Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever

Abstract

Querying the knowledge base (KB) has long been a challenge in the end-to-end taskoriented dialogue system. Previous sequenceto-sequence (Seq2Seq) dialogue generation work treats the KB query as an attention over the entire KB, without the guarantee that the generated entities are consistent with each other. In this paper, we propose a novel framework which queries the KB in two steps to improve the consistency of generated entities. In the first step, inspired by the observation that a response can usually be supported by a single KB row, we introduce a KB retrieval component which explicitly returns the most relevant KB row given a dialogue history. The retrieval result is further used to filter the irrelevant entities in a Seq2Seq response generation model to improve the consistency among the output entities. In the second step, we further perform the attention mechanism to address the most correlated KB column. Two methods are proposed to make the training feasible without labeled retrieval data, which include distant supervision and Gumbel-Softmax technique. Experiments on two publicly available task oriented dialog datasets show the effectiveness of our model by outperforming the baseline systems and producing entity-consistent responses. ) = softmax (3 4 + 6 ) AddressDistance POI type POI Traffic info

Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training

“…Compared Methods We compare TTOS with several state-of-the-art task-oriented dialogue systems, including Seq2Seq/+Attn (Luong et al, 2015), Seq2Seq model with copy mechanism (Ptr-Unk) (Gulcehre et al, 2016), network-based seq2seq (Mem2Seq) (Madotto et al, 2018), bagof-sequences memory network (BossNet) , entity-consistent network with KB retriever (ECET) (Qin et al, 2019) local memory pointer network (GLMP) (Wu et al, 2019).…”

Recent advances and challenges in task-oriented dialog systems

“…In ref. [127], a two-step KB retrieval is proposed to improve the entities' consistency by first deciding the entity row and then selecting the most relevant KB column.…”

Improving Knowledge-Aware Dialogue Response Generation by Using Human-Written Prototype Dialogues

“…Traditional models can merely access the surface knowledge from the plain text of the query (Ghazvininejad et al, 2018). Researchers have shown the generated dialogue responses can be more diverse and informative, by introducing the external knowledge, such as the unstructured background documents (Meng et al, 2019), structured knowledge graphs (Zhou et al, 2018;Wu et al, 2020a) and knowledge tables (Qin et al, 2019), or the hybrid of them .…”

“…However, traditional dialogue systems can merely access the surface knowledge in the given query (Ghazvininejad et al, 2018). To tackle this issue, a feasible scheme is incorporating external knowledge into the dialogue generation (Qin et al, 2019;Wu et al, 2020b). This paper focuses on introducing the structured open-domain commonsense knowledge graph into the single-turn dialogue response generation.…”