Related papers: Language-Informed Beam Search Decoding for Multili…
Zero-shot In-context learning is the phenomenon where models can perform the task simply given the instructions. However, pre-trained large language models are known to be poorly calibrated for this task. One of the most effective…
Decoding methods for large language models often trade-off between diversity of outputs and parallelism of computation. Methods such as beam search and Gumbel top-k sampling can guarantee a different output for each element of the beam, but…
Neural Machine Translation (NMT) has made remarkable progress over the past years. However, under-translation and over-translation remain two challenging problems in state-of-the-art NMT systems. In this work, we conduct an in-depth…
Neural Machine Translation (NMT) systems are typically evaluated using automated metrics that assess the agreement between generated translations and ground truth candidates. To improve systems with respect to these metrics, NLP researchers…
To be included into chatbot systems, Large language models (LLMs) must be aligned with human conversational conventions. However, being trained mainly on web-scraped data gives existing LLMs a voice closer to informational text than actual…
Vision-language model (VLM) embeddings have been shown to encode biases present in their training data, such as societal biases that prescribe negative characteristics to members of various racial and gender identities. VLMs are being…
Multilingual neural machine translation aims at learning a single translation model for multiple languages. These jointly trained models often suffer from performance degradation on rich-resource language pairs. We attribute this…
We present Grid Beam Search (GBS), an algorithm which extends beam search to allow the inclusion of pre-specified lexical constraints. The algorithm can be used with any model that generates a sequence $ \mathbf{\hat{y}} = \{y_{0}\ldots…
Neural machine translation inference procedures like beam search generate the most likely output under the model. This can exacerbate any demographic biases exhibited by the model. We focus on gender bias resulting from systematic errors in…
Attentional sequence-to-sequence models have become the new standard for machine translation, but one challenge of such models is a significant increase in training and decoding cost compared to phrase-based systems. Here, we focus on…
Neural Machine Translation (NMT) currently exhibits biases such as producing translations that are too short and overgenerating frequent words, and shows poor robustness to copy noise in training data or domain shift. Recent work has tied…
We propose a novel decoding approach for neural machine translation (NMT) based on continuous optimisation. We convert decoding - basically a discrete optimization problem - into a continuous optimization problem. The resulting constrained…
We report on search errors and model errors in neural machine translation (NMT). We present an exact inference procedure for neural sequence models based on a combination of beam search and depth-first search. We use our exact search to…
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…
In this work we look into adding a new language to a multilingual NMT system in an unsupervised fashion. Under the utilization of pre-trained cross-lingual word embeddings we seek to exploit a language independent multilingual sentence…
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…
Beam search is widely used in neural machine translation, and usually improves translation quality compared to greedy search. It has been widely observed that, however, beam sizes larger than 5 hurt translation quality. We explain why this…
Cross-lingual natural language processing relies on translation, either by humans or machines, at different levels, from translating training data to translating test sets. However, compared to original texts in the same language,…
The ability of zero-shot translation emerges when we train a multilingual model with certain translation directions; the model can then directly translate in unseen directions. Alternatively, zero-shot translation can be accomplished by…
Decoding for many NLP tasks requires an effective heuristic algorithm for approximating exact search since the problem of searching the full output space is often intractable, or impractical in many settings. The default algorithm for this…