Hierarchical Context Tagging for Utterance Rewriting


  • Lisa Jin University of Rochester
  • Linfeng Song Tencent AI Lab
  • Lifeng Jin Tencent AI Lab
  • Dong Yu Tencent AI Lab
  • Daniel Gildea University of Rochester




Speech & Natural Language Processing (SNLP)


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.




How to Cite

Jin, L., Song, L., Jin, L., Yu, D., & Gildea, D. (2022). Hierarchical Context Tagging for Utterance Rewriting. Proceedings of the AAAI Conference on Artificial Intelligence, 36(10), 10849-10857. https://doi.org/10.1609/aaai.v36i10.21331



AAAI Technical Track on Speech and Natural Language Processing