António Góis

Tiago da Silva, Bruna Bazaluk, Eliezer de Souza da Silva et al.

Causal discovery (CD) algorithms are notably brittle when data is scarce, inferring unreliable causal relations that may contradict expert knowledge, especially when considering latent confounders. Furthermore, the lack of uncertainty quantification in most CD methods hinders users from diagnosing and refining results. To address these issues, we introduce Ancestral GFlowNets (AGFNs). AGFN samples ancestral graphs (AGs) proportionally to a score-based belief distribution representing our epistemic uncertainty over the causal relationships. Building upon this distribution, we propose an elicitation framework for expert-driven assessment. This framework comprises an optimal experimental design to probe the expert and a scheme to incorporate the obtained feedback into AGFN. Our experiments show that: i) AGFN is competitive against other methods that address latent confounding on both synthetic and real-world datasets; and ii) our design for incorporating feedback from a (simulated) human expert or a Large Language Model (LLM) improves inference quality.

António Góis, Mehrnaz Mofakhami, Fernando P. Santos et al.

Agents often have individual goals which depend on a group's actions. If agents trust a forecast of collective action and adapt strategically, such prediction can influence outcomes non-trivially, resulting in a form of performative prediction. This effect is ubiquitous in scenarios ranging from pandemic predictions to election polls, but existing work has ignored interdependencies among predicted agents. As a first step in this direction, we study a collective risk dilemma where agents dynamically decide whether to trust predictions based on past accuracy. As predictions shape collective outcomes, social welfare arises naturally as a metric of concern. We explore the resulting interplay between accuracy and welfare, and demonstrate that searching for stable accurate predictions can minimize social welfare with high probability in our setting. By assuming knowledge of a Bayesian agent behavior model, we then show how to achieve better trade-offs and use them for mechanism design.

Tristan Deleu, António Góis, Chris Emezue et al.

In Bayesian structure learning, we are interested in inferring a distribution over the directed acyclic graph (DAG) structure of Bayesian networks, from data. Defining such a distribution is very challenging, due to the combinatorially large sample space, and approximations based on MCMC are often required. Recently, a novel class of probabilistic models, called Generative Flow Networks (GFlowNets), have been introduced as a general framework for generative modeling of discrete and composite objects, such as graphs. In this work, we propose to use a GFlowNet as an alternative to MCMC for approximating the posterior distribution over the structure of Bayesian networks, given a dataset of observations. Generating a sample DAG from this approximate distribution is viewed as a sequential decision problem, where the graph is constructed one edge at a time, based on learned transition probabilities. Through evaluation on both simulated and real data, we show that our approach, called DAG-GFlowNet, provides an accurate approximation of the posterior over DAGs, and it compares favorably against other methods based on MCMC or variational inference.

Marcos Treviso, António Góis, Patrick Fernandes et al.

Transformers' quadratic complexity with respect to the input sequence length has motivated a body of work on efficient sparse approximations to softmax. An alternative path, used by entmax transformers, consists of having built-in exact sparse attention; however this approach still requires quadratic computation. In this paper, we propose Sparsefinder, a simple model trained to identify the sparsity pattern of entmax attention before computing it. We experiment with three variants of our method, based on distances, quantization, and clustering, on two tasks: machine translation (attention in the decoder) and masked language modeling (encoder-only). Our work provides a new angle to study model efficiency by doing extensive analysis of the tradeoff between the sparsity and recall of the predicted attention graph. This allows for detailed comparison between different models along their Pareto curves, important to guide future benchmarks for sparse attention models.

António Góis, Kyunghyun Cho, André Martins

Recent research in neural machine translation has explored flexible generation orders, as an alternative to left-to-right generation. However, training non-monotonic models brings a new complication: how to search for a good ordering when there is a combinatorial explosion of orderings arriving at the same final result? Also, how do these automatic orderings compare with the actual behaviour of human translators? Current models rely on manually built biases or are left to explore all possibilities on their own. In this paper, we analyze the orderings produced by human post-editors and use them to train an automatic post-editing system. We compare the resulting system with those trained with left-to-right and random post-editing orderings. We observe that humans tend to follow a nearly left-to-right order, but with interesting deviations, such as preferring to start by correcting punctuation or verbs.

António Góis, André F. T. Martins

The combination of machines and humans for translation is effective, with many studies showing productivity gains when humans post-edit machine-translated output instead of translating from scratch. To take full advantage of this combination, we need a fine-grained understanding of how human translators work, and which post-editing styles are more effective than others. In this paper, we release and analyze a new dataset with document-level post-editing action sequences, including edit operations from keystrokes, mouse actions, and waiting times. Our dataset comprises 66,268 full document sessions post-edited by 332 humans, the largest of the kind released to date. We show that action sequences are informative enough to identify post-editors accurately, compared to baselines that only look at the initial and final text. We build on this to learn and visualize continuous representations of post-editors, and we show that these representations improve the downstream task of predicting post-editing time.

Fabio Kepler, Jonay Trénous, Marcos Treviso et al.

We present the contribution of the Unbabel team to the WMT 2019 Shared Task on Quality Estimation. We participated on the word, sentence, and document-level tracks, encompassing 3 language pairs: English-German, English-Russian, and English-French. Our submissions build upon the recent OpenKiwi framework: we combine linear, neural, and predictor-estimator systems with new transfer learning approaches using BERT and XLM pre-trained models. We compare systems individually and propose new ensemble techniques for word and sentence-level predictions. We also propose a simple technique for converting word labels into document-level predictions. Overall, our submitted systems achieve the best results on all tracks and language pairs by a considerable margin.