2024
Joanne Boisson, Asahi Ushio, Hsuvas Borkakoty, Kiamehr Rezaee, Dimosthenis Antypas, Zara Siddique, Nina White, Jose Camacho-Collados
How Are Metaphors Processed by Language Models? The Case of Analogies
Proceedings of CoNLL 2024 Main Conference [acl anthology]
Dimosthenis Antypas, Asahi Ushio, Francesco Barbieri, Jose Camacho-Collados
Multilingual Topic Classification in X: Dataset and Analysis
Proceedings of EMNLP 2024 Main Conference [acl anthology]
Asahi Ushio and Jose Camacho Collados
A Systematic Analysis on the Temporal Generalization of Language Models in Social Media
Proceedings of 14th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis [dataset] [acl anthology] [arxiv]
Asahi Ushio, Jose Camacho Collados, Steven Schockaert
A RelEntLess Benchmark for Modelling Graded Relations between Named Entities
Proceedings of EACL 2024 Main Conference [dataset] [slide] [acl anthology] [arxiv]
2023
Asahi Ushio
Representing Relational Knowledge with Language Models
Ph.D. Thesis, Cardiff University, 2023 [slide] [thesis pdf]
Asahi Ushio, Yi Zhou, Jose Camacho-Collados
An Efficient Multilingual Language Model Compression through Vocabulary Trimming
Proceedings of EMNLP 2023 Findings [code] [slide] [acl anthology] [arxiv]
Dimosthenis Antypas, Asahi Ushio, Francesco Barbieri, Leonardo Neves, Kiamehr Rezaee, Luis Espinosa-Anke, Jiaxin Pei, Jose Camacho-Collados
SuperTweetEval: A Challenging, Unified and Heterogeneous Benchmark for Social Media NLP Research
Proceedings of EMNLP 2023 Findings [dataset] [code] [acl anthology]
Asahi Ushio, Fernando Alva-Manchego, and Jose Camacho-Collados
A Practical Toolkit for Multilingual Question and Answer Generation
Proceedings of ACL 2023 System Demonstration [code] [slide] [acl anthology] [arxiv]
Asahi Ushio, Fernando Alva-Manchego, and Jose Camacho-Collados
An Empirical Comparison of LM-based Question and Answer Generation Methods
Proceedings of ACL 2023 Findings [code] [acl anthology] [arxiv]
Asahi Ushio, Jose Camacho Collados, Steven Schockaert
RelBERT: Embedding Relations with Language Models
arXiv:2305.15002 [code] [arxiv]
2022
Asahi Ushio, Fernando Alva-Manchego, and Jose Camacho-Collados
Generative Language Models for Paragraph-Level Question Generation: A Unified Benchmark and Evaluation
Proceedings of EMNLP 2022 Main Conference [dataset] [code] [slide] [acl anthology] [arxiv]
Jose Camacho-Collados, Kiamehr Rezaee, Talayeh Riahi, Asahi Ushio, Daniel Loureiro, Dimosthenis Antypas, Joanne Boisson, Luis Espinosa-Anke, Fangyu Liu, Eugenio Martínez-Cámara, Gonzalo Medina, Thomas Buhrmann, Leonardo Neves, and Francesco Barbieri
TweetNLP: Cutting-Edge Natural Language Processing for Social Media
Proceedings of EMNLP 2022 System Demonstration [code] [demo] [acl anthology] [arxiv]
Asahi Ushio and Danushka Bollegala
Zero-shot Cross-Lingual Counterfactual Detection via Automatic Extraction and Prediction of Clue Phrases
Proceedings of the 2nd Workshop on Multilingual Representation Learning [acl anthology]
Aleksandra Edwards, Asahi Ushio, Jose Camacho-Collados, Helene de Ribaupierre, and Alun Preece
Guiding Generative Language Models for Data Augmentation in Few-Shot Text Classification
Proceedings of the 3rd Workshop on Data Science with Human in the Loop [acl anthology]
Asahi Ushio, Leonardo Neves, Vitor Silva, Francesco Barbieri, and Jose Camacho-Collados
Named Entity Recognition in Twitter: A Dataset and Analysis on Short-Term Temporal Shifts
Proceedings of AACL 2022 Main Conference [dataset] [code] [slide] [acl anthology] [arxiv]
Dimosthenis Antypas*, Asahi Ushio*, Jose Camacho-Collados, Leonardo Neves, Vitor Silva, and Francesco Barbieri
Twitter Topic Classification (*equal contribution)
Proceedings of COLING 2022 Main Conference [dataset (multi)] [dataset (single)] [acl anthology] [arxiv]
2021
Asahi Ushio, Jose Camacho-Collados, and Steven Schockaert
Distilling Relation Embeddings from Pre-trained Language Models
Proceedings of EMNLP 2021 Main Conference [code] [slide] [acl anthology] [arxiv]
Asahi Ushio, Federico Liberatore, and Jose Camacho-Collados
Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction
Proceedings of EMNLP 2021 Main Conference [code] [slide] [acl anthology] [arxiv]
Asahi Ushio, Luis Espinosa-Anke, Steven Schockaert, and Jose Camacho-Collados
BERT is to NLP what AlexNet is to CV: Can Pre-Trained Language Models Identify Analogies?
Proceedings of ACL-IJCNLP 2021 Main Conference [code] [slide] [acl anthology] [arxiv]
Asahi Ushio and Jose Camacho-Collados
T-NER: An All-Round Python Library for Transformer-based Named Entity Recognition
Proceedings of EACL 2021 System Demonstration [code] [demo] [slide] [acl anthology] [arxiv]
2019
Max F. Frenzel, Bogdan Teleaga, and Asahi Ushio
Latent Space Cartography: Generalised Metric-Inspired Measures and Measure-Based Transformations for Generative Models
arXiv:1902.02113 [arxiv]
Asahi Ushio and Masahiro Yukawa
Projection-based Regularized Dual Averaging for Stochastic Optimization
IEEE Trans. Signal Processing 2019 [code] [ieee explorer] [paper]
Ken McAlinn, Asahi Ushio, and Teruo Nakatsuma
Volatility Forecasts Using Nonlinear Leverage Effects
Journal of Forecasting, 2019 [arxiv]
2018
Asahi Ushio
Projection-based Regularized Dual Averaging for Stochastic Optimization with Its Applications to Classification and Regression
Master thesis, Keio University, 2018 [code] [slide] [thesis pdf]
2017
Asahi Ushio and Masahiro Yukawa
Projection-based Regularized Dual Averaging for Stochastic Optimization
Proceedings of ICASSP 2017 [code] [slide] [ieee explorer]