“Reading table”版本间的差异

来自cslt Wiki
跳转至: 导航搜索
 
(15位用户的181个中间修订版本未显示)
第5行: 第5行:
 
| rowspan="1"|2014/10/22  ||Zhang Dong Xu|| Why RNN? [[媒体文件:Why_LSTM.pdf|PPT]] [[媒体文件:Learning_Long-Term_Dependencies_with_Gradient_Descent_is_Difficult.pdf|paper 1]],[[媒体文件:LongShortTermMemory.pdf|paper  2]]
 
| rowspan="1"|2014/10/22  ||Zhang Dong Xu|| Why RNN? [[媒体文件:Why_LSTM.pdf|PPT]] [[媒体文件:Learning_Long-Term_Dependencies_with_Gradient_Descent_is_Difficult.pdf|paper 1]],[[媒体文件:LongShortTermMemory.pdf|paper  2]]
 
|-
 
|-
| rowspan="3"| 2014/12/8 || rowspan='3'|Liu Rong || Yu Zhao, Zhiyuan Liu, Maosong Sun. Phrase Type Sensitive Tensor Indexing Model for Semantic Composition. The 29th AAAI Conference on Artificial Intelligence (AAAI'15). [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_tim.pdf pdf]
+
| rowspan="3"| 2014/12/8 || rowspan='3'|Liu Rong || Yu Zhao, Zhiyuan Liu, Maosong Sun. Phrase Type Sensitive Tensor Indexing Model for Semantic Composition. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_tim.pdf pdf]
 
|-
 
|-
| Yang Liu, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun. Topical Word Embeddings. The 29th AAAI Conference on Artificial Intelligence (AAAI'15).  
+
| Yang Liu, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun. Topical Word Embeddings. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_twe.pdf pdf][https://github.com/largelymfs/topical_word_embeddings code]
[http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_twe.pdf pdf][https://github.com/largelymfs/topical_word_embeddings code]
+
 
|-
 
|-
|  Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu. Learning Entity and Relation Embeddings for Knowledge Graph Completion. The 29th AAAI Conference on Artificial Intelligence (AAAI'15). [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf pdf][https://github.com/mrlyk423/relation_extraction code]
+
|  Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu. Learning Entity and Relation Embeddings for Knowledge Graph Completion. AAAI'15. [http://nlp.csai.tsinghua.edu.cn/~lzy/publications/aaai2015_transr.pdf pdf][https://github.com/mrlyk423/relation_extraction code]
 +
 
