August 4, 2020 Algorithms Leave a comment

ICML 2020 highlights: A Transformer-based RL agent, causal ML for increased privacy, and more

With over 50 papers from Microsoft accepted at this year’s International Conference on Machine Learning (ICML 2020), a number of which were presented in virtual workshops, Microsoft researchers are in full summer swing when it comes to advancing machine learning in accessibility, privacy, healthcare, and other areas. As Microsoft Partner Research Manager and ICML President John Langford puts it, “ICML is a very broad conference, so its specialty is in some sense ‘all of the above.’” But Langford goes on […]

August 3, 2020 Artificial intelligence Leave a comment

Three new reinforcement learning methods aim to improve AI in gaming and beyond

Reinforcement learning (RL) provides exciting opportunities for game development, as highlighted in our recently announced Project Paidia—a research collaboration between our Game Intelligence group at Microsoft Research Cambridge and game developer Ninja Theory. In Project Paidia, we push the state of the art in reinforcement learning to enable new game experiences. In particular, we focus on developing game agents that learn to genuinely collaborate in teams with human players. In this blog post we showcase three of our recent research […]

July 16, 2020 automatic metrics in MT, NLP Leave a comment

Issue #90 – Tangled up in BLEU: Reevaluating how we evaluate automatic metrics in Machine Translation

16 Jul20 Issue #90 – Tangled up in BLEU: Reevaluating how we evaluate automatic metrics in Machine Translation Author: Dr. Karin Sim, Machine Translation Scientist @ Iconic Introduction Automatic metrics have a crucial role in Machine Translation (MT). They are used to tune the MT systems during the development phase, to determine which model is best, and to subsequently determine the accuracy of the final translations. Currently, the performance of these automatic metrics is judged by seeing how well they […]

July 2, 2020 Multilingual Denoising Pre-training, NLP Leave a comment

Issue #88 – Multilingual Denoising Pre-training for Neural Machine Translation

02 Jul20 Issue #88 – Multilingual Denoising Pre-training for Neural Machine Translation Author: Dr. Chao-Hong Liu, Machine Translation Scientist @ Iconic Introduction Pre-training has been used in many natural language processing (NLP) tasks with significant improvements in performance. In neural machine translation (NMT), pre-training is mostly applied to building blocks of the whole system, e.g. encoder or decoder. In a previous post (#70), we compared several approaches using pre-training with masked language models. In this post, we take a closer […]

June 25, 2020 Estimation Metric, NLP Leave a comment

Issue #87 – YiSi – A Unified Semantic MT Quality Evaluation and Estimation Metric

25 Jun20 Issue #87 – YiSi – A Unified Semantic MT Quality Evaluation and Estimation Metric Author: Dr. Karin Sim, Machine Translation Scientist @ Iconic Introduction Automatic evaluation is an issue that has long troubled machine translation (MT): how do we evaluate how good the MT output is? Traditionally, BLEU has been the “go to”, as it is simple to use across language pairs. However, it is overly simplistic, evaluating string matches to a single reference translation. More sophisticated metrics […]

June 18, 2020 Levenshtein Transformer, NLP Leave a comment

Issue #86 – Neural MT with Levenshtein Transformer

18 Jun20 Issue #86 – Neural MT with Levenshtein Transformer Author: Dr. Patrik Lambert, Senior Machine Translation Scientist @ Iconic Introduction The standard Transformer model is autoregressive, meaning that the prediction of each target word is based on the predictions for the previous words. The output is generated from left to right, with no chance to revise a past decision and without considering future predictions of the words on the right of the current word. In a recent post (#82), […]

June 11, 2020 Neural MT, NLP Leave a comment

Issue #85 – Applying Terminology Constraints in Neural MT

11 Jun20 Issue #85 – Applying Terminology Constraints in Neural MT Author: Dr. Chao-Hong Liu, Machine Translation Scientist @ Iconic Introduction Maintaining consistency of terminology translation in Neural Machine Translation (NMT) is a more challenging task than in Statistical MT (SMT). In this post, we review a method proposed by Dinu et al. (2019) to train NMT to use custom terminology. Translation with Terminology Constraints Applying terminology constraints to translation may appear to be an easy task. It is a […]

June 4, 2020 Estimators of Quality, NLP Leave a comment

Issue #84 – Are Neural Machine Translation Systems Good Estimators of Quality?

04 Jun20 Issue #84 – Are Neural Machine Translation Systems Good Estimators of Quality? Author: Prof. Lucia Specia, Professor of Natural Language Processing, Imperial College London (also to ADAPT/Dublin City University and University of Sheffield) This week, we are delighted to have a guest post from Prof. Lucia Specia of Imperial College London, and laterally the University of Sheffield and our own alma mater, Dublin City University. Prof. Specia is one of the world’s preeminent experts on the topic of […]

May 14, 2020 Constrained Decoding, NLP Leave a comment

Issue #82 – Constrained Decoding using Levenshtein Transformer

14 May20 Issue #82 – Constrained Decoding using Levenshtein Transformer Author: Raj Patel, Machine Translation Scientist @ Iconic Introduction In constrained decoding, we force in-domain terminology to appear in the final translation. We have previously discussed constrained decoding in earlier blog posts (#7, #9, #79). In this blog post, we will discuss a simple and effective algorithm for incorporating lexical constraints in Neural Machine Translation (NMT) proposed by Susanto et al. (2020) and try to understand how it is better than […]

May 7, 2020 Human-Machine Parity, NLP Leave a comment

Issue #81 – Evaluating Human-Machine Parity in Language Translation: part 2

07 May20 Issue #81 – Evaluating Human-Machine Parity in Language Translation: part 2 Author: Dr. Sheila Castilho, Post-Doctoral Researcher @ ADAPT Research Centre This is the second in a 2-part post addressing machine translation quality evaluation – an overarching topic regardless of the underlying algorithms. Following our own summary last week, this week we are delighted to have one of the paper’s authors, Dr. Sheila Castilho, give her take on the paper, their motivations for writing it, and where we […]

« 1 … 909 910 911 912 913 … 916 »