1 / 9

47 th Annual Meeting of the Association for Computational Linguistics and

47 th Annual Meeting of the Association for Computational Linguistics and 4 th International Joint Conference on Natural Language Processing Of the AFNLP. 2-7 Aug 2009. Do Automatic Annotation Techniques Have Any Impact on Supervised Complex Question Answering?.

aladdin-reed
Download Presentation

47 th Annual Meeting of the Association for Computational Linguistics and

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. 47th Annual Meeting of the Association for Computational Linguistics and 4th International Joint Conference on Natural Language Processing Of the AFNLP 2-7 Aug 2009

  2. Do Automatic Annotation Techniques Have Any Impact on Supervised Complex Question Answering? Yllias Chali and Sadid A. Hasan Dept. of Computer Science University of Lethbridge Lethbridge, AB, Canada Shafiq R. Joty Dept. of Computer Science University of British Columbia Vancouver, BC, Canada

  3. Research Problem and Our Approach “Given a complex question (topic description) and a collection of relevant documents, the task is to synthesize a fluent, well-organized 250-word summary of the documents that answers the question(s) in the topic”. Example: Describe steps taken and worldwide reaction prior to the introduction of the Euro on January 1, 1999. Include predictions and expectations reported in the press. -Use supervised learning methods. -Use automatic annotation techniques.

  4. Motivation Huge amount of annotated or labeled data is a prerequisite for supervised training. When humans are employed, the whole process becomes time consuming and expensive. In order to produce a large set of labeled data we prefer the automatic annotation strategy.

  5. Automatic Annotation Techniques Using ROUGE Similarity Measures. Basic Element (BE) Overlap Measure. Syntactic Similarity Measure. Semantic Similarity Measure. Extended String Subsequence Kernel (ESSK).

  6. Supervised Systems Support Vector Machines (SVM). Conditional Random Fields (CRF). Hidden Markov Models (HMM). Maximum Entropy (MaxEnt).

  7. Feature Space • Query-related features: • n-gram overlap, Longest Common Subsequence (LCS), Weighted LCS (WLCS), skip-bigram, exact word overlap, synonym overlap, hypernym/hyponym overlap, gloss overlap, Basic Element (BE) overlap and syntactic tree similarity measure • Important features: • position of sentences, length of sentences, Named Entity (NE), cue word match and title match

  8. Experimental Results

  9. Conclusion Sem annotation is the best for SVM. ESSK works well for HMM, CRF and MaxEnt systems.

More Related