Cookies Policy
The website need some cookies and similar means to function. If you permit us, we will use those means to collect data on your visits for aggregated statistics to improve our service. Find out More
Accept Reject
  • Menu
Interest
Topics
Details

Details

  • Name

    Daniel Bouçanova Loureiro
  • Cluster

    Computer Science
  • Role

    External Research Collaborator
  • Since

    01st November 2017
003
Publications

2022

LMMS reloaded: Transformer-based sense embeddings for disambiguation and beyond

Authors
Loureiro, D; Mário Jorge, A; Camacho Collados, J;

Publication
ARTIFICIAL INTELLIGENCE

Abstract

2022

TimeLMs: Diachronic Language Models from Twitter

Authors
Loureiro, D; Barbieri, F; Neves, L; Anke, LE; Camacho-Collados, J;

Publication
PROCEEDINGS OF THE 60TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2022): PROCEEDINGS OF SYSTEM DEMONSTRATIONS

Abstract
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 strategy contributes to enhancing Twitter-based language models' capacity to deal with future and out-of-distribution tweets, while making them competitive with standardized and more monolithic benchmarks. We also perform a number of qualitative analyses showing how they cope with trends and peaks in activity involving specific named entities or concept drift. TimeLMs is available at https://github.com/cardiffnlp/timelms.

2021

Analysis and evaluation of language models for word sense disambiguation

Authors
Loureiro, D; Rezaee, K; Pilehvar, MT; Camacho Collados, J;

Publication
COMPUTATIONAL LINGUISTICS

Abstract
Transformer-based language models have taken many fields in NLP by storm. BERT and its derivatives dominate most of the existing evaluation benchmarks, including those for Word Sense Disambiguation (WSD), thanks to their ability in capturing context-sensitive semantic nuances. However, there is still little knowledge about their capabilities and potential limitations in encoding and recovering word senses. In this article, we provide an in-depth quantitative and qualitative analysis of the celebrated BERT model with respect to lexical ambiguity. One of the main conclusions of our analysis is that BERT can accurately capture high-level sense distinctions, even when a limited number of examples is available for each word sense. Our analysis also reveals that in some cases language models come close to solving coarse-grained noun disambiguation under ideal conditions in terms of availability of training data and computing resources. However, this scenario rarely occurs in real-world settings and, hence, many practical challenges remain even in the coarse-grained setting. We also perform an in-depth comparison of the two main language model-based WSD strategies, namely, fine-tuning and feature extraction, finding that the latter approach is more robust with respect to sense bias and it can better exploit limited available training data. In fact, the simple feature extraction strategy of averaging contextualized embeddings proves robust even using only three training sentences per word sense, with minimal improvements obtained by increasing the size of this training data.

2021

Improving Portuguese Semantic Role Labeling with Transformers and Transfer Learning

Authors
Oliveira, S; Loureiro, D; Jorge, A;

Publication
2021 IEEE 8TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA)

Abstract
The Natural Language Processing task of determining Who did what to whom is called Semantic Role Labeling. For English, recent methods based on Transformer models have allowed for major improvements in this task over the previous state of the art. However, for low resource languages, like Portuguese, currently available semantic role labeling models are hindered by scarce training data. In this paper, we explore a model architecture with only a pre-trained Transformer-based model, a linear layer, softmax and Viterbi decoding. We substantially improve the state-of-the-art performance in Portuguese by over 15 F1. Additionally, we improve semantic role labeling results in Portuguese corpora by exploiting cross-lingual transfer learning using multilingual pre-trained models, and transfer learning from dependency parsing in Portuguese, evaluating the various proposed approaches empirically.

2020

MedLinker: Medical Entity Linking with Neural Representations and Dictionary Matching

Authors
Loureiro, D; Jorge, AM;

Publication
Advances in Information Retrieval - 42nd European Conference on IR Research, ECIR 2020, Lisbon, Portugal, April 14-17, 2020, Proceedings, Part II

Abstract