Abstract

Neural sequence generation systems oftentimes generate sequences by searching for the most likely sequence under the learnt probability distribution. This assumes that the most likely sequence, i.e. the mode, under such a model must also be the best sequence it has to offer (often in a given context, e.g. conditioned on a source sentence in translation). Recent findings in neural machine translation (NMT) show that the true most likely sequence oftentimes is empty under many state-of-the-art NMT models. This follows a large list of other pathologies and biases observed in NMT and other sequence generation models: a length bias, larger beams degrading performance, exposure bias, and many more. Many of these works blame the probabilistic formulation of NMT or maximum likelihood estimation. We provide a different view on this: it is mode-seeking search, e.g. beam search, that introduces many of these pathologies and biases, and such a decision rule is not suitable for the type of distributions learnt by NMT systems. We show that NMT models spread probability mass over many translations, and that the most likely translation oftentimes is a rare event. We further show that translation distributions do capture important aspects of translation well in expectation. Therefore, we advocate for decision rules that take into account the entire probability distribution and not just its mode. We provide one example of such a decision rule, and show that this is a fruitful research direction.

Biography

I am an assistant professor (UD) in natural language processing at the Institute for Logic, Language and Computation where I lead the Probabilistic Language Learning group.

My work concerns the design of models and algorithms that learn to represent, understand, and generate language data. Examples of specific problems I am interested in include language modelling, machine translation, syntactic parsing, textual entailment, text classification, and question answering.

I also develop techniques to approach general machine learning problems such as probabilistic inference, gradient and density estimation.

My interests sit at the intersection of disciplines such as statistics, machine learning, approximate inference, global optimization, formal languages, and computational linguistics.