Aitor Soroa

Bio: Aitor Soroa is an academic researcher from University of the Basque Country. The author has contributed to research in topics: WordNet & Computer science. The author has an hindex of 24, co-authored 96 publications receiving 3551 citations. Previous affiliations of Aitor Soroa include National University of Distance Education & Polytechnic University of Catalonia.

A Study on Similarity and Relatedness Using Distributional and WordNet-based Approaches

Abstract: This paper presents and compares WordNet-based and distributional similarity approaches. The strengths and weaknesses of each approach regarding similarity and relatedness tasks are discussed, and a combination is presented. Each of our methods independently provide the best results in their class on the RG and WordSim353 datasets, and a supervised combination of them yields the best published results on all datasets. Finally, we pioneer cross-lingual similarity, showing that our methods are easily adapted for a cross-lingual task with minor losses.

Personalizing PageRank for Word Sense Disambiguation

Abstract: In this paper we propose a new graph-based method that uses the knowledge in a LKB (based on WordNet) in order to perform unsupervised Word Sense Disambiguation. Our algorithm uses the full graph of the LKB efficiently, performing better than previous approaches in English all-words datasets. We also show that the algorithm can be easily ported to other languages with good results, with the only requirement of having a wordnet. In addition, we make an analysis of the performance of the algorithm, showing that it is efficient and that it could be tuned to be faster.

BLOOM: A 176B-Parameter Open-Access Multilingual Language Model

Abstract: Large language models (LLMs) have been shown to be able to perform new tasks based on a few demonstrations or natural language instructions. While these capabilities have led to widespread adoption, most LLMs are developed by resource-rich organizations and are frequently kept from the public. As a step towards democratizing this powerful technology, we present BLOOM, a 176B-parameter open-access language model designed and built thanks to a collaboration of hundreds of researchers. BLOOM is a decoder-only Transformer language model that was trained on the ROOTS corpus, a dataset comprising hundreds of sources in 46 natural and 13 programming languages (59 in total). We find that BLOOM achieves competitive performance on a wide variety of benchmarks, with stronger results after undergoing multitask prompted finetuning. To facilitate future research and applications using LLMs, we publicly release our models and code under the Responsible AI License.

Random walks for knowledge-based word sense disambiguation

Abstract: Word Sense Disambiguation WSD systems automatically choose the intended meaning of a word in context. In this article we present a WSD algorithm based on random walks over large Lexical Knowledge Bases LKB. We show that our algorithm performs better than other graph-based methods when run on a graph built from WordNet and eXtended WordNet. Our algorithm and LKB combination compares favorably to other knowledge-based approaches in the literature that use similar knowledge on a variety of English data sets and a data set on Spanish. We include a detailed analysis of the factors that affect the algorithm. The algorithm and the LKBs used are publicly available, and the results easily reproducible.

SemEval-2007 Task 02: Evaluating Word Sense Induction and Discrimination Systems

Abstract: The goal of this task is to allow for comparison across sense-induction and discrimination systems, and also to compare these systems to other supervised and knowledge-based systems. In total there were 6 participating systems. We reused the SemEval-2007 English lexical sample subtask of task 17, and set up both clustering-style unsupervised evaluation (using OntoNotes senses as gold-standard) and a supervised evaluation (using the part of the dataset for mapping). We provide a comparison to the results of the systems participating in the lexical sample subtask of task 17.

Word sense disambiguation: A survey

Abstract: Word sense disambiguation (WSD) is the ability to identify the meaning of words in context in a computational manner. WSD is considered an AI-complete problem, that is, a task whose solution is at least as hard as the most difficult problems in artificial intelligence. We introduce the reader to the motivations for solving the ambiguity of words and provide a description of the task. We overview supervised, unsupervised, and knowledge-based approaches. The assessment of WSD systems is discussed in the context of the Senseval/Semeval campaigns, aiming at the objective evaluation of systems participating in several different disambiguation tasks. Finally, applications, open problems, and future directions are discussed.

Don't count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors

Abstract: Context-predicting models (more commonly known as embeddings or neural language models) are the new kids on the distributional semantics block. Despite the buzz surrounding these models, the literature is still lacking a systematic comparison of the predictive models with classic, count-vector-based distributional semantic approaches. In this paper, we perform such an extensive evaluation, on a wide range of lexical semantics tasks and across many parameter settings. The results, to our own surprise, show that the buzz is fully justified, as the context-predicting models obtain a thorough and resounding victory against their count-based counterparts.

Improving Distributional Similarity with Lessons Learned from Word Embeddings

Abstract: Recent trends suggest that neural-network-inspired word embedding models outperform traditional count-based distributional models on word similarity and analogy detection tasks. We reveal that much of the performance gains of word embeddings are due to certain system design choices and hyperparameter optimizations, rather than the embedding algorithms themselves. Furthermore, we show that these modifications can be transferred to traditional distributional models, yielding similar gains. In contrast to prior reports, we observe mostly local or insignificant performance differences between the methods, with no global advantage to any single approach over the others.