 
|-
 
|-
 +
|2015/07/10 ||Liu Rong||
 +
*Context-Dependent Translation Selection Using Convolutional Neural Network [http://arxiv.org/abs/1503.02357]
 +
*Syntax-based Deep Matching of Short Texts [http://arxiv.org/abs/1503.02427]
 +
*Convolutional Neural Network Architectures for Matching Natural Language Sentences[http://www.hangli-hl.com/uploads/3/1/6/8/3168008/hu-etal-nips2014.pdf]
 +
*LSTM: A Search Space Odyssey [http://arxiv.org/pdf/1503.04069.pdf]
 +
*A Deep Embedding Model for Co-occurrence Learning  [http://arxiv.org/abs/1504.02824]
 +
*Text segmentation based on semantic word embeddings[http://arxiv.org/abs/1503.05543]
 +
*semantic parsing via paraphrashings[http://www.cs.tau.ac.il/research/jonathan.berant/homepage_files/publications/ACL14.pdf]
 +
|-
 +
|-
 +
|2015/07/22 ||Dong Wang||
 +
*From Word Embeddings To Document Distances [http://jmlr.org/proceedings/papers/v37/kusnerb15.pdf pdf]
 +
*[[Asr-read-icml|Reading list for ICML2015]]
 +
|-
 +
|2015/07/29 ||Xiaoxi Wang||
 +
* Sequence to Sequence Learning with Neural Networks [http://papers.nips.cc/paper/5346-information-based-learning-by-agents-in-unbounded-state-spaces pdf]
 +
* Neural Machine Translation by Jointly Learning to Align and Translate [http://arxiv.org/abs/1409.0473 pdf]
 +
|-
 +
|2015/08/05 ||Tianyi Luo||
 +
* A Hierarchical Knowledge Representation for Expert Finding on Social Media(ACL 2015 short paper) [[http://aclanthology.info/papers/a-hierarchical-knowledge-representation-for-expert-finding-on-social-media pdf]]
 +
|-
 +
|2015/08/05 ||Dongxu Zhang||
 +
* Describing Multimedia Content using Attention-based Encoder-Decoder Networks[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/e/e0/Describing_Multimedia_Content_using_Attention-based_Encoder-Decoder_Networks.pdf]
 +
* Attention-Based Models for Speech Recognition[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/58/Attention-Based_Models_for_Speech_Recognition.pdf] details in speech recognition.
 +
* Neural Machine Translation by Joint Learning to Align and Translate[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c3/Neural_Machine_Translation_by_Joint_Learning_to_Align_and_Translate.pdf] details in machine translation.
 +
|-
 +
|2015/08/07 ||Chao Xing||
 +
* Neural Word Embedding as Implicit Matrix Factorization [[http://papers.nips.cc/paper/5477-neural-word-embedding-as-implicit-matrix-factorization.pdf pdf]]
 +
* Matrix factorization techniques for recommender systems [[http://www.columbia.edu/~jwp2128/Teaching/W4721/papers/ieeecomputer.pdf]]
 +
|-
 +
|2015/10/14 ||Tianyi Luo, Dongxu Zhang, Chao Xing||
 +
* MEMORY NETWORKS(ICLR 2015) [[http://arxiv.org/pdf/1410.3916v10.pdf pdf]]
 +
* End-To-End Memory Networks(NIPS 2015) [[http://arxiv.org/pdf/1503.08895v4.pdf pdf]]
 +
|-
 +
|2015/10/20 ||Tianyi Luo, Xiaoxi Wang||
 +
* The Kendall and Mallows Kernels for Permutations (ICML 2015) [[http://jmlr.csail.mit.edu/proceedings/papers/v37/jiao15.pdf pdf]]
 +
* The ordering of expression among a few genes can provide simple cancer biomarkers and signal BRCA1 mutations (BMC Bioinformatics) [[http://www.biomedcentral.com/content/pdf/1471-2105-10-256.pdf pdf]]
 +
* Reasoning about Entailment with Neural Attention [[http://arxiv.org/pdf/1509.06664v1.pdf pdf]]
 +
|-
 +
|2015/10/28 ||Lantian Li||
 +
* Binary Code Ranking with Weighted Hamming Distance [[http://www.cv-foundation.org/openaccess/content_cvpr_2013/papers/Zhang_Binary_Code_Ranking_2013_CVPR_paper.pdf pdf]]
 +
|-
 +
|2015/11/05 || Chao Xing, Xiaoxi Wang||
 +
* Generative Image Modeling Using Spatial LSTMs [[http://arxiv.org/pdf/1506.03478v2.pdf pdf]]
 +
* Character-level Convolutional Networks for Text Classification [[http://arxiv.org/pdf/1509.01626.pdf pdf]]
