1

Assessing the Limits of the Distributional Hypothesis in Semantic Spaces: Trait-based Relational Knowledge and the Impact of Co-occurrences
The increase in performance in NLP due to the prevalence of distributional models and deep learning has brought with it a reciprocal …
Mark Anderson, Jose Camacho-Collados
PDF Cite DOI
CardiffNLP-Metaphor at SemEval-2022 Task 2: Targeted Fine-tuning of Transformer-based Language Models for Idiomaticity Detection
This paper describes the experiments ran for SemEval-2022 Task 2, subtask A, zero-shot and one-shot settings for idiomaticity …
Joanne Boisson, Jose Camacho-Collados, Luis Espinosa-Anke
PDF Cite DOI
PeruSIL: A Framework to Build a Continuous Peruvian Sign Language Interpretation Dataset
Video-based datasets for Continuous Sign Language are scarce due to the challenging task of recording videos from native signers and …
Gissella Bejarano, Joe Huamani-Malca, Francisco Cerna-Herrera, Fernando Alva-Manchego, Pablo Rivas
PDF Cite
Simple TICO-19: A Dataset for Joint Translation and Simplification of COVID-19 Texts
Specialist high-quality information is typically first available in English, and it is written in a language that may be difficult to …
Matthew Shardlow, Fernando Alva-Manchego
PDF Cite
Towards Readability-Controlled Machine Translation of COVID-19 Texts
This project investigates the capabilities of Machine Translation models for generating translations at varying levels of readability, …
Fernando Alva-Manchego, Matthew Shardlow
PDF Cite
XLM-T: Multilingual Language Models in Twitter for Sentiment Analysis and Beyond
Language models are ubiquitous in current NLP, and their multilingual capacity has recently attracted considerable attention. However, …
Francesco Barbieri, Luis Espinosa-Anke, Jose Camacho-Collados
PDF Cite
TimeLMs: Diachronic Language Models from Twitter
Despite its importance, the time variable has been largely neglected in the NLP and language model literature. In this paper, we …
Daniel Loureiro, Francesco Barbieri, Leonardo Neves, Luis Espinosa-Anke, Jose Camacho-Collados
PDF Cite DOI
Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction
Term weighting schemes are widely used in Natural Language Processing and Information Retrieval. In particular, term weighting is the …
Asahi Ushio, Federico Liberatore, Jose Camacho-Collados
PDF Cite Code DOI
Distilling Relation Embeddings from Pretrained Language Models
Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense …
Asahi Ushio, Jose Camacho-Collados, Steven Schockaert
PDF Cite Code DOI
On the Cross-lingual Transferability of Contextualized Sense Embeddings
In this paper we analyze the extent to which contextualized sense embeddings, i.e., sense embeddings that are computed based on …
Kiamehr Rezaee, Daniel Loureiro, Jose Camacho-Collados, Mohammad Taher Pilehvar
PDF Cite DOI