ICLR15, Neural Machine Translation by Jointly Learning to Align and Translate , Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio.

ACL15, Encoding Source Language with Convolutional Neural Network for Machine Translation , Fandong Meng, Zhengdong Lu, Mingxuan Wang, Hang Li, Wenbin Jiang, Qun Liu

ACL15, A Hierarchical Neural Autoencoder for Paragraphs and Documents , Jiwei Li, Minh-Thang Luong, Dan Jurafsky

EMNLP15, A Neural Attention Model for Sentence Summarization, Alexander M. Rush, Sumit Chopra and Jason Weston

EMNLP15 short, Not All Contexts Are Created Equal: Better Word Representations with Variable Attention6, Wang Ling.

NAACL15 , Two/Too Simple Adaptations of Word2Vec for Syntax Problems

NIPS14, Volodymyr Mnih, Nicolas Heess, Alex Graves, Koray Kavukcuoglu. Recurrent Models of Visual Attention.

ICLR15, Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio. Neural Machine Translation by Jointly Learning to Align and Translate.

ACL15, Fandong Meng, Zhengdong Lu, Mingxuan Wang, et al. Encoding Source Language with Convolutional Neural Network for Machine Translation.

ACL15, Jiwei Li, Minh-Thang Luong, Dan Jurafsky. A Hierarchical Neural Autoencoder for Paragraphs and Documents.

EMNLP15, Alexander M. Rush, Sumit Chopra, Jason Weston. A Neural Attention Model for Sentence Summarization.

EMNLP15, Wang Ling, Lin Chu-Cheng, Yulia Tsvetkov, et al. Not All Contexts Are Created Equal: Better Word Representations with Variable Attention

End-to-End Attention-based Large Vocabulary Speech Recognition

NIPS14 ws, End-to-end Continuous Speech Recognition using Attention-based Recurrent NN: First Results http://arxiv.org/abs/1412.1602

NIPS15, Attention-Based Models for Speech Recognition

EMNLP15, Effective Approaches to Attention-based Neural Machine Translation

ICML15, Kelvin Xu, Jimmy Ba, Ryan Kiros, et al. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention.

Karol Gregor, Ivo Danihelka, Alex Graves, et al. DRAW: A Recurrent Neural Network For Image Generation.

NIPS15, Karl Moritz Hermann, Tomáš Kočiský, Edward Grefenstette, et al. Teaching Machines to Read and Comprehend.

NIPS15, Lei Jimmy Ba, Roger Grosse, Ruslan Salakhutdinov, Brendan Frey. Learning Wake-Sleep Recurrent Attention Models.

DSSM

Learning deep structured semantic models for web search using clickthrough data, cikm2013 Paper code1 code2

CDSSM
A latent semantic model with convolutional-pooling structure for information retrieval, msr, CIKM2014

ARC-I
convolutional neural network architectures for matching natural language sentences, NIPS2014

ARC-II
convolutional neural network architectures for matching natural language sentences, NIPS2014

RAE
Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection, NIPS2011

Deep Match
A deep architecture for matching short texts, NIPS,2013

CNTN
Convolutional Neural Tensor Network Architecture for Community-based Question Answering, IJCAI2015

CNNPI
convolutional neural network for paraphrase identification, NAACL2015

MultiGranCNN
MultiGranCNN: An architecture for general matching of text chunks on multiple levels of granularity, ACL2015

CLSTM
Contextual LSTM (CLSTM) models for Large scale NLP tasks, Google, Arxiv201602

CLSM
A latent semantic model with convolutional-pooling structure for information retrieval, cikm2014

Recurrent-DSSM
Palangi, H., Deng, L., Shen, Y., Gao, J., He, X., Chen, J., Song, X., and Ward, R. Learning sequential semantic representations of natural language using recurrent neural networks. In ICASSP, 2015.

LSTM-DSSM
SEMANTIC MODELLING WITH LONG-SHORT-TERM MEMORY FOR INFORMATION RETRIEVAL,ICLR2016, workshop

DCNN: Dynamic convolutional neural network
a convolutional neural network for modeling sentences, acl2014 convolutional neural network architectures for matching natural language sentences, nips2014, noah

BRAE: bilingually-constrained recursive auto-encoders
bilingually-constrained phrase embeddings for machine translation, acl2014, long paper

LSTM-RNN
Deep sentence embedding using lstm networks: analysis and application to information retrieval, 201602

SkipThought
Skip thought vectors,

Bidirectional LSTM-RNN
Bi-directional LSTM Recurrent Neural Network for Chinese Word Segmentation, 201602, Arxiv

MV-DNN
A multi-view deep learning approach for cross domain user modeling in recommendation systems, WWW2015