 +
|-
 +
|2015/11/20 || qixinWang||
 +
* Are You Talking to a Machine? [[http://arxiv.org/pdf/1505.05612v3.pdf pdf]]
 +
* m-RNN [[http://arxiv.org/pdf/1412.6632v5.pdf pdf]]
 +
* PresentationPPT [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/93/PresentationPaper--QixinWang20151120.pdf pdf]]
 +
|-
 +
|2015/11/27 || Xiaoxi Wang||
 +
* NEURAL PROGRAMMER-INTERPRETERS [[http://arxiv.org/pdf/1511.06279v2.pdf pdf]]
 +
* Subset Selection by Pareto Optimization [[http://www.researchgate.net/profile/Yang_Yu87/publication/282632653_Subset_Selection_by_Pareto_Optimization/links/561495d908aed47facee68b5.pdf pdf]]
 +
|-
 +
|-
 +
|2015/11/27 || Chao Xing ||
 +
*Random Walks and Neural Network Language Models [[http://www.aclweb.org/anthology/N15-1165 pdf]]
 +
*SENSEMBED: Learning Sense Embeddings forWord and Relational Similarity[[http://wwwusers.di.uniroma1.it/~navigli/pubs/ACL_2015_Iacobaccietal.pdf pdf]]
 +
|-
 +
|-
 +
|2015/12/4 || Dongxu Zhang, Qixin Wang, Chao Xing ||
 +
*Building a shared world: Mapping distributional to model-theoretic semantic spaces[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/da/Building_a_shared_world.pdf pdf]]
 +
*Playing Atari with Deep Reinforcement Learning[[http://arxiv.org/pdf/1312.5602v1.pdf pdf]]
 +
*Word Embedding Revisited A New Representation Learning and Explicit Matrix Factorization Perspective [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/45/Report-1.pdf pdf]]
 +
|-
 +
|-
 +
|2015/12/11 || Chao Xing, Yiqiao Pan ||
 +
*Semi-Supervised Word Sense Disambiguation Using Word Embeddings in General and Specific Domains [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/57/Report-12-11-02.pdf pdf]]
 +
*SENSE2VEC - A FAST AND ACCURATE METHOD FOR WORD SENSE DISAMBIGUATION IN NEURAL WORD EMBEDDINGS [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f0/Report-12-11-03.pdf pdf]]
 +
*Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space[[http://arxiv.org/pdf/1504.06654v1.pdf pdf]]
 +
*Distributional Semantics in Use[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/97/Report-12-11-01.pdf pdf]]
 +
|-
 +
|-
 +
|2015/12/18 || Tianyi Luo, Dongxu Zhang ||
 +
*Human-level concept learning through probabilistic program induction(Cognitive Science) [[http://cdn1.almosthuman.cn/wp-content/uploads/2015/12/Human-level-concept-learning-through-probabilistic-program-induction.pdf pdf]]
 +
*Cluster Analysis of Heterogeneous Rank Data(ICML 2007) [[http://machinelearning.wustl.edu/mlpapers/paper_files/icml2007_BusseOB07.pdf pdf]]
 +
*Building a shared world: Mapping distributional to model-theoretic semantic spaces[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/da/Building_a_shared_world.pdf pdf]]
 +
|-
 +
|-
 +
|2015/12/25 || Dongxu zhang, Qixin Wang ||
 +
*Exploiting Multiple Sources for Open-domain Hypernym Discovery[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/d1/Exploiting_Multiple_Sources_for_Open-domain_Hypernym_Discovery.pdf]]
 +
*learning semantic hierarchies via word embeddings[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/4f/Learning_semantic_hierarchies_via_word_embeddings_acl2014.pdf]]
 +
|-
 +
|-
 +
|2015/12/31 || Xiaoxi Wang, Chao Xing||
 +
* Multilingual Language Processing From Bytes [[http://arxiv.org/pdf/1512.00103v1.pdf pdf]]
 +
* Towards universal neural nets: Gibbs machines and ACE. [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/3b/Report-12-31.pdf pdf]]
 +
|-
 +
|-
 +
|2016/1/8 || Qixin Wang, Tianyi Luo||
 +
*Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a1/Unveiling_the_Dreams_of_Word_Embeddings-_Towards_Language-Driven_Image_Generation.pdf pdf]]
 +
*Generating Chinese Couplets using a Statistical MT Approach[[http://aclweb.org/anthology/C/C08/C08-1048.pdf pdf]]
