REVIEW 2 cited by
A Compare Aggregate Transformer for Understanding Document-grounded Dialogue
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Unstructured documents serving as external knowledge of the dialogues help to generate more informative responses. Previous research focused on knowledge selection (KS) in the document with dialogue. However, dialogue history that is not related to the current dialogue may introduce noise in the KS processing. In this paper, we propose a Compare Aggregate Transformer (CAT) to jointly denoise the dialogue context and aggregate the document information for response generation. We designed two different comparison mechanisms to reduce noise (before and during decoding). In addition, we propose two metrics for evaluating document utilization efficiency based on word overlap. Experimental results on the CMUDoG dataset show that the proposed CAT model outperforms the state-of-the-art approach and strong baselines.
Forward citations
Cited by 2 Pith papers
-
Collective oscillations in the finite-size Kuramoto model below the critical coupling: shot-noise approach
In a finite Kuramoto population below the synchronization threshold, the order parameter fluctuations are described by the spectrum W(ω) = (2π/N)|(1+iω)/(1+iω-K/2)|² g(ω), with variance 1/[N(1-K/2)].
-
Emergent togetherness in collaborative dance improvisation: neural and motor synchronization reveal a coupling-decoupling paradox
After dance training, inter-person EEG synchronization increased while hand-motion synchronization decreased, a dissociation the authors call the coupling-decoupling paradox.
Discussion (0). Continue with ORCID to comment.