Gang Wang, Fei Wang, et al.
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
End-to-End task-oriented dialogue systems generate responses based on dialog history and an accompanying knowledge base (KB). Inferring those KB entities that are most relevant for an utterance is crucial for response generation. Existing state of the art scales to large KBs by softly filtering over irrelevant KB information. In this paper, we propose a novel filtering technique that consists of (1) a pairwise similarity based filter that identifies relevant information by respecting the n-ary structure in a KB record. and, (2) an auxiliary loss that helps in separating contextually unrelated KB information. We also propose a new metric – multiset entity F1 which fixes a correctness issue in the existing entity F1 metric. Experimental results on three publicly available task-oriented dialog datasets show that our proposed approach outperforms existing state-ofthe-art models.
Gang Wang, Fei Wang, et al.
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Atsuyoshi Nakamura, Naoki Abe
Electronic Commerce Research
Kun Wang, Juwei Shi, et al.
PACT 2011
Benny Kimelfeld, Yehoshua Sagiv
ICDT 2013