 +
*Generating Chinese Classical Poems with Statistical Machine Translation Models[[http://www.aaai.org/ocs/index.php/AAAI/AAAI12/paper/viewFile/4753/5314 pdf]]
 +
*Chinese Poetry Generation with Recurrent Neural Networks[[http://www.aclweb.org/old_anthology/D/D14/D14-1074.pdf pdf]]
 +
|-
 +
|2016/1/15 || Chao Xing||
 +
*Learning from Chris Dyer [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/cd/Learning_From_Chris_Dyer.pptx ppt]]
 +
*Learning Word Representations with Hierarchical Sparse Coding [[http://arxiv.org/pdf/1406.2035v2.pdf pdf]]
 +
*Non-distributional Word Vector Representations [[http://www.cs.cmu.edu/~mfaruqui/papers/acl15-nondist.pdf pdf]]
 +
*Sparse Overcomplete Word Vector Representations [[http://www.cs.cmu.edu/~mfaruqui/papers/acl15-overcomplete.pdf pdf]]
 +
|-
 +
|2016/1/22 || Qixin Wang, Tianyi Luo||
 +
*Skip_thought_vector [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/aa/Skip_thought_vector.pdf pdf]]
 +
|-
 +
|2016/1/29 || Dongxu Zhang||
 +
*Towards Neural Network-based Reasoning[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/cb/Towards_Neural_Network-based_Reasoning.pdf]]
 +
|-
 +
|2016/3/25 || Jiyuan Zhang||
 +
*Modeling Temporal Dependencies in High-Dimensional Sequences:Application to Polyphonic Music Generation and Transcription[[http://www-etud.iro.umontreal.ca/~boulanni/ICML2012.pdf pdf]]
 +
*Composing Music With Recurrent Neural Networks[[http://www.hexahedria.com/2015/08/03/composing-music-with-recurrent-neural-networks/  blog]]
 +
|-
 +
|2016/4/1 || Chao Xing||
 +
*Generating Text with Deep Reinforcement Learning[[http://arxiv.org/pdf/1510.09202v1.pdf pdf]]
 +
|-
 +
|2016/4/8 || Tianyi Luo||
 +
*Generating Chinese Classical Poems with RNN[[http://nlp.hivefire.com/articles/share/56982/]]
 +
|-
 +
|2016/4/28 || Chao Xing||
 +
*Knowledge Base Completion via Search-Based Question Answering [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b1/Knowledge_Base_Completion_via_Search-Based_Question_Answering_-_Report.pdf]]
 +
*Open Domain Question Answering via Semantic Enrichment [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/15/Open_Domain_Question_Answering_via_Semantic_Enrichment_-_Report.pdf]]
 +
*A Neural Conversational Model [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/15/A_Neural_Conversational_Model_-_Report.pdf]]
 +
|-
 +
|2016/5/11 || Chao Xing||
 +
*A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion
 +
*A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
 +
*Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
 +
*Neural Responding Machine for Short-Text Conversation
 +
*Learning from Real Users Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
 +
|-
 +
|2016/7/28 || Aiting Liu ||
 +
*Intrinsic Subspace Evaluation of Word Embedding Representations    [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/68/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/1/17/Intrinsic_Subspace_Evaluation_of_Word_Embedding_Representations.pptx slides]]
 +
|-
 +
|2016/8/4 ||
 +
* Aodong Li
 +
* Jiyuan Zhang
 +
* Andi Zhang
 +
||
 +
*On the Role of Seed Lexicons in Learning Bilingual Word Embeddings  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5b/On_the_Role_of_Seed_Lexicons_in_Learning_Bilingual_Word_Embeddings.pdf pdf]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/51/2.0On_the_Role_of_Seed_Lexicons_in_Learning_Bilingual_Word_Embeddings_.pdf slides]]
 +
*ABCNN- Attention-Based Convolutional Neural Network for Modeling Sentence Pairs
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/7/76/ABCNN-_Attention-Based_Convolutional_Neural_Network_for_Modeling_Sentence_Pairs_.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/0d/Attention-Based_Convolutianal_Neural_Network_for_Modeling_Sentence_Pairs.pptx slides]]
