Introduced global and local attention mechanisms, improving English-German translation by 5.0 BLEU points.

Minh-Thang Luong, Hieu Pham, Christopher D. Manning

Compositional training for TransE and bilinear models cuts path-query error by up to 76.2% and improves KBC.

Kelvin Guu, John Miller, Percy Liang

Proposes a hybrid deep learning and rule-based approach for text-to-3D scene generation, achieving significant improvements in scene fidelity and diversity, with a new dataset and evaluation metrics.

Angel Chang, Will Monroe, Manolis Savva et al.

Proposes a deep multi-layer LSTM-based end-to-end sequence-to-sequence model achieving BLEU 34.8 on WMT'14 English-French translation, outperforming phrase-based SMT.

Ilya Sutskever, Oriol Vinyals, Quoc V. Le

Introduces a neural machine translation model with joint alignment and translation via attention, achieving BLEU 28.45 on WMT’14 English-French.

Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio

Introduces SimLex-999, a gold standard for semantic similarity, covering multiple POS and abstract/concrete concepts, outperforming WordSim-353 and MEN.

Felix Hill, Roi Reichart, Anna Korhonen

Turney’s dual-space model unifies analogy and composition through domain/function cosine similarities; the supplied text omits numerical scores.

Peter D. Turney

Introduces a Linearized Phrase Structure model to improve semantic orientation detection in financial texts.

Pekka Malo, Ankur Sinha, Pyry Takala et al.

Proposes two efficient models—CBOW and Skip-gram—for large-scale word embedding training, achieving 53.3% accuracy on semantic-syntactic tasks within 3 days on 1.6B words.

Tomas Mikolov, Kai Chen, Greg Corrado et al.

Joint language-perception model using probabilistic grammar and classifiers significantly improves grounded attribute learning, achieving 82% precision in object set selection.

Cynthia Matuszek, Nicholas FitzGerald, Luke Zettlemoyer et al.