Measuring the quality of a generated sequence against a set of references is a central problem in many learning frameworks, be it to compute a score, to assign a reward, or to perform discrimination. Despite great advances in model architectures, metrics that scale independently of the number of references are still based on n-gram estimates. We show that the underlying operations, counting words and comparing counts, can be lifted to embedding words and comparing embeddings. An in-depth analysis of BERT embeddings shows empirically that contextual embeddings can be employed to capture the required dependencies while maintaining the necessary scalability through appropriate pruning and smoothing techniques. We cast unconditional generation as a reinforcement learning problem and show that our reward function indeed provides a more effective learning signal than n-gram reward in this challenging setting.

Distributed applications are not new. The first distributed applications were developed over 50 years ago with the arrival of computer networks, such as ARPANET. Since then, developers have leveraged distributed systems to scale out applications and services, including large-scale simulations, web serving, and big data processing. In my own career, which started more than 20 years ago, I have worked on distributed systems in the context of the internet, peer-to-peer networks, big data, and now, machine learning. However, until recently, distributed applications have been the exception, rather than the norm.

Recent advancements in attention mechanisms have replaced recurrent neural networks and its variants for machine translation tasks. Transformer using attention mechanism solely achieved state-of-the-art results in sequence modeling. Neural machine translation based on the attention mechanism is parallelizable and addresses the problem of handling long-range dependencies among words in sentences more effectively than recurrent neural networks. One of the key concepts in attention is to learn three matrices, query, key, and value, where global dependencies among words are learned through linearly projecting word embeddings through these matrices. Multiple query, key, value matrices can be learned simultaneously focusing on a different subspace of the embedded dimension, which is called multi-head in Transformer. We argue that certain dependencies among words could be learned better through an intermediate context than directly modeling word-word dependencies. This could happen due to the nature of certain dependencies or lack of patterns that lend them difficult to be modeled globally using multi-head self-attention. In this work, we propose a new way of learning dependencies through a context in multi-head using convolution. This new form of multi-head attention along with the traditional form achieves better results than Transformer on the WMT 2014 English-to-German and English-to-French translation tasks. We also introduce a framework to learn POS tagging and NER information during the training of encoder which further improves results achieving a new state-of-the-art of 32.1 BLEU, better than existing best by 1.4 BLEU, on the WMT 2014 English-to-German and 44.6 BLEU, better than existing best by 1.1 BLEU, on the WMT 2014 English-to-French translation tasks. We call this Transformer++.

In light of the recent breakthroughs in automatic machine translation systems, we propose a novel approach that we term as "Face-to-Face Translation". As today's digital communication becomes increasingly visual, we argue that there is a need for systems that can automatically translate a video of a person speaking in language A into a target language B with realistic lip synchronization. In this work, we create an automatic pipeline for this problem and demonstrate its impact on multiple real-world applications. First, we build a working speech-to-speech translation system by bringing together multiple existing modules from speech and language. We then move towards "Face-to-Face Translation" by incorporating a novel visual module, LipGAN for generating realistic talking faces from the translated audio. Quantitative evaluation of LipGAN on the standard LRW test set shows that it significantly outperforms existing approaches across all standard metrics. We also subject our Face-to-Face Translation pipeline, to multiple human evaluations and show that it can significantly improve the overall user experience for consuming and interacting with multimodal content across languages. Code, models and demo video are made publicly available. Demo video: https://www.youtube.com/watch?v=aHG6Oei8jF0 Code and models: https://github.com/Rudrabha/LipGAN

Uncertainty estimation is important for ensuring safety and robustness of AI systems, especially for high-risk applications. While much progress has recently been made in this area, most research has focused on un-structured prediction, such as image classification and regression tasks. However, while task-specific forms of confidence score estimation have been investigated by the speech and machine translation communities, limited work has investigated general uncertainty estimation approaches for structured prediction. Thus, this work aims to investigate uncertainty estimation for structured prediction tasks within a single unified and interpretable probabilistic ensemble-based framework. We consider uncertainty estimation for sequence data at the token-level and complete sequence-level, provide interpretations for, and applications of, various measures of uncertainty and discuss the challenges associated with obtaining them. This work also explores the practical challenges associated with obtaining uncertainty estimates for structured predictions tasks and provides baselines for token-level error detection, sequence-level prediction rejection, and sequence-level out-of-domain input detection using ensembles of auto-regressive transformer models trained on the WMT'14 English-French and WMT'17 English-German translation and LibriSpeech speech recognition datasets.