 +
*[[Tutorial]]: Introduction to different LMs: NNLM, RNNLM, continuous bag of words, skip-gram
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/d/da/Models_for_computing_continuous_vector_representations_of_words.pdf slides]]
 +
|-
 +
|2016/8/18 ||
 +
* Shiyao Li
 +
* Aiting Liu
 +
||
 +
*Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/a/a4/Multilingual_part-of-speech_tagging_with_bidirectional_long_short-term_memory_models_and_auxiliary_loss.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c5/Multilingual_Part-of-Speech_Tagging_with.pdf slides]]
 +
*A Sentence Interaction Network for Modeling Dependence between Sentences
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/04/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/6/6c/A_Sentence_Interaction_Network_for_Modeling_Dependence_between_Sentences.pptx slides]]
 +
|-
 +
|2016/8/25 ||
 +
* Ziwei Bai
 +
||
 +
*[[Tutorial]]: Tensorflow guidelines and some examples
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/32/Tensor_flow_bai.pdf slides]]
 +
|-
 +
|2016/8/26 ||
 +
* Jiyuan Zhang
 +
* Shiyao Li
 +
||
 +
*[[Tutorial]]: Introduction to GRU, LSTM, RBM [[http://cslt.riit.tsinghua.edu.cn/mediawiki/index.php/%E6%96%87%E4%BB%B6:An_overview_of_LSTM,GRU,RBM.pptx slides]]
 +
* [[Tutorial]] : Linear Algebra, Probability and Information Basics
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f1/LinearAlgebra.pdf LinearAlgebra]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/9/97/ProbilityTheoryandInformationTheory.pdf ProbabilityAndInformationTheory]]
 +
|-
 +
|2016/9/9 ||
 +
* Aodong Li
 +
||
 +
*Pointing the Unknown Words [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/c/c7/Pointing_the_Unknown_Words.pdf pdf]]
 +
|-
 +
|2016/9/18 ||
 +
* Andy Zhang
 +
*Shiyao Li
 +
*Aodong Li
 +
||
 +
*Large-Scale Information Extraction from Textual Definitions through Deep Syntactic and Semantic Analysis  [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/0/04/Large-Scale_Information_Extraction_from_Textual_Definitions_through_Deep_Syntactic_and_Semantic_Analysis.pdf pdf]][[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/8/80/Large-scale_information_extraction_from_textual_definitions_through_deep_syntactic_and_semantic_analysis.pdf slides]]
 +
*Finding the Middle Ground - A Model for Planning Satisficing Answers [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b3/Finding_the_Middle_Ground_-_A_Model_for_Planning_Satisficing_Answers.pdf pdf]]
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/4/44/Finding_the_Middle_Ground.pdf slides]]
 +
*Compressing Neural Language Models by Sparse Word Representations [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/b6/Compressing_Neural_Language_Models_by_Sparse_Word_Representations.pdf pdf]]
 +
|-
 +
|2016/9/30 ||
 +
* Jiyuan Zhang
 +
*Shiyue Zhang
 +
||
 +
*On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/fa/On-line_Active_Reward_Learning_for_Policy_Optimisation_in_Spoken_Dialogue_Systems.pdf pdf]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bb/On-line_Active_Reward.pdf slides]]
 +
*Stack-propagation: Improved Representation Learning for Syntax
 +
[[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bf/Stack-propagation-_Improved_Representation_Learning_for_Syntax.pdf pdf]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/5/5d/Stack_propagation.pdf slides]]
 +
|-
 +
|2017/5/18 ||
 +
*Shiyue Zhang
 +
||
 +
*Convolutional Sequence to Sequence Learning [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f3/Conv_seq2seq.pptx slides]] [[http://cslt.riit.tsinghua.edu.cn/mediawiki/images/b/bb/Cnn_seq2seq.pdf pdf]]
 
