Learning language through SHRDLURN game interaction, model accuracy improved by 8%.

Sida I. Wang, Percy Liang, Christopher D. Manning

Proposed a decomposable attention model achieving state-of-the-art results on SNLI with significantly fewer parameters.

Ankur P. Parikh, Oscar Täckström, Dipanjan Das et al.

Using deep reinforcement learning for dialogue generation, improving coherence and informativeness.

Jiwei Li, Will Monroe, Alan Ritter et al.

On Yelp restaurant reviews, TF-IDF unigrams+bigrams with logistic regression reached 64% validation accuracy; test accuracy was 54% with RMSE 0.92.

Nabiha Asghar

Introduces the 'Story Cloze Test' framework using ROCStories corpus, highlighting causal understanding; baseline models perform poorly (~60%), deep models reach 70%.

Nasrin Mostafazadeh, Nathanael Chambers, Xiaodong He et al.

Introduces bidirectional LSTM-CRF and transition-based models for NER, achieving state-of-the-art results without language-specific resources.

Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian et al.

Abstractive text summarization using sequence-to-sequence RNNs achieves state-of-the-art performance on two datasets.

Ramesh Nallapati, Bowen Zhou, Cicero Nogueira dos santos et al.

Introduces multiCluster and multiCCA methods for training multilingual embeddings across 59 languages, using dictionaries and monolingual data without parallel corpora.

Waleed Ammar, George Mulcaire, Yulia Tsvetkov et al.

Proposes Minimum Risk Training (MRT) for end-to-end neural machine translation, outperforming maximum likelihood estimation with up to +8.61 BLEU points.

Shiqi Shen, Yong Cheng, Zhongjun He et al.

Proposes PPDB-based universal paraphrastic sentence embeddings; simple models outperform LSTMs in cross-domain tasks.

John Wieting, Mohit Bansal, Kevin Gimpel et al.

Introducing BPE-based subword units for NMT, significantly improving rare word translation with 1.1-1.3 BLEU gains.

Rico Sennrich, Barry Haddow, Alexandra Birch

Character CNN combined with highway networks and LSTM achieves comparable performance to state-of-the-art with 60% fewer parameters, excelling across multiple languages.

Yoon Kim, Yacine Jernite, David Sontag et al.

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.