English

Robust Dialog State Tracking for Large Ontologies

Computation and Language 2016-05-10 v1 Artificial Intelligence Machine Learning

Abstract

The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself from the previous three editions as follows: the number of slot-value pairs present in the ontology is much larger, no spoken language understanding output is given, and utterances are labeled at the subdialog level. This paper describes a novel dialog state tracking method designed to work robustly under these conditions, using elaborate string matching, coreference resolution tailored for dialogs and a few other improvements. The method can correctly identify many values that are not explicitly present in the utterance. On the final evaluation, our method came in first among 7 competing teams and 24 entries. The F1-score achieved by our method was 9 and 7 percentage points higher than that of the runner-up for the utterance-level evaluation and for the subdialog-level evaluation, respectively.

Keywords

Cite

@article{arxiv.1605.02130,
  title  = {Robust Dialog State Tracking for Large Ontologies},
  author = {Franck Dernoncourt and Ji Young Lee and Trung H. Bui and Hung H. Bui},
  journal= {arXiv preprint arXiv:1605.02130},
  year   = {2016}
}

Comments

Paper accepted at IWSDS 2016

R2 v1 2026-06-22T13:55:20.177Z