|}
 
|}

2017年5月18日 (四) 02:51的最后版本

Date Speaker Materials
2014/10/22 Zhang Dong Xu Why RNN? PPT paper 1,paper 2
2014/12/8 Liu Rong Yu Zhao, Zhiyuan Liu, Maosong Sun. Phrase Type Sensitive Tensor Indexing Model for Semantic Composition. AAAI'15. pdf
Yang Liu, Zhiyuan Liu, Tat-Seng Chua, Maosong Sun. Topical Word Embeddings. AAAI'15. pdfcode
Yankai Lin, Zhiyuan Liu, Maosong Sun, Yang Liu, Xuan Zhu. Learning Entity and Relation Embeddings for Knowledge Graph Completion. AAAI'15. pdfcode
2015/07/10 Liu Rong
  • Context-Dependent Translation Selection Using Convolutional Neural Network [1]
  • Syntax-based Deep Matching of Short Texts [2]
  • Convolutional Neural Network Architectures for Matching Natural Language Sentences[3]
  • LSTM: A Search Space Odyssey [4]
  • A Deep Embedding Model for Co-occurrence Learning [5]
  • Text segmentation based on semantic word embeddings[6]
  • semantic parsing via paraphrashings[7]
2015/07/22 Dong Wang
2015/07/29 Xiaoxi Wang
  • Sequence to Sequence Learning with Neural Networks pdf
  • Neural Machine Translation by Jointly Learning to Align and Translate pdf
2015/08/05 Tianyi Luo
  • A Hierarchical Knowledge Representation for Expert Finding on Social Media(ACL 2015 short paper) [pdf]
2015/08/05 Dongxu Zhang
  • Describing Multimedia Content using Attention-based Encoder-Decoder Networks[8]
  • Attention-Based Models for Speech Recognition[9] details in speech recognition.
  • Neural Machine Translation by Joint Learning to Align and Translate[10] details in machine translation.
2015/08/07 Chao Xing
  • Neural Word Embedding as Implicit Matrix Factorization [pdf]
  • Matrix factorization techniques for recommender systems [[11]]
2015/10/14 Tianyi Luo, Dongxu Zhang, Chao Xing
  • MEMORY NETWORKS(ICLR 2015) [pdf]
  • End-To-End Memory Networks(NIPS 2015) [pdf]
2015/10/20 Tianyi Luo, Xiaoxi Wang
  • The Kendall and Mallows Kernels for Permutations (ICML 2015) [pdf]
  • The ordering of expression among a few genes can provide simple cancer biomarkers and signal BRCA1 mutations (BMC Bioinformatics) [pdf]
  • Reasoning about Entailment with Neural Attention [pdf]
2015/10/28 Lantian Li
  • Binary Code Ranking with Weighted Hamming Distance [pdf]
2015/11/05 Chao Xing, Xiaoxi Wang
  • Generative Image Modeling Using Spatial LSTMs [pdf]
  • Character-level Convolutional Networks for Text Classification [pdf]
2015/11/20 qixinWang
  • Are You Talking to a Machine? [pdf]
  • m-RNN [pdf]
  • PresentationPPT [pdf]
2015/11/27 Xiaoxi Wang
  • NEURAL PROGRAMMER-INTERPRETERS [pdf]
  • Subset Selection by Pareto Optimization [pdf]
2015/11/27 Chao Xing
  • Random Walks and Neural Network Language Models [pdf]
  • SENSEMBED: Learning Sense Embeddings forWord and Relational Similarity[pdf]
2015/12/4 Dongxu Zhang, Qixin Wang, Chao Xing
  • Building a shared world: Mapping distributional to model-theoretic semantic spaces[pdf]
  • Playing Atari with Deep Reinforcement Learning[pdf]
  • Word Embedding Revisited A New Representation Learning and Explicit Matrix Factorization Perspective [pdf]
2015/12/11 Chao Xing, Yiqiao Pan
  • Semi-Supervised Word Sense Disambiguation Using Word Embeddings in General and Specific Domains [pdf]
  • SENSE2VEC - A FAST AND ACCURATE METHOD FOR WORD SENSE DISAMBIGUATION IN NEURAL WORD EMBEDDINGS [pdf]
  • Efficient Non-parametric Estimation of Multiple Embeddings per Word in Vector Space[pdf]
  • Distributional Semantics in Use[pdf]
2015/12/18 Tianyi Luo, Dongxu Zhang
  • Human-level concept learning through probabilistic program induction(Cognitive Science) [pdf]
  • Cluster Analysis of Heterogeneous Rank Data(ICML 2007) [pdf]
  • Building a shared world: Mapping distributional to model-theoretic semantic spaces[pdf]
2015/12/25 Dongxu zhang, Qixin Wang
  • Exploiting Multiple Sources for Open-domain Hypernym Discovery[[12]]
  • learning semantic hierarchies via word embeddings[[13]]
2015/12/31 Xiaoxi Wang, Chao Xing
  • Multilingual Language Processing From Bytes [pdf]
  • Towards universal neural nets: Gibbs machines and ACE. [pdf]
2016/1/8 Qixin Wang, Tianyi Luo
  • Unveiling the Dreams of Word Embeddings: Towards Language-Driven Image Generation[pdf]
  • Generating Chinese Couplets using a Statistical MT Approach[pdf]
  • Generating Chinese Classical Poems with Statistical Machine Translation Models[pdf]
  • Chinese Poetry Generation with Recurrent Neural Networks[pdf]
2016/1/15 Chao Xing
  • Learning from Chris Dyer [ppt]
  • Learning Word Representations with Hierarchical Sparse Coding [pdf]
  • Non-distributional Word Vector Representations [pdf]
  • Sparse Overcomplete Word Vector Representations [pdf]
2016/1/22 Qixin Wang, Tianyi Luo
  • Skip_thought_vector [pdf]
2016/1/29 Dongxu Zhang
  • Towards Neural Network-based Reasoning[[14]]
2016/3/25 Jiyuan Zhang
  • Modeling Temporal Dependencies in High-Dimensional Sequences:Application to Polyphonic Music Generation and Transcription[pdf]
  • Composing Music With Recurrent Neural Networks[blog]
2016/4/1 Chao Xing
  • Generating Text with Deep Reinforcement Learning[pdf]
2016/4/8 Tianyi Luo
  • Generating Chinese Classical Poems with RNN[[15]]
2016/4/28 Chao Xing
  • Knowledge Base Completion via Search-Based Question Answering [[16]]
  • Open Domain Question Answering via Semantic Enrichment [[17]]
  • A Neural Conversational Model [[18]]
2016/5/11 Chao Xing
  • A Hierarchical Recurrent Encoder-Decoder for Generative Context-Aware Query Suggestion
  • A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
  • Building End-To-End Dialogue Systems Using Generative Hierarchical Neural Network Models
  • Neural Responding Machine for Short-Text Conversation
  • Learning from Real Users Rating Dialogue Success with Neural Networks for Reinforcement Learning in Spoken Dialogue Systems
2016/7/28 Aiting Liu
  • Intrinsic Subspace Evaluation of Word Embedding Representations [pdf]

