Table of Links
3 Method and 3.1 Phase 1: Taxonomy Generation
3.2 Phase 2: LLM-Augmented Text Classification
4 Evaluation Suite and 4.1 Phase 1 Evaluation Strategies
4.2 Phase 2 Evaluation Strategies
5.3 LLM-Augmented Text Classification
5.4 Summary of Findings and Suggestions
6 Discussion and Future Work, and References
A TAXONOMIES
The user intent taxonomy and conversation domain taxonomy used in the label assignment phase are provided in Tables 5 and 6. Note although the label name and the majority of label description are automatically generated through our TnT-LLM framework, we did perform a lightweight human calibration on these generated taxonomies and added artificial examples. These examples are purely for illustration purpose and do not link to any particular data point in our corpus.
This paper is available on arxiv under CC BY-NC-ND 4.0 DEED license.
Authors:
(1) Mengting Wan, Microsoft Corporation and Microsoft Corporation;
(2) Tara Safavi (Corresponding authors), Microsoft Corporation;
(3) Sujay Kumar Jauhar, Microsoft Corporation;
(4) Yujin Kim, Microsoft Corporation;
(5) Scott Counts, Microsoft Corporation;
(6) Jennifer Neville, Microsoft Corporation;
(7) Siddharth Suri, Microsoft Corporation;
(8) Chirag Shah, University of Washington and Work done while working at Microsoft;
(9) Ryen W. White, Microsoft Corporation;
(10) Longqi Yang, Microsoft Corporation;
(11) Reid Andersen, Microsoft Corporation;
(12) Georg Buscher, Microsoft Corporation;
(13) Dhruv Joshi, Microsoft Corporation;
(14) Nagu Rangan, Microsoft Corporation.
