TY - JOUR AU - Jin, Lisa AU - Song, Linfeng AU - Jin, Lifeng AU - Yu, Dong AU - Gildea, Daniel PY - 2022/06/28 Y2 - 2024/03/28 TI - Hierarchical Context Tagging for Utterance Rewriting JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 36 IS - 10 SE - AAAI Technical Track on Speech and Natural Language Processing DO - 10.1609/aaai.v36i10.21331 UR - https://ojs.aaai.org/index.php/AAAI/article/view/21331 SP - 10849-10857 AB - 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. ER -