Although neural machine translation (NMT) with the encoder-decoder framework has achieved great success in recent times, it still suffers from some drawbacks: RNNs tend to forget old information which is often useful and the encoder only operates through words without considering word relationship. To solve these problems, we introduce a relation networks (RN) into NMT to refine the encoding representations of the source. In our method, the RN first augments the representation of each source word with its neighbors and reasons all the possible pairwise relations between them. Then the source representations and all the relations are fed to the attention module and the decoder together, keeping the main encoder-decoder architecture unchanged. Experiments on two Chinese-to-English data sets in different scales both show that our method can outperform the competitive baselines significantly.

NVIDIA (NASDAQ:NVDA) recently reported powerful fiscal first-quarter 2018 results. The graphics processing unit (GPU) specialist's revenue jumped 66%, GAAP earnings per share soared 151%, and adjusted EPS surged 141%. There was a wealth of information about the company's results and future prospects shared on the earnings call. Our focus here is on NVIDIA's data center, which is growing like gangbusters -- its revenue grew 71% year over year to $701 million in the quarter, accounting for 22% of the company's total revenue. We see the data center opportunity as very large, fueled by growing demand for accelerated computing and applications ranging from AI [artificial intelligence] to high-performance computing across multiple market segments and vertical industries.

Avi Goldfarb, a professor at the University of Toronto's Rotman School of Management, explains the economics of machine learning, a branch of artificial intelligence that makes predictions. He says as prediction gets cheaper and better, machines are going to be doing more of it. That means businesses -- and individual workers -- need to figure out how to take advantage of the technology to stay competitive. Goldfarb is the coauthor of the book Prediction Machines: The Simple Economics of Artificial Intelligence. CURT NICKISCH: Welcome to the HBR IdeaCast, from Harvard Business Review. YOUTUBE: [Two women speaking] We've got this all tabbed up? In it, three young English-speaking women use Google Translate to order food in Hindi from an Indian restaurant. They copy and paste their order in English into the computer, and it translates items like "samosas" and reads them aloud in the foreign language.

NVIDIA (NASDAQ: NVDA) recently reported powerful fiscal first-quarter 2018 results. The graphics processing unit (GPU) specialist's revenue jumped 66%, GAAP earnings per share soared 151%, and adjusted EPS surged 141%. There was a wealth of information about the company's results and future prospects shared on the earnings call. Our focus here is on NVIDIA's data center, which is growing like gangbusters -- its revenue grew 71% year over year to $701 million in the quarter, accounting for 22% of the company's total revenue. We see the data center opportunity as very large, fueled by growing demand for accelerated computing and applications ranging from AI [artificial intelligence] to high-performance computing across multiple market segments and vertical industries.

Recent work has managed to learn cross-lingual word embeddings without parallel data by mapping monolingual embeddings to a shared space through adversarial training. However, their evaluation has focused on favorable conditions, using comparable corpora or closely-related languages, and we show that they often fail in more realistic scenarios. This work proposes an alternative approach based on a fully unsupervised initialization that explicitly exploits the structural similarity of the embeddings, and a robust self-learning algorithm that iteratively improves this solution. Our method succeeds in all tested scenarios and obtains the best published results in standard datasets, even surpassing previous supervised systems. Our implementation is released as an open source project at https://github.com/artetxem/vecmap

In the closing weeks of 2016, Google published an article that quietly sailed under most people's radars. Which is a shame, because it may just be the most astonishing article about machine learning that I read last year. Don't feel bad if you missed it. Not only was the article competing with the pre-Christmas rush that most of us were navigating -- it was also tucked away on Google's Research Blog, beneath the geektastic headline Zero-Shot Translation with Google's Multilingual Neural Machine Translation System. This doesn't exactly scream must read, does it?

We present a paper abstract writing system based on an attentive neural sequence-to-sequence model that can take a title as input and automatically generate an abstract. We design a novel Writing-editing Network that can attend to both the title and the previously generated abstract drafts and then iteratively revise and polish the abstract. With two series of Turing tests, where the human judges are asked to distinguish the system-generated abstracts from human-written ones, our system passes Turing tests by junior domain experts at a rate up to 30% and by non-expert at a rate up to 80%.

Over the past years, distributed representations have proven effective and flexible keepers of prior knowledge to be integrated into downstream applications. This survey is focused on semantic representation of meaning. We start from the theoretical background behind word vector space models and highlight one of their main limitations: the meaning conflation deficiency, which arises from representing a word with all its possible meanings as a single vector. Then, we explain how this deficiency can be addressed through a transition from word level to the more fine-grained level of word senses (in its broader acceptation) as a method for modelling unambiguous lexical meaning. We present a comprehensive overview of the wide range of techniques in the two main branches of sense representation, i.e., unsupervised and knowledge-based. Finally, this survey covers the main evaluation procedures and provides an analysis of five important aspects: interpretability, sense granularity, adaptability to different domains, compositionality and integration into downstream applications.

Neural Machine Translation (NMT) performs poor on the low-resource language pair $(X,Z)$, especially when $Z$ is a rare language. By introducing another rich language $Y$, we propose a novel triangular training architecture (TA-NMT) to leverage bilingual data $(Y,Z)$ (may be small) and $(X,Y)$ (can be rich) to improve the translation performance of low-resource pairs. In this triangular architecture, $Z$ is taken as the intermediate latent variable, and translation models of $Z$ are jointly optimized with a unified bidirectional EM algorithm under the goal of maximizing the translation likelihood of $(X,Y)$. Empirical results demonstrate that our method significantly improves the translation quality of rare languages on MultiUN and IWSLT2012 datasets, and achieves even better performance combining back-translation methods.

What do linguists make of AI and natural language processing (NLP)? Do they see a bright future for their careers with AI, or worry about being replaced by it entirely? To find out, Locaria ran a survey with 150 participating linguists from across the globe. The survey was a combination of questions that required them to select from a list of answers, or give their view in their own words. An essential part of the survey saw each linguist describe their feelings towards AI, NLP, and machine translation.