Text-2014-08-19

QA Research：

 ProMe: 对我们有帮助的地方有：
   1. Question classification 其中需要注意的是question type的定义
   2. Key-Word extraction
 Leveraging social Q&A collections for improving complex question answering: 对我们有帮助的地方有:
   1. Question type classification.
   2. 依据 question type classification 对 answer 做 re-score.

QA Develop:

 1. Mean value by using word2vec training question treat as baseline.
 2. 先做分类，再做搜索。
 3. Question 分类 ==> Lucene 40 best (加入 word2vec 策略， 加入 translation 策略（ps：邢超完成）) ==> content 分类 （lasso 精确匹配）
 4. 爬去百度知道的数据

晓曦：

 word2vec train 字的vector ==> predict 实体vector （领域可以是公司名称识别）
 王老师提供的思路：
    词的vector 作为baseline
    字的vector <=> 词的vector
              转化为
    选几组词作为测试，看看有没有什么相对靠谱一些的转化思路。
    建议：这周能够使用translation model的结果

Knowledge Vector:

 learning cost fuction ==> Link from wiki
                       ==> 正文的over lap程度（相似度）
                           思路：可以用我们之前做过的text vector 辅助 计算相似度
                       ==> 已经结构化好的模块，比如说wiki中的上下位关系等
          Link 的长度以及深度
          子类在某一程度上聚集在父类的周围

recorded by Chao Xing

Paper List

1. a paper for practical design: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.

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.

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),

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

5 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).

6. Bordes, Antoine, Sumit Chopra, and Jason Weston. "Question Answering with Subgraph Embeddings." arXiv preprint arXiv:1406.3676 (2014).

7 Choi, Erik, Vanessa Kitzie, and Chirag Shah. "A machine learning-based approach to predicting success of questions on social question-answering." (2013).

8 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.

9 Zhou, Guangyou, et al. "Statistical Machine Translation Improves Question Retrieval in Community Question Answering via Matrix Factorization." ACL (1). 2013.

10.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

11 Wu, Youzheng, et al. "Leveraging Social Q&A Collections for Improving Complex Question Answering." Computer Speech & Language (2014).

12 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).