English

Hierarchical Context Tagging for Utterance Rewriting

Computation and Language 2022-08-09 v2

Abstract

Utterance rewriting aims to recover coreferences and omitted information from the latest turn of a multi-turn dialogue. Recently, methods that tag rather than linearly generate sequences have proven stronger in both in- and out-of-domain rewriting settings. This is due to a tagger's smaller search space as it can only copy tokens from the dialogue context. However, these methods may suffer from low coverage when phrases that must be added to a source utterance cannot be covered by a single context span. This can occur in languages like English that introduce tokens such as prepositions into the rewrite for grammaticality. We propose a hierarchical context tagger (HCT) that mitigates this issue by predicting slotted rules (e.g., "besides_") whose slots are later filled with context spans. HCT (i) tags the source string with token-level edit actions and slotted rules and (ii) fills in the resulting rule slots with spans from the dialogue context. This rule tagging allows HCT to add out-of-context tokens and multiple spans at once; we further cluster the rules to truncate the long tail of the rule distribution. Experiments on several benchmarks show that HCT can outperform state-of-the-art rewriting systems by ~2 BLEU points.

Keywords

Cite

@article{arxiv.2206.11218,
  title  = {Hierarchical Context Tagging for Utterance Rewriting},
  author = {Lisa Jin and Linfeng Song and Lifeng Jin and Dong Yu and Daniel Gildea},
  journal= {arXiv preprint arXiv:2206.11218},
  year   = {2022}
}

Comments

Update terms for span index attention in Eq. 6 and add appendix. 10 pages, AAAI 2022

R2 v1 2026-06-24T12:00:30.306Z