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 1907.03040cs.CL
收藏

BERT-DST:基于Transformer双向编码器表示的可扩展端到端对话状态跟踪

BERT-DST: Scalable End-to-End Dialogue State Tracking with Bidirectional Encoder Representations from Transformer

Carnegie Mellon University(卡内基梅隆大学)

Guan-Lin Chao, Ian Lane

摘要:

对话状态跟踪(DST)中一个重要但很少解决的问题是动态本体的可扩展性(例如,电影、餐馆)和看不见的槽值。我们专注于一个特定的条件,其中本体是未知的状态跟踪器,但目标槽值(除了没有和dontcare),可能在训练过程中看不见,可以在对话上下文中找到的词段。先前的方法通常依赖于从n-gram枚举或时隙标记器输出的候选生成,这可能是低效的或遭受错误传播。我们提出了BERT-DST,一个端到端的对话状态跟踪器,直接从对话上下文中提取插槽值。我们使用BERT作为对话上下文编码器,其上下文化的语言表示适合于可扩展的DST,以从其语义上下文中识别槽值。此外,我们采用编码器参数共享在所有槽有两个优点:(1)参数的数量不与本体线性增长。(2)语言表征知识可以在槽之间转移。实证评估表明,跨时隙参数共享的BERT-DST在基准可扩展DST数据集Sim-M和Sim-R上的性能优于先前的工作,并在标准DSTC 2和WOZ 2.0数据集上实现了有竞争力的性能。

英文摘要:

An important yet rarely tackled problem in dialogue state tracking (DST) is scalability for dynamic ontology (e.g., movie, restaurant) and unseen slot values. We focus on a specific condition, where the ontology is unknown to the state tracker, but the target slot value (except for none and dontcare), possibly unseen during training, can be found as word segment in the dialogue context. Prior approaches often rely on candidate generation from n-gram enumeration or slot tagger outputs, which can be inefficient or suffer from error propagation. We propose BERT-DST, an end-to-end dialogue state tracker which directly extracts slot values from the dialogue context. We use BERT as dialogue context encoder whose contextualized language representations are suitable for scalable DST to identify slot values from their semantic context. Furthermore, we employ encoder parameter sharing across all slots with two advantages: (1) Number of parameters does not grow linearly with the ontology. (2) Language representation knowledge can be transferred among slots. Empirical evaluation shows BERT-DST with cross-slot parameter sharing outperforms prior work on the benchmark scalable DST datasets Sim-M and Sim-R, and achieves competitive performance on the standard DSTC2 and WOZ 2.0 datasets.

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。

↑