Waverly Labs' Ambassador, an over-the-ear translation device, can support up to 20 languages and 42 dialects. The greatest obstacle to international understanding is the barrier of language," wrote British scholar and author Christopher Dawson in November 1957, believing that relying on live, human translators to accurately capture and reflect a speaker's meaning, inflection, and emotion was too great of a challenge to overcome. More than 60 years later, Dawson's theory may finally be proven outdated, thanks to the development of powerful, portable real-time translation devices. The convergence of natural language processing technology, machine learning algorithms, and powerful portable chipsets has led to the development of new devices and applications that allow real-time, two-way translation of speech and text. Language translation devices are capable of listening to an audio source in one language, translating what is being said into another language, and then translating a ...

Transformers are feedforward networks that can process input tokens in parallel. While this parallelization makes them computationally efficient, it restricts the model from fully exploiting the sequential nature of the input - the representation at a given layer can only access representations from lower layers, rather than the higher level representations already built in previous time steps. In this work, we propose the Feedback Transformer architecture that exposes all previous representations to all future representations, meaning the lowest representation of the current timestep is formed from the highest-level abstract representation of the past. We demonstrate on a variety of benchmarks in language modeling, neural machine translation, summarization, and reinforcement learning that the increased representation capacity can improve over Transformer baselines.

The Attention mechanism is now an established technique in many NLP tasks. I've heard about it often, but wanted to go a bit more deep and understand the details. In this first blog post - since I plan to publish a few more blog posts regarding the attention subject - I make an introduction by focusing in the first proposal of attention mechanism, as applied to the task of neural machine translation. To the best of my knowledge the attention mechanism within the context of NLP was first presented in "Neural Machine Translation by Jointly Learning to Align and Translate" at ICLR 2015 (Bahdanau et al. 2015). This was proposed in the context of machine translation, where given a sentence in one language, the model has to produce a translation for that sentence in another language.

The recent advances in Natural Language Processing have been a boon for well-represented languages in terms of available curated data and research resources. One of the challenges for low-resourced languages is clear guidelines on the collection, curation and preparation of datasets for different use-cases. In this work, we take on the task of creation of two datasets that are focused on news headlines (i.e short text) for Setswana and Sepedi and creation of a news topic classification task. We document our work and also present baselines for classification. We investigate an approach on data augmentation, better suited to low resource languages, to improve the performance of the classifiers

Many sequence-to-sequence generation tasks, including machine translation and text-to-speech, can be posed as estimating the density of the output y given the input x: p(y|x). Given this interpretation, it is natural to evaluate sequence-to-sequence models using conditional log-likelihood on a test set. However, the goal of sequence-to-sequence generation (or structured prediction) is to find the best output y^ given an input x, and each task has its own downstream metric R that scores a model output by comparing against a set of references y*: R(y^, y* | x). While we hope that a model that excels in density estimation also performs well on the downstream metric, the exact correlation has not been studied for sequence generation tasks. In this paper, by comparing several density estimators on five machine translation tasks, we find that the correlation between rankings of models based on log-likelihood and BLEU varies significantly depending on the range of the model families being compared. First, log-likelihood is highly correlated with BLEU when we consider models within the same family (e.g. autoregressive models, or latent variable models with the same parameterization of the prior). However, we observe no correlation between rankings of models across different families: (1) among non-autoregressive latent variable models, a flexible prior distribution is better at density estimation but gives worse generation quality than a simple prior, and (2) autoregressive models offer the best translation performance overall, while latent variable models with a normalizing flow prior give the highest held-out log-likelihood across all datasets. Therefore, we recommend using a simple prior for the latent variable non-autoregressive model when fast generation speed is desired.