Deep Learning for NLP 文章列举

一、大部分文章来自:

原文:http://www.xperseverance.net/blogs/2013/07/2124/

http://www.socher.org/

http://deeplearning.stanford.edu/wiki/index.php/UFLDL_Tutorial

包括从他们里面的论文里找到的related work

 

Word Embedding Learnig

SENNA原始论文【ACL'07】Fast Semantic Extraction Using a Novel Neural Network Architecture

Ronan Collobert and Jason Weston【ICML'08】A unified architecture for natural language processing: deep neural networks with multitask learning

Joseph Turian, et al.【ACL'10】Word representations：A simple and general method for semi-supervised learning

Antoine Bordes, et al. 【AAAI'11】Learning Structured Embeddings of Knowledge Bases

our model learns one embedding for each entity (i.e. one low dimensional vector) and one operator for each relation (i.e. a matrix).

Ronan Collobert, et al.【JMLR'12】Natural Language Processing (Almost) from Scratch

Eric H. Huang, et al.【ACL'12】Improving Word Representations via Global Context and Multiple Word Prototypes

T. Mikolov, et al.【HLT-NAACL'13】Linguistic regularities in continuous spaceword representations

Yoshua Bengio et al,【13】 Representation Learning: A Review and New Perspectives

 

待读列表：

Semi-supervised learning of compact document representations with deep networks

【UAI'13】Modeling Documents with a Deep Boltzmann Machine

 

Language Model

Y. Bengio, et al. Neural probabilistic language model

博士论文：Statistical Language Models based on Neural Networks 这人貌似在ICASSP上有个文章

T Mikolov Statistical Language Models Based on Neural Networks

 

Sentiment

【HLT'11】Learning word vectors for sentiment analysis

【EMNLP'11】Semi-supervised recursive autoencoders for predicting sentiment distributions

【NAACL'13】 Discourse Connectors for Latent Subjectivity in Sentiment Analysis

 

other NLP 以下内容见socher主页

Parsing with Compositional Vector Grammars

Better Word Representations with Recursive Neural Networks for Morphology
Semantic Compositionality through Recursive Matrix-Vector Spaces
Dynamic Pooling and Unfolding Recursive Autoencoders for Paraphrase Detection
Parsing Natural Scenes and Natural Language with Recursive Neural Networks
Learning Continuous Phrase Representations and Syntactic Parsing with Recursive Neural Networks

Joint Learning of Words and Meaning Representations for Open-Text Semantic Parsing

 

Tutorials

Ronan Collobert and Jason Weston【NIPS'09】Deep Learning for Natural Language Processing

Richard Socher, et al.【NAACL'13】【ACL'12】Deep Learning for NLP

Yoshua Bengio【ICML'12】Representation Learning

Leon Bottou, Natural language processing and weak supervision

Yoshua Bengio最新AAAI 2013 tutorial：http://www.iro.umontreal.ca/~bengioy/talks/aaai2013-tutorial.pdf

 

Socher NAACL 2013：http://nlp.stanford.edu/courses/NAACL2013/

二、知远点评

原文：http://www.52cs.org/?p=182&utm_source=tuicool

• 作者刘知远 weibo：http://weibo.com/zibuyu9  主页：http://nlp.csai.tsinghua.edu.cn/~lzy  

1. 翟成祥老师早期在语言模型的工作很有影响力，他在2009年写过一本综述专著：Statistical Language Models for Information Retrieval，建议阅读。
2. 北大 @BatmanFly （现在是人大老师啦）他们做的Knowledge Sharing via Social Login: Exploiting Microblogging Service for Warming up Social Question Answering Websites在微博和知乎之间建立了语义联系，也是很赞的角度。http://t.cn/RPOzhh4
3. COLING 2014论文集：http://t.cn/RPpdIIk ，首先要去看今年最佳论文，中科院自动化所 @刘康_自动化所 赵军老师团队的大作：Relation Classification via Convolutional Deep Neural Network。:)
4. 斯坦福Richard Socher在EMNLP2014发表新作：GloVe: Global Vectors for Word Representation 粗看是融合LSA等算法的想法，利用global word co-occurrence信息提升word vector学习效果，很有意思，在word analogy task上准确率比word2vec提升了11%。 http://t.cn/RPohHyc
5. 哈工大@张牧宇-哈工大SCIR 的Triple based Background Knowledge Ranking for Document Enrichment利用knowledge triple表示文档，与今年WSDM的Knowledge-based Graph Document Modeling有异曲同工之妙。
6. 发现哈工大的这篇 Learning Sense-specific Word Embeddings By Exploiting Bilingual Resources 利用双语数据学习词义表示。多语角度很有意思。
7.  MSRA A Probabilistic Model for Learning Multi-Prototype Word Embeddings，基于skip-gram采用概率模型和EM算法解决一词多义的表示问题。
8. @周光有_CAS 和赵军老师在社区问答系统上的工作：Group Non-negative Matrix Factorization with Natural Categories for Question Retrieval in Community Question Answer Archives。最近word embedding和NMF都开始在NLP领域大显身手了。
9. IBM有篇Deep Convolutional Neural Networks for Sentiment Analysis of Short Texts，在Fine-Grained的评测上效果比Socher的RNTN高大约3个百分点不到。
10. MSRA有篇 A Probabilistic Model for Learning Multi-Prototype Word Embeddings，基于skip-gram采用概率模型和EM算法解决一词多义的表示问题。这个问题很有实用价值。@陈新雄_THU 也将在今年EMNLP展示我们组在这方面的工作：A Unified Model for Word Sense Representation and Disambiguation。
11. 哈工大和MSRA合作的 Building Large-Scale Twitter-Specific Sentiment Lexicon : A Representation Learning Approach 想法也很有意思，利用word embedding技术构建情感词典。作者 @唐都钰HIT-SCIR 今年还有篇ACL和EMNLP，都是以情感分析为主题，国内NLP新星啊。:)
12. 谢 @刘康_自动化所 推介。Jiawei Han老师综述介绍得非常全面，建议以此为入口学习。我们组司宪策师兄博士论文也以此为主题，中文写的比较好读，下载地址http://t.cn/8F1qSPX 。社会标签可从两个角度思考，一是ML角度可看做多标签分类问题，二是NLP角度可看做关键词产生问题，都有大量前人工作参考。
13. Richard Socher一如既往很有诚意地放出了代码和数据，大家快围观： http://t.cn/RPohHyc
14. David Blei组提出主题模型新概念：Real-time Topic Models for Crisis Counseling。好像是KDD短文。http://t.cn/RPohSwB
15. Barabasi团队把“魔爪”伸向了历史学：A network framework of cultural history发表在最近Science杂志的Quantitative Social Science栏目。
16. IEEE TKDE上的一篇综述：A Review on Multi-Label Learning Algorithmshttp://t.cn/RPirZh6 @张敏灵-SEU 老师和 @南大周志华 老师的工作，关注。