[Adapt] [Adapt Seminar] Semantic Text Similarity

[Luo Kangqi]

Hi all,


In today's seminar, I'll talk about Semantic Text Similarity.


Semantic similarity is a core technique for many topics in natural language processing, such as question answering, semantic searching, and computer-assisted assessment. The task is to compute a similarity score given two natural language texts. Due to the different aspects of understanding for semantic similarity, various methods has been proposed to solve this task. I will present some typical framework to model natural texts, the algorithms to compute the similarity score, and how we evaluate those semantic similarity methods.


Cheers,
Kangqi
------------------
Luo Kangqi
ADAPT Lab, SEIEE 3-341
Shanghai Jiao Tong University
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://cs.sjtu.edu.cn/pipermail/adapt/attachments/20130925/07f71e5f/attachment-0001.html>