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.
翻译:缩略图重写的目的是从一个多方向对话框的最新转弯中恢复引用和省略信息。 最近, 标记而不是线性生成序列的方法在主页内外的重写设置中都表现得更强。 这是因为塔格的搜索空间较小, 因为它只能复制对话背景中的符号。 但是, 当必须添加到源词的语句无法以单一的上下文范围覆盖时, 这些方法可能会受到低覆盖率的影响 。 这可能以英语等语言出现, 这些语言会引入符号, 如在重写语法格式中引入预定位。 我们建议使用一个等级上行语法的调格( HCT ), 通过预测时间档规则( 例如, “ 位置 位置 ” ) 来缓解这一问题 。 但是, 这些方法可能会受到低覆盖率的影响 。 HCT (i) 在源字符串中标记必须添加到源词级编辑动作和时间档规则, 以及 (ii) 在由此产生的规则槽中, 将 HCT 标记允许 HCT 在重写规则的外加点, 和多尾版规则再显示 B 的基号 。 一旦我们可以进一步显示 B- trireal- tral 规则在 B tral 的 B tral 上, 的系统上, 。