Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in conventional NMT systems is their inability to correctly translate very rare words: end-to-end NMTs tend to have relatively small vocabularies with a single unk symbol that represents every possible out-of-vocabulary (OOV) word. In this paper, we propose and implement an effective technique to address this problem. We train an NMT system on data that is augmented by the output of a word alignment algorithm, allowing the NMT system to emit, for each OOV word in the target sentence, the position of its corresponding word in the source sentence. This information is later utilized in a post-processing step that translates every OOV word using a dictionary. Our experiments on the WMT'14 English to French translation task show that this method provides a substantial improvement of up to 2.8 BLEU points over an equivalent NMT system that does not use this technique. With 37.5 BLEU points, our NMT system is the first to surpass the best result achieved on a WMT'14 contest task.

Recent work in learning bilingual representations tend to tailor towards achieving good performance on bilingual tasks, most often the crosslingual document classification (CLDC) evaluation, but to the detriment of preserving clustering structures of word representations monolingually.In this work, we propose a joint model to learn word representations from scratch that utilizes both the context coocurrence information through the monolingual component and the meaning equivalent signals from the bilingual constraint. Specifically, we extend the recently popular skipgram model to learn high quality bilingual representations efficiently. Our learned embeddings achieve a new state-of-the-art accuracy of 80.3 for the German to English CLDC task and a highly competitive performance of 90.7 for the other classification direction. At the same time, our models outperform best embeddings from past bilingual representation work by a large margin in the monolingual word similarity evaluation. 1

Natural language generation of coherent long texts like paragraphs or longer documents is a challenging problem for recurrent networks models. In this paper, we explore an important step toward this generation task: training an LSTM (Longshort term memory) auto-encoder to preserve and reconstruct multi-sentence paragraphs. We introduce an LSTM model that hierarchically builds an embedding for a paragraph from embeddings for sentences and words, then decodes this embedding to reconstruct the original paragraph. We evaluate the reconstructed paragraph using standard metrics like ROUGE and Entity Grid, showing that neural models are able to encode texts in a way that preserve syntactic, semantic, and discourse coherence. While only a first step toward generating coherent text units from neural models, our work has the potential to significantly impact natural language generation and summarization 1 .

Recursive neural models, which use syntactic parse trees to recursively generate representations bottom-up, are a popular architecture. But there have not been rigorous evaluations showing for exactly which tasks this syntax-based method is appropriate. In this paper we benchmark recursive neural models against sequential recurrent neural models (simple recurrent and LSTM models), enforcing apples-to-apples comparison as much as possible. We investigate 4 tasks: (1) sentiment classification at the sentence level and phrase level; (2) matching questions to answer-phrases; (3) discourse parsing; (4) semantic relation extraction (e.g., component-whole between nouns).Our goal is to understand better when, and why, recursive models can outperform simpler models. We find that recursive models help mainly on tasks (like semantic relation extraction) that require associating headwords across a long distance, particularly on very long sequences. We then introduce a method for allowing recurrent models to achieve similar performance: breaking long sentences into clause-like units at punctuation and processing them separately before combining. Our results thus help understand the limitations of both classes of models, and suggest directions for improving recurrent models.

We propose a novel approach to learning distributed representations of variable-length text sequences in multiple languages simultaneously. Unlike previous work which often derive representations of multi-word sequences as weighted sums of individual word vectors, our model learns distributed representations for phrases and sentences as a whole. Our work is similar in spirit to the recent paragraph vector approach but extends to the bilingual context so as to efficiently encode meaning-equivalent text sequences of multiple languages in the same semantic space. Our learned embeddings achieve state-of-theart performance in the often used crosslingual document classification task (CLDC) with an accuracy of 92.7 for English to German and 91.5 for German to English. By learning text sequence representations as a whole, our model performs equally well in both classification directions in the CLDC task in which past work did not achieve.