Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Anke, Luis Espinosa"'
Autor:
Gajbhiye, Amit, Bouraoui, Zied, Li, Na, Chatterjee, Usashi, Anke, Luis Espinosa, Schockaert, Steven
Concepts play a central role in many applications. This includes settings where concepts have to be modelled in the absence of sentence context. Previous work has therefore focused on distilling decontextualised concept embeddings from language model
Externí odkaz:
http://arxiv.org/abs/2310.14793
Autor:
Loureiro, Daniel, Rezaee, Kiamehr, Riahi, Talayeh, Barbieri, Francesco, Neves, Leonardo, Anke, Luis Espinosa, Camacho-Collados, Jose
This paper introduces a large collection of time series data derived from Twitter, postprocessed using word embedding techniques, as well as specialized fine-tuned language models. This data comprises the past five years and captures changes in n-gra
Externí odkaz:
http://arxiv.org/abs/2308.02142
Autor:
Loureiro, Daniel, D'Souza, Aminette, Muhajab, Areej Nasser, White, Isabella A., Wong, Gabriel, Anke, Luis Espinosa, Neves, Leonardo, Barbieri, Francesco, Camacho-Collados, Jose
Language evolves over time, and word meaning changes accordingly. This is especially true in social media, since its dynamic nature leads to faster semantic shifts, making it challenging for NLP models to deal with new content and trends. However, th
Externí odkaz:
http://arxiv.org/abs/2209.07216
Autor:
Jain, Devansh, Anke, Luis Espinosa
In this paper, we analyze zero-shot taxonomy learning methods which are based on distilling knowledge from language models via prompting and sentence scoring. We show that, despite their simplicity, these methods outperform some supervised strategies
Externí odkaz:
http://arxiv.org/abs/2202.04876
Autor:
Loureiro, Daniel, Barbieri, Francesco, Neves, Leonardo, Anke, Luis Espinosa, Camacho-Collados, Jose
Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we present TimeLMs, a set of language models specialized on diachronic Twitter data. We show that a continual learning strat
Externí odkaz:
http://arxiv.org/abs/2202.03829
Autor:
Mellado, Elena Álvarez, Anke, Luis Espinosa, Arroyo, Julio Gonzalo, Lignos, Constantine, Zamorano, Jordi Porta
Publikováno v:
Procesamiento del Lenguaje Natural 67 (2021), p. 277-285
This paper summarizes the main findings of the ADoBo 2021 shared task, proposed in the context of IberLef 2021. In this task, we invited participants to detect lexical borrowings (coming mostly from English) in Spanish newswire texts. This task was f
Externí odkaz:
http://arxiv.org/abs/2110.15682
One of the long-standing challenges in lexical semantics consists in learning representations of words which reflect their semantic properties. The remarkable success of word embeddings for this purpose suggests that high-quality representations can
Externí odkaz:
http://arxiv.org/abs/2106.07947
Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, current analyses have almost exclusively focused on (multilingual variants of) standard benchmarks, and have relied
Externí odkaz:
http://arxiv.org/abs/2104.12250
Publikováno v:
In Procedia - Social and Behavioral Sciences 25 October 2013 95:612-620
Autor:
Anke, Luis Espinosa
Publikováno v:
In Procedia - Social and Behavioral Sciences 25 October 2013 95:267-275