arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1605.02130cs.CLcs.AIcs.LG
收藏

大型本体的鲁棒对话状态跟踪

Robust Dialog State Tracking for Large Ontologies

Adobe Research(奥多比研究院);MIT(麻省理工学院);Massachusetts Institute of Technology(麻省理工学院)

Franck Dernoncourt, Ji Young Lee, Trung H. Bui, Hung H. Bui

摘要:

对话状态跟踪挑战4(DSTC 4)与前三个版本的区别如下:本体中存在的槽值对的数量要大得多,没有给出口语语言理解输出,并且在子对话级别标记话语。本文描述了一种新的对话状态跟踪方法,旨在这些条件下,使用精心设计的字符串匹配,共指消解定制的对话框和其他一些改进工作鲁棒。该方法可以正确地识别话语中未明确存在的许多值。在最后的评估中,我们的方法在7个参赛团队和24个参赛作品中获得第一名。通过我们的方法实现的F1分数分别比话语级评估和子对话级评估的亚军高出9和7个百分点。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