“Reading Paper”版本间的差异

来自cslt Wiki
跳转至： 导航、 搜索
Lr（讨论 | 贡献）
（→‎word vector）
 
（相同用户的44个中间修订版本未显示）
第1行： 第1行：
 +
==tool==
 +
* word2vec tool
 +
:* word vector tool for text classification, text clustering or information retrieval[http://sourceforge.net/projects/wvtool/]
 +
:* google word2ve[http://code.google.com/p/word2vec/]
 +
* document vector[http://radimrehurek.com/2014/12/doc2vec-tutorial/?utm_source=rss&utm_medium=rss&utm_campaign=doc2vec-tutorial]
 +
:*　genSim[https://github.com/piskvorky/gensim/] new function
 +
* Deep Learning for Java[http://deeplearning4j.org/]
 +
:* word2vec[http://deeplearning4j.org/word2vec.html]
 +
 
==QA==
 
==QA==
−
===2014-08-22===
+
[[2014-08-22-qalr]]
−
'''desin:'''
+
  
−
1. a more detailed design of question classification
+
[[random reading]]
  
−
2. a more detailed design of keyword compensation
+
==NN & RNN LM==
 +
*[[2013-12-3]]
 +
*[[2014-8-31]]
 +
*[[2014-10-9]]
 +
*[[Approaches to convert RNNLM to BNLM]]
  
−
3. a more detailed design of word normalization, word expansion
+
==document classification==
 +
* [[2014-9-10]]
 +
==word vector==
 +
* [[useful tutorial]]
 +
* [[2014-10-20-word2vec|Learning Word Vectors for Sentiment Analysis]]
 +
* deep learing in nlp
 +
:* distributed representations for compositional semantics [http://arxiv.org/pdf/1411.3146.pdf]
 +
:* Deep Learning for Natural Language Processing and Machine Translation [http://cl.naist.jp/~kevinduh/notes/cwmt14tutorial.pdf]
 +
*Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews[http://arxiv.org/abs/1412.5335]
 +
:*使用RNN和PV在情感分析效果不错,代码[https://github.com/mesnilgr/iclr15]
  
−
'''PPT''' [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/3/3c/%E9%98%85%E8%AF%BB.pdf]
+
==learn report==
 +
[[2014-10-19| basic tasks of speech processing]]
 +
==learn process==
 +
[[Information Retrieval]]
  
−
'''learn'''
+
[[nlp class]]
−
* the word weight that computed using preme
+
−
* the translate model for similarity of word
+
−
* Queston answering with subgraph embeddings to learn the relation and entity matrix
+
  
−
'''paper:'''
+
[[nlp tool]]
  
−
1 Zhang, Guangzhi, et al. "The Architecture of ProMe Instant Question Answering System." Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC), 2013 International Conference on. IEEE, 2013.
+
==Some Things to remember==
−
 
+
*　video lectures [http://videolectures.net/]
−
2 Park, Jungyeul, Jong Gun Lee, and Beatrice Daille. "UNPMC: Naive approach to extract keyphrases from scientific articles." Proceedings of the 5th international workshop on semantic evaluation. Association for Computational Linguistics, 2010.
+
*　free books [http://www.justfreebooks.info/]
−
 
+
* 推荐系统的tutorial slides [http://alex.smola.org/teaching/berkeley2012/slides/8_Recommender.pdf][http://www.slideshare.net/xamat/recommender-systems-machine-learning-summer-school-2014-cmu]
−
3.Guangyou Zhou, Li Cai, Jun Zhao, and Kang Liu. 2011. Phrase-based translation model for question retrieval in community question answer archives. In Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1 (HLT '11), Vol. 1. Association for Computational Linguistics, Stroudsburg, PA, USA, 653-662.
+
* understanding-lbfgs [http://aria42.com/blog/2014/12/understanding-lbfgs/]
−
 
