Bruno Martins


2024

pdf bib
Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings
Goncalo Gomes | Isabel Coutinho | Bruno Martins
Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)

Although the International Classification of Diseases (ICD) has been adopted worldwide, manually assigning ICD codes to clinical text is time-consuming, error-prone, and expensive, motivating the development of automated approaches. This paper describes a novel approach for automated ICD coding, combining several ideas from previous related work. We specifically employ a strong Transformer-based model as a text encoder and, to handle lengthy clinical narratives, we explored either (a) adapting the base encoder model into a Longformer, or (b) dividing the text into chunks and processing each chunk independently. The representations produced by the encoder are combined with a label embedding mechanism that explores diverse ICD code synonyms. Experiments with different splits of the MIMIC-III dataset show that the proposed approach outperforms the current state-of-the-art models in ICD coding, with the label embeddings significantly contributing to the good performance. Our approach also leads to properly calibrated classification results, which can effectively inform downstream tasks such as quantification.

2023

pdf bib
LMCap: Few-shot Multilingual Image Captioning by Retrieval Augmented Language Model Prompting
Rita Ramos | Bruno Martins | Desmond Elliott
Findings of the Association for Computational Linguistics: ACL 2023

Multilingual image captioning has recently been tackled by training with large-scale machine translated data, which is an expensive, noisy, and time-consuming process. Without requiring any multilingual caption data, we propose LMCap, an image-blind few-shot multilingual captioning model that works by prompting a language model with retrieved captions. Specifically, instead of following the standard encoder-decoder paradigm, given an image, LMCap first retrieves the captions of similar images using a multilingual CLIP encoder. These captions are then combined into a prompt for an XGLM decoder, in order to generate captions in the desired language. In other words, the generation model does not directly process the image, instead it processes retrieved captions. Experiments on the XM3600 dataset of geographically diverse images show that our model is competitive with fully-supervised multilingual captioning models, without requiring any supervised training on any captioning data.

pdf bib
Retrieval-augmented Image Captioning
Rita Ramos | Desmond Elliott | Bruno Martins
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

Inspired by retrieval-augmented language generation and pretrained Vision and Language (V&L) encoders, we present a new approach to image captioning that generates sentences given the input image and a set of captions retrieved from a datastore, as opposed to the image alone. The encoder in our model jointly processes the image and retrieved captions using a pretrained V&L BERT, while the decoder attends to the multimodal encoder representations, benefiting from the extra textual evidence from the retrieved captions. Experimental results on the COCO dataset show that image captioning can be effectively formulated from this new perspective. Our model, named EXTRA, benefits from using captions retrieved from the training dataset, and it can also benefit from using an external dataset without the need for retraining. Ablation studies show that retrieving a sufficient number of captions (e.g., k=5) can improve captioning quality. Our work contributes towards using pretrained V&L encoders for generative tasks, instead of standard classification tasks.

pdf bib
Prompting, Retrieval, Training: An exploration of different approaches for task-oriented dialogue generation
Gonçalo Raposo | Luisa Coheur | Bruno Martins
Proceedings of the 24th Annual Meeting of the Special Interest Group on Discourse and Dialogue

Task-oriented dialogue systems need to generate appropriate responses to help fulfill users’ requests. This paper explores different strategies, namely prompting, retrieval, and fine-tuning, for task-oriented dialogue generation. Through a systematic evaluation, we aim to provide valuable insights and guidelines for researchers and practitioners working on developing efficient and effective dialogue systems for real-world applications. Evaluation is performed on the MultiWOZ and Taskmaster-2 datasets, and we test various versions of FLAN-T5, GPT-3.5, and GPT-4 models. Costs associated with running these models are analyzed, and dialogue evaluation is briefly discussed. Our findings suggest that when testing data differs from the training data, fine-tuning may decrease performance, favoring a combination of a more general language model and a prompting mechanism based on retrieved examples.

