TY - UNPB
T1 - Refer, reuse, reduce: Generating subsequent references in visual and conversational contexts
AU - Takmaz, Ece
AU - Giