Ranked #10 on Relation Extraction on TACRED
1 code implementation • 1 Feb 2021 • Aitzol Elu, Gorka Azkune, Oier Lopez de Lacalle, Ignacio Arganda-Carreras, Aitor Soroa, Eneko Agirre
Previous work did not use the caption text information, but a manually provided relation holding between the subject and the object.
no code implementations • LREC 2020 • Piroska Lendvai, S{\'a}ndor Dar{\'a}nyi, Christian Geng, Moniek Kuijpers, Oier Lopez de Lacalle, Jean-Christophe Mensonides, Simone Rebora, Uwe Reichel
To detect how and when readers are experiencing engagement with a literary work, we bring together empirical literary studies and language technology via focusing on the affective state of absorption.
no code implementations • LREC 2020 • Andrea Horbach, Itziar Aldabe, Marie Bexte, Oier Lopez de Lacalle, Montse Maritxalar
Automatic generation of reading comprehension questions is a topic receiving growing interest in the NLP community, but there is currently no consensus on evaluation metrics and many approaches focus on linguistic quality only while ignoring the pedagogic value and appropriateness of questions.
no code implementations • LREC 2020 • Oscar Sainz, Oier Lopez de Lacalle, Itziar Aldabe, Montse Maritxalar
In this paper we present a relation extraction system that given a text extracts pedagogically motivated relation types, as a previous step to obtaining a semantic representation of the text which will make possible to automatically generate questions for reading comprehension.
1 code implementation • 4 Apr 2020 • Oier Lopez de Lacalle, Ander Salaberria, Aitor Soroa, Gorka Azkune, Eneko Agirre
In the case of textual representations, inference tasks such as Textual Entailment and Semantic Textual Similarity have been often used to benchmark the quality of textual representations.
no code implementations • 11 Sep 2018 • Oier Lopez de Lacalle, Aitor Soroa, Eneko Agirre
In this paper we introduce vSTS, a new dataset for measuring textual similarity of sentences using multimodal information.
no code implementations • COLING 2016 • Haiqing Tang, Deyi Xiong, Oier Lopez de Lacalle, Eneko Agirre
Selecting appropriate translations for source words with multiple meanings still remains a challenge for statistical machine translation (SMT).
no code implementations • LREC 2016 • Steven Neale, Lu{\'\i}s Gomes, Eneko Agirre, Oier Lopez de Lacalle, Ant{\'o}nio Branco
Although it is commonly assumed that word sense disambiguation (WSD) should help to improve lexical choice and improve the quality of machine translation systems, how to successfully integrate word senses into such systems remains an unanswered question.
no code implementations • 13 Jul 2015 • Itziar Aldabe, Oier Lopez de Lacalle, Iñigo Lopez-Gazpio, Montse Maritxalar
This paper describes a hierarchical system that predicts one label at a time for automated student response analysis.
no code implementations • LREC 2012 • Eneko Agirre, Ander Barrena, Oier Lopez de Lacalle, Aitor Soroa, Fern, Samuel o, Mark Stevenson
Digitised Cultural Heritage (CH) items usually have short descriptions and lack rich contextual information.