2022

pdf bib
Annotating Arguments in a Corpus of Opinion Articles
Gil Rocha | Luís Trigo | Henrique Lopes Cardoso | Rui Sousa-Silva | Paula Carvalho | Bruno Martins | Miguel Won
Proceedings of the Thirteenth Language Resources and Evaluation Conference

Interest in argument mining has resulted in an increasing number of argument annotated corpora. However, most focus on English texts with explicit argumentative discourse markers, such as persuasive essays or legal documents. Conversely, we report on the first extensive and consolidated Portuguese argument annotation project focused on opinion articles. We briefly describe the annotation guidelines based on a multi-layered process and analyze the manual annotations produced, highlighting the main challenges of this textual genre. We then conduct a comprehensive inter-annotator agreement analysis, including argumentative discourse units, their classes and relations, and resulting graphs. This analysis reveals that each of these aspects tackles very different kinds of challenges. We observe differences in annotator profiles, motivating our aim of producing a non-aggregated corpus containing the insights of every annotator. We note that the interpretation and identification of token-level arguments is challenging; nevertheless, tasks that focus on higher-level components of the argument structure can obtain considerable agreement. We lay down perspectives on corpus usage, exploiting its multi-faceted nature.

pdf bib
Dense Template Retrieval for Customer Support
Tiago Mesquita | Bruno Martins | Mariana Almeida
Proceedings of the 29th International Conference on Computational Linguistics

Templated answers are used extensively in customer support scenarios, providing an efficient way to cover a plethora of topics, with an easily maintainable collection of templates. However, the number of templates is often too high for an agent to manually search. Automatically suggesting the correct template for a given question can thus improve the service efficiency, reducing costs and leading to a better customer satisfaction. In this work, we propose a dense retrieval framework for the customer support scenario, adapting a standard in-batch negatives technique to support unpaired sampling of queries and templates. We also propose a novel loss that extends the typical query-centric similarity, exploiting other similarity relations in the training data. Experiments show that our approach achieves considerable improvements, in terms of performance and training speed, over more standard dense retrieval methods. This includes methods such as DPR, and also ablated versions of the proposed approach.

2020

pdf bib
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation
André Martins | Helena Moniz | Sara Fumega | Bruno Martins | Fernando Batista | Luisa Coheur | Carla Parra | Isabel Trancoso | Marco Turchi | Arianna Bisazza | Joss Moorkens | Ana Guerberof | Mary Nurminen | Lena Marg | Mikel L. Forcada
Proceedings of the 22nd Annual Conference of the European Association for Machine Translation

2015

pdf bib
Semi-Supervised Bootstrapping of Relationship Extractors with Distributional Semantics
David S. Batista | Bruno Martins | Mário J. Silva
Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

pdf bib
ULisboa: Recognition and Normalization of Medical Concepts
André Leal | Bruno Martins | Francisco Couto
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf bib
INESC-ID: A Regression Model for Large Scale Twitter Sentiment Lexicon Induction
Silvio Amir | Ramon F. Astudillo | Wang Ling | Bruno Martins | Mario J. Silva | Isabel Trancoso
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

pdf bib
INESC-ID: Sentiment Analysis without Hand-Coded Features or Linguistic Resources using Embedding Subspaces
Ramon F. Astudillo | Silvio Amir | Wang Ling | Bruno Martins | Mario J. Silva | Isabel Trancoso
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)

2014

pdf bib
TUGAS: Exploiting unlabelled data for Twitter sentiment analysis
Silvio Amir | Miguel B. Almeida | Bruno Martins | João Filgueiras | Mário J. Silva
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

pdf bib
ULisboa: Identification and Classification of Medical Concepts
André Leal | Diogo Gonçalves | Bruno Martins | Francisco M. Couto
Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)

2013

pdf bib
REACTION: A naive machine learning approach for sentiment classification
Silvio Moreira | João Filgueiras | Bruno Martins | Francisco Couto | Mário J. Silva
Second Joint Conference on Lexical and Computational Semantics (*SEM), Volume 2: Proceedings of the Seventh International Workshop on Semantic Evaluation (SemEval 2013)

2011

pdf bib
Named entity translation using anchor texts
Wang Ling | Pável Calado | Bruno Martins | Isabel Trancoso | Alan Black | Luísa Coheur
Proceedings of the 8th International Workshop on Spoken Language Translation: Papers

This work describes a process to extract Named Entity (NE) translations from the text available in web links (anchor texts). It translates a NE by retrieving a list of web documents in the target language, extracting the anchor texts from the links to those documents and finding the best translation from the anchor texts, using a combination of features, some of which, are specific to anchor texts. Experiments performed on a manually built corpora, suggest that over 70% of the NEs, ranging from unpopular to popular entities, can be translated correctly using sorely anchor texts. Tests on a Machine Translation task indicate that the system can be used to improve the quality of the translations of state-of-the-art statistical machine translation systems.