publications

2023

1. ArXiv

   Neurons in Large Language Models: Dead, N-gram, Positional

   Voita, Elena,  Ferrando, Javier, and Nalmpantis, Christoforos

   In ArXiv 2023

   Abs PDF

   We analyze a family of large language models in such a lightweight manner that can be done on a single GPU. Specifically, we focus on the OPT family of models ranging from 125m to 66b parameters and rely only on whether an FFN neuron is activated or not. First, we find that the early part of the network is sparse and represents many discrete features. Here, many neurons (more than 70% in some layers of the 66b model) are "dead", i.e. they never activate on a large collection of diverse data. At the same time, many of the alive neurons are reserved for discrete features and act as token and n-gram detectors. Interestingly, their corresponding FFN updates not only promote next token candidates as could be expected, but also explicitly focus on removing the information about triggering them tokens, i.e., current input. To the best of our knowledge, this is the first example of mechanisms specialized at removing (rather than adding) information from the residual stream. With scale, models become more sparse in a sense that they have more dead neurons and token detectors. Finally, some neurons are positional: them being activated or not depends largely (or solely) on position and less so (or not at all) on textual data. We find that smaller models have sets of neurons acting as position range indicators while larger models operate in a less explicit manner.

2. WMT

   Automating Behavioral Testing in Machine Translation

   Ferrando, Javier, Sperber, Matthias, Setiawan, Hendra, Telaar, Dominic, and Hasan, Saša

   In Eight Conference on Machine Translation (WMT 2023) 2023

   Abs PDF

   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.

3. ACL

   Explaining How Transformers Use Context to Build Predictions

   Ferrando, Javier, Gállego, Gerard I., Tsiamas, Ioannis, and Costa-jussà, Marta R.

   In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics 2023

   Abs PDF

   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.

2022

1. EMNLP

   Towards Opening the Black Box of Neural Machine Translation: Source and Target Interpretations of the Transformer

   Ferrando, Javier, Gállego, Gerard I., Alastruey, Belen, Escolano, Carlos, and Costa-jussà, Marta R.

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 2022

   Abs PDF

   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 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 complete input token attributions. 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.

2. EMNLP

   Measuring the Mixing of Contextual Information in the Transformer

   Ferrando, Javier, Gállego, Gerard I., and Costa-jussà, Marta R.

   In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing 2022

   Abs PDF

   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, considering the characteristics of the representation space. 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 faithful explanations and outperforms similar aggregation methods.

3. ACL SRW

   On the Locality of Attention in Direct Speech Translation

   Alastruey*, Belen,  Ferrando*, Javier, Gállego, Gerard I., and Costa-jussá, Marta R.

   In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: Student Research Workshop May 2022

   Abs PDF

   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.

4. AAAI

   Interpreting Gender Bias in Neural Machine Translation: Architecture Matters

   Costa-jussà, Marta R., Escolano, Carlos, Basta, Christine,  Ferrando, Javier, Batlle, Roser, and Kharitonova, Ksenia

   In Proceedings of AAAI May 2022

   Abs PDF

   Multilingual neural machine translation architectures mainly differ in the number of sharing modules and parameters applied among languages. In this paper, and from an algorithmic perspective, we explore whether the chosen architecture, when trained with the same data, influences the level of gender bias. Experiments conducted in three language pairs show that language-specific encoder-decoders exhibit less bias than the shared architecture. We propose two methods for interpreting and studying gender bias in machine translation based on source embeddings and attention. Our analysis shows that, in the language-specific case, the embeddings encode more gender information, and their attention is more diverted. Both behaviors help in mitigating gender bias.

2021

1. EMNLP Findings

   Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions

   Ferrando, Javier, and Costa-jussà, Marta R.

   In Findings of the Association for Computational Linguistics: EMNLP 2021 Nov 2021

   Abs PDF

   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.

2020

1. ICCS

   Improving Accuracy and Speeding Up Document Image Classification Through Parallel Systems

   Ferrando, Javier, Domínguez, Juan Luis, Torres, Jordi, García, Raúl, García, David, Garrido, Daniel, Cortada, Jordi, and Valero, Mateo

   In Computational Science – ICCS 2020 Nov 2020

   Abs PDF

   This paper presents a study showing the benefits of the EfficientNet models compared with heavier Convolutional Neural Networks (CNNs) in the Document Classification task, essential problem in the digitalization process of institutions. We show in the RVL-CDIP dataset that we can improve previous results with a much lighter model and present its transfer learning capabilities on a smaller in-domain dataset such as Tobacco3482. Moreover, we present an ensemble pipeline which is able to boost solely image input by combining image model predictions with the ones generated by BERT model on extracted text by OCR. We also show that the batch size can be effectively increased without hindering its accuracy so that the training process can be sped up by parallelizing throughout multiple GPUs, decreasing the computational time needed. Lastly, we expose the training performance differences between PyTorch and Tensorflow Deep Learning frameworks.