[slides]

2016/8/4
  • Aodong Li
  • Jiyuan Zhang
  • Andi Zhang
  • On the Role of Seed Lexicons in Learning Bilingual Word Embeddings [pdf] [slides]
  • ABCNN- Attention-Based Convolutional Neural Network for Modeling Sentence Pairs

[pdf] [slides]

  • Tutorial: Introduction to different LMs: NNLM, RNNLM, continuous bag of words, skip-gram

[slides]

2016/8/18
  • Shiyao Li
  • Aiting Liu
  • Multilingual part-of-speech tagging with bidirectional long short-term memory models and auxiliary loss

[pdf] [slides]

  • A Sentence Interaction Network for Modeling Dependence between Sentences

[pdf] [slides]

2016/8/25
  • Ziwei Bai
  • Tutorial: Tensorflow guidelines and some examples

[slides]

2016/8/26
  • Jiyuan Zhang
  • Shiyao Li
  • Tutorial: Introduction to GRU, LSTM, RBM [slides]
  • Tutorial : Linear Algebra, Probability and Information Basics

[LinearAlgebra] [ProbabilityAndInformationTheory]

2016/9/9
  • Aodong Li
  • Pointing the Unknown Words [pdf]
2016/9/18
  • Andy Zhang
  • Shiyao Li
  • Aodong Li
  • Large-Scale Information Extraction from Textual Definitions through Deep Syntactic and Semantic Analysis [pdf][slides]
  • Finding the Middle Ground - A Model for Planning Satisficing Answers [pdf]

[slides]

  • Compressing Neural Language Models by Sparse Word Representations [pdf]
2016/9/30
  • Jiyuan Zhang
  • Shiyue Zhang
  • On-line Active Reward Learning for Policy Optimisation in Spoken Dialogue Systems

[pdf] [slides]

  • Stack-propagation: Improved Representation Learning for Syntax

[pdf] [slides]

2017/5/18
  • Shiyue Zhang
  • Convolutional Sequence to Sequence Learning [slides] [pdf]