+
* ml blog[http://www.cs.waikato.ac.nz/~bernhard/good-machine-learning-blogs.html][http://www.quora.com/What-are-the-best-machine-learning-blogs-or-resources-available]
−
4. Lei Zou, Ruizhe Huang, Haixun Wang, Jeffrey Xu Yu, Wenqiang He, and Dongyan Zhao. 2014. Natural language question answering over RDF: a graph data driven approach. In Proceedings of the 2014 ACM SIGMOD international conference on Management of data (SIGMOD '14). ACM, New York, NY, USA, 313-324. DOI=10.1145/2588555.2610525 http://doi.acm.org/10.1145/2588555.2610525
+
* 公开课[http://52opencourse.com/]
−
 
+
* 机器学习日报[http://ml.memect.com/]
−
4. Shekarpour, Saeedeh, et al. "SINA: Semantic interpretation of user queries for question answering on interlinked data." Web Semantics: Science, Services and Agents on the World Wide Web 2014).
+
:*　包含大量的学习资源
−
 
+
* Advanced Machine Learning[http://www.seas.harvard.edu/courses/cs281/]
−
5. Bordes, Antoine, Sumit Chopra, and Jason Weston. "Question Answering with Subgraph Embeddings." arXiv preprint arXiv:1406.3676 (2014).
+
−
 
+
−
6. Choi, Erik, Vanessa Kitzie, and Chirag Shah. "A machine learning-based approach to predicting success of questions on social question-answering." (2013).
+
−
 
+
−
7. iphaine Dalmas, Bonnie Webber, Answer comparison in automated question answering, Journal of Applied Logic, Volume 5, Issue 1, March 2007, Pages 104-120, ISSN 1570-8683, http://dx.doi.org/10.1016/j.jal.2005.12.002.
+
−
 
+
−
8. Zhou, Guangyou, et al. "Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization." ACL (1). 2013.
+
−
 
+
−
9. Sherzod Hakimov, Hakan Tunc, Marlen Akimaliev, and Erdogan Dogdu. 2013. Semantic question answering system over linked data using relational patterns. In Proceedings of the Joint EDBT/ICDT 2013 Workshops (EDBT '13). ACM, New York, NY, USA, 83-88. DOI=10.1145/2457317.2457331 http://doi.acm.org/10.1145/2457317.2457331
+
−
 
+
−
10. Wu, Youzheng, et al. "Leveraging Social Q&A Collections for Improving Complex Question Answering." Computer Speech & Language (2014).
+
−
 
+
−
11. Giannone, Cristina, Valentina Bellomaria, and Roberto Basili. "A HMM-based approach to question answering against linked data." Proceedings of the Question Answering over Linked Data lab (QALD-3) at CLEF (2013).
+
−
 
+
−
==RNN==
+
−
===2014-8-31===
+
−
1. "Efficient Estimation of Word Representations in Vector Space".  Tomas Mikolov
+
−
 
+
−
2. Distributed Representations ofWords and Phrases and their Compositionality. Tomas Mikolov
+
−
 
+
−
3. Deep Learning Embeddings for Discontinuous Linguistic Units
+
−
 
+
−
==word vector==
+
−
===2014-9-4===
+
−
*useful ppt for acl [http://cslt.riit.tsinghua.edu.cn/mediawiki/images/f/f8/AclVectorTutorial.pdf]
+

2014年12月29日 (一) 07:58的最后版本

tool

  • word2vec tool
  • word vector tool for text classification, text clustering or information retrieval[1]
  • google word2ve[2]
  • document vector[3]
  • 　genSim[4] new function
  • Deep Learning for Java[5]

QA

2014-08-22-qalr

random reading

NN & RNN LM

document classification

word vector

  • distributed representations for compositional semantics [7]
  • Deep Learning for Natural Language Processing and Machine Translation [8]
  • Ensemble of Generative and Discriminative Techniques for Sentiment Analysis of Movie Reviews[9]
  • 使用RNN和PV在情感分析效果不错,代码[10]

learn report

basic tasks of speech processing

learn process

Information Retrieval

nlp class

nlp tool

Some Things to remember

  • 　包含大量的学习资源
  • Advanced Machine Learning[20]
取自“http://index.cslt.org/mediawiki/index.php?title=Reading_Paper&oldid=13194”