In this paper, we investigate the problem of learning a machine translation model that can simultaneously translate sentences from one source language to multiple target languages. Our solution is inspired by the recently proposed neural machine translation model which generalizes machine translation as a sequence learning problem. We extend the neural machine translation to a multi-task learning framework which shares source language representation and separates the modeling of different target language translation. Our framework can be applied to situations where either large amounts of parallel data or limited parallel data is available. Experiments show that our multi-task learning model is able to achieve significantly higher translation quality over individually learned model in both situations on the data sets publicly available.

Semantic hierarchy construction aims to build structures of concepts linked by hypernym-hyponym ("is-a") relations. A major challenge for this task is the automatic discovery of such relations. This paper proposes a novel and effective method for the construction of semantic hierarchies based on word embeddings, which can be used to measure the semantic relationship between words. We identify whether a candidate word pair has hypernym-hyponym relation by using the word-embedding-based semantic projections between words and their hypernyms. Our result, an F-score of 73.74%, outperforms the state-of-theart methods on a manually labeled test dataset. Moreover, combining our method with a previous manually-built hierarchy extension method can further improve Fscore to 80.29%.

This paper investigates the problem of cross-lingual dependency parsing, aiming at inducing dependency parsers for low-resource languages while using only training data from a resource-rich language (e.g. English). Existing approaches typically don't include lexical features, which are not transferable across languages. In this paper, we bridge the lexical feature gap by using distributed feature representations and their composition. We provide two algorithms for inducing cross-lingual distributed representations of words, which map vocabularies from two different languages into a common vector space. Consequently, both lexical features and non-lexical features can be used in our model for cross-lingual transfer. Furthermore, our framework is able to incorporate additional useful features such as cross-lingual word clusters. Our combined contributions achieve an average relative error reduction of 10.9% in labeled attachment score as compared with the delexicalized parser, trained on English universal treebank and transferred to three other languages. It also significantly outperforms McDonald et al. (2013) augmented with projected cluster features on identical data.

This paper proposes a novel method for phrase-based statistical machine translation based on the use of a pivot language. To translate between languages L s and L t with limited bilingual resources, we bring in a third language, L p , called the pivot language. For the language pairs L s − L p and L p − L t , there exist large bilingual corpora. Using only L s − L p and L p − L t bilingual corpora, we can build a translation model for L s − L t . The advantage of this method lies in the fact that we can perform translation between L s and L t even if there is no bilingual corpus available for this language pair. Using BLEU as a metric, our pivot language approach significantly outperforms the standard model trained on a small bilingual corpus. Moreover, with a small L s − L t bilingual corpus available, our method can further improve translation quality by using the additional L s − L p and L p − L t bilingual corpora.

Recent work has shown success in using continuous word embeddings learned from unlabeled data as features to improve supervised NLP systems, which is regarded as a simple semi-supervised learning mechanism. However, fundamental problems on effectively incorporating the word embedding features within the framework of linear models remain. In this study, we investigate and analyze three different approaches, including a new proposed distributional prototype approach, for utilizing the embedding features. The presented approaches can be integrated into most of the classical linear models in NLP. Experiments on the task of named entity recognition show that each of the proposed approaches can better utilize the word embedding features, among which the distributional prototype approach performs the best. Moreover, the combination of the approaches provides additive improvements, outperforming the dense and continuous embedding features by nearly 2 points of F1 score.