Javier Ferrando


2023

pdf bib
Explaining How Transformers Use Context to Build Predictions
Javier Ferrando | Gerard I. Gállego | Ioannis Tsiamas | Marta R. Costa-jussà
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Language Generation Models produce words based on the previous context. Although existing methods offer input attributions as explanations for a model’s prediction, it is still unclear how prior words affect the model’s decision throughout the layers. In this work, we leverage recent advances in explainability of the Transformer and present a procedure to analyze models for language generation. Using contrastive examples, we compare the alignment of our explanations with evidence of the linguistic phenomena, and show that our method consistently aligns better than gradient-based and perturbation-based baselines. Then, we investigate the role of MLPs inside the Transformer and show that they learn features that help the model predict words that are grammatically acceptable. Lastly, we apply our method to Neural Machine Translation models, and demonstrate that they generate human-like source-target alignments for building predictions.

pdf bib
Toxicity in Multilingual Machine Translation at Scale
Marta Costa-jussà | Eric Smith | Christophe Ropers | Daniel Licht | Jean Maillard | Javier Ferrando | Carlos Escolano
Findings of the Association for Computational Linguistics: EMNLP 2023

Machine Translation systems can produce different types of errors, some of which are characterized as critical or catastrophic due to the specific negative impact that they can have on users. In this paper we focus on one type of critical error: added toxicity. We evaluate and analyze added toxicity when translating a large evaluation dataset (HOLISTICBIAS, over 472k sentences, covering 13 demographic axes) from English into 164 languages. An automatic toxicity evaluation shows that added toxicity across languages varies from 0% to 5%. The output languages with the most added toxicity tend to be low-resource ones, and the demographic axes with the most added toxicity include sexual orientation, gender and sex, and ability. We also perform human evaluation on a subset of 8 translation directions, confirming the prevalence of true added toxicity. We use a measurement of the amount of source contribution to the translation, where a low source contribution implies hallucination, to interpret what causes toxicity. Making use of the input attributions allows us to explain toxicity, because the source contributions significantly correlate with toxicity for 84% of languages studied. Given our findings, our recommendations to reduce added toxicity are to curate training data to avoid mistranslations, mitigate hallucination and check unstable translations.

pdf bib
Automating Behavioral Testing in Machine Translation
Javier Ferrando | Matthias Sperber | Hendra Setiawan | Dominic Telaar | Saša Hasan
Proceedings of the Eighth Conference on Machine Translation

Behavioral testing in NLP allows fine-grained evaluation of systems by examining their linguistic capabilities through the analysis of input-output behavior. Unfortunately, existing work on behavioral testing in Machine Translation (MT) is currently restricted to largely handcrafted tests covering a limited range of capabilities and languages. To address this limitation, we propose to use Large Language Models (LLMs) to generate a diverse set of source sentences tailored to test the behavior of MT models in a range of situations. We can then verify whether the MT model exhibits the expected behavior through matching candidate sets that are also generated using LLMs. Our approach aims to make behavioral testing of MT systems practical while requiring only minimal human effort. In our experiments, we apply our proposed evaluation framework to assess multiple available MT systems, revealing that while in general pass-rates follow the trends observable from traditional accuracy-based metrics, our method was able to uncover several important differences and potential bugs that go unnoticed when relying only on accuracy.

2022

pdf bib
On the Locality of Attention in Direct Speech Translation
Belen Alastruey | Javier Ferrando | Gerard I. Gállego | Marta R. Costa-jussà
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop

Transformers have achieved state-of-the-art results across multiple NLP tasks. However, the self-attention mechanism complexity scales quadratically with the sequence length, creating an obstacle for tasks involving long sequences, like in the speech domain. In this paper, we discuss the usefulness of self-attention for Direct Speech Translation. First, we analyze the layer-wise token contributions in the self-attention of the encoder, unveiling local diagonal patterns. To prove that some attention weights are avoidable, we propose to substitute the standard self-attention with a local efficient one, setting the amount of context used based on the results of the analysis. With this approach, our model matches the baseline performance, and improves the efficiency by skipping the computation of those weights that standard attention discards.

pdf bib
Measuring the Mixing of Contextual Information in the Transformer
Javier Ferrando | Gerard I. Gállego | Marta R. Costa-jussà
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

The Transformer architecture aggregates input information through the self-attention mechanism, but there is no clear understanding of how this information is mixed across the entire model. Additionally, recent works have demonstrated that attention weights alone are not enough to describe the flow of information. In this paper, we consider the whole attention block –multi-head attention, residual connection, and layer normalization– and define a metric to measure token-to-token interactions within each layer. Then, we aggregate layer-wise interpretations to provide input attribution scores for model predictions. Experimentally, we show that our method, ALTI (Aggregation of Layer-wise Token-to-token Interactions), provides more faithful explanations and increased robustness than gradient-based methods.

pdf bib
Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer
Javier Ferrando | Gerard I. Gállego | Belen Alastruey | Carlos Escolano | Marta R. Costa-jussà
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing

In Neural Machine Translation (NMT), each token prediction is conditioned on the source sentence and the target prefix (what has been previously translated at a decoding step). However, previous work on interpretability in NMT has mainly focused solely on source sentence tokens’ attributions. Therefore, we lack a full understanding of the influences of every input token (source sentence and target prefix) in the model predictions. In this work, we propose an interpretability method that tracks input tokens’ attributions for both contexts. Our method, which can be extended to any encoder-decoder Transformer-based model, allows us to better comprehend the inner workings of current NMT models. We apply the proposed method to both bilingual and multilingual Transformers and present insights into their behaviour.

2021

pdf bib
The TALP-UPC Participation in WMT21 News Translation Task: an mBART-based NMT Approach
Carlos Escolano | Ioannis Tsiamas | Christine Basta | Javier Ferrando | Marta R. Costa-jussa | José A. R. Fonollosa
Proceedings of the Sixth Conference on Machine Translation

This paper describes the submission to the WMT 2021 news translation shared task by the UPC Machine Translation group. The goal of the task is to translate German to French (De-Fr) and French to German (Fr-De). Our submission focuses on fine-tuning a pre-trained model to take advantage of monolingual data. We fine-tune mBART50 using the filtered data, and additionally, we train a Transformer model on the same data from scratch. In the experiments, we show that fine-tuning mBART50 results in 31.69 BLEU for De-Fr and 23.63 BLEU for Fr-De, which increases 2.71 and 1.90 BLEU accordingly, as compared to the model we train from scratch. Our final submission is an ensemble of these two models, further increasing 0.3 BLEU for Fr-De.

pdf bib
Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions
Javier Ferrando | Marta R. Costa-jussà
Findings of the Association for Computational Linguistics: EMNLP 2021

This work proposes an extensive analysis of the Transformer architecture in the Neural Machine Translation (NMT) setting. Focusing on the encoder-decoder attention mechanism, we prove that attention weights systematically make alignment errors by relying mainly on uninformative tokens from the source sequence. However, we observe that NMT models assign attention to these tokens to regulate the contribution in the prediction of the two contexts, the source and the prefix of the target sequence. We provide evidence about the influence of wrong alignments on the model behavior, demonstrating that the encoder-decoder attention mechanism is well suited as an interpretability method for NMT. Finally, based on our analysis, we propose methods that largely reduce the word alignment error rate compared to standard induced alignments from attention weights.