dialogue act tagging using tbl sachin kamboj cisc 889: statistical approaches to nlp spring 2003...
TRANSCRIPT
Dialogue Act Dialogue Act TaggingTagging
Using TBLUsing TBL
Sachin KambojSachin Kamboj
CISC 889: Statistical Approaches to NLPCISC 889: Statistical Approaches to NLPSpring 2003Spring 2003
April 19, 2023April 19, 2023
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
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.
# Speaker Utterance Dialogue Act
1 John Hello. Greet
2 John I’d like to meet you on Tuesday at 2:00 Suggest
3 Mary That’s no good for me, Reject
4 Mary But I am free at 3:00 Suggest
5 John That sounds fine to me Accept
6 John I’ll see you then. Bye
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
TBL: Training PhaseSTART
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
NoNo
YesYes
Label each utterancewith an initial tag
TBL: Example
# Condition (s) New Dialogue Act1 None SUGGEST
2 Includes “see” and “you” BYE
3 Includes “sounds” ACCEPT
4 Length < 4 words Previous tag is none GREET
5 Includes “no” Previous tag is SUGGEST REJECT
UtteranceCorrect
TagRule #
1 2 3 4 5
Hello. G S S S G G
I’d like to meet you on Tuesday at 2:00 S S S S S S
That’s no good for me, R S S S S R
But I am free at 3:00 S S S S S S
That sounds fine to me A S S A A A
I’ll see you then. B S B B B B
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
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…
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 instancesp = no of passesf = no of featuresd = max. feature distancev = avg. no. of distinct
values for each feature
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
Other Extensions
Committee-Based Sampling method to assign confidence measures
Automatic generation of “Cue Phases”
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.
Questions?