Presentation is loading. Please wait.

Presentation is loading. Please wait.

Dialogue Act Tagging Using TBL Sachin Kamboj CISC 889: Statistical Approaches to NLP Spring 2003 September 14, 2015September 14, 2015September 14, 2015.

Similar presentations


Presentation on theme: "Dialogue Act Tagging Using TBL Sachin Kamboj CISC 889: Statistical Approaches to NLP Spring 2003 September 14, 2015September 14, 2015September 14, 2015."— Presentation transcript:

1 Dialogue Act Tagging Using TBL Sachin Kamboj CISC 889: Statistical Approaches to NLP Spring 2003 September 14, 2015September 14, 2015September 14, 2015

2 Outline Dialogue Acts Transformation Based Learning (TBL) Introduction Training Phase Example Motivation for use of TBL in Dialogue Limitations of TBL Monte Carlo Version of TBL Other Extensions References

3 Dialogue Acts For a computer system to understand (and participate in) a dialogue, the system should know the intentions of the speaker. Defined as: A concise abstraction of the intentional function of a speaker. #SpeakerUtteranceDialogue Act 1JohnHello.Greet 2JohnI’d like to meet you on Tuesday at 2:00Suggest 3MaryThat’s no good for me,Reject 4MaryBut I am free at 3:00Suggest 5JohnThat sounds fine to meAccept 6JohnI’ll see you then.Bye

4 Transformation-based Learning Uses machine learning to generate a sequence of rules to use in tagging data The first rules are general, making sweeping generalization and several errors Subsequent rules are more specific and usually correct specific errors

5 TBL: Training Phase START For each incorrect tag, generate ALL rules to fix this tag Compute a score for each rule Apply this rule to the corpus Find the highest Scoring rule Repeat? END No Yes Label each utterance with an initial tag

6 TBL: Example #Condition (s)New Dialogue Act 1NoneSUGGEST 2Includes “see” and “you”BYE 3Includes “sounds”ACCEPT 4Length < 4 words Previous tag is noneGREET 5Includes “no” Previous tag is SUGGESTREJECT Utterance Correct Tag Rule # 12345 Hello.GSSSGG I’d like to meet you on Tuesday at 2:00SSSSSS That’s no good for me,RSSSSR But I am free at 3:00SSSSSS That sounds fine to meASSAAA I’ll see you then.BSBBBB

7 TBL: Motivation for use in Dialogue Computing Dialogue Acts is similar to computing POS tags: POS tags depend on surrounding words Dialogue Acts depend on surrounding utterances. Advantages over other ML methods used for Dialogue Act Tagging: Generates intuitive rules: Allows researchers to gain insights into discourse theory Leverage learning: Can use tags that have already been computed. Does not overtrain

8 Limitations TBL does not assign a confidence measure to the tags TBL is highly dependent on the rule templates. Rule templates need to be manually selected in advance However, its difficult to find only and all the relevant templates. Omissions would result in handicapping the system Solution: Allow the system to learn which templates are useful Allow an overly general set of templates TBL is capable of discarding irrelevant rules…

9 Limitations (cont.) Problem with the solution: The system becomes intractable with more than 30 templates The system must generate and evaluate O( ip(v + 1) (2d + 1)f ) rules, where: i= no of instances p= no of passes f = no of features d = max. feature distance v = avg. no. of distinct values for each feature

10 A Monte Carlo Version of TBL Allows the system to consider a huge number of templates while still maintaining tractability System does not perform an exhaustive search through the space of possible rules. Instead only R randomly selected templates are instantiated at each pass Hence, system only considers O ( ipR ) rules. System still finds the best rules: Because the system has many opportunities to find the best rules

11 Other Extensions Committee-Based Sampling method to assign confidence measures Automatic generation of “Cue Phases”

12 Reference Sources Samuel, Ken and Carberry, Sandra and Vijay-Shanker, K. 1998. Dialogue Act Tagging with Transformation-Based Learning. In Proceedings of the 17th International Conference on Computational Linguistics and the 36th Annual Meeting of the Association for Computational Linguistics. Montreal, Quebec, Canada. 1150-1156. Samuel, Ken and Carberry, Sandra and Vijay-Shanker, K. 1998. An Investigation of Transformation-Based Learning in Discourse. In Machine Learning: Proceedings of the Fifteenth International Conference. Madison, Wisconsin. 497-505. Samuel, Ken and Carberry, Sandra and Vijay-Shanker, K. 1999. Automatically Selecting Useful Phrases for Dialogue Act Tagging. In Proceedings of the Fourth Conference of the Pacific Association for Computational Linguistics. Waterloo, Ontario, Canada. Samuel, Ken and Carberry, Sandra and Vijay-Shanker, K. 1998. Computing Dialogue Acts from Features with Transformation- Based Learning. In Applying Machine Learning to Discourse Processing: Papers from the 1998 AAAI Spring Symposium. Stanford, California. 90-97..

13 Questions?


Download ppt "Dialogue Act Tagging Using TBL Sachin Kamboj CISC 889: Statistical Approaches to NLP Spring 2003 September 14, 2015September 14, 2015September 14, 2015."

Similar presentations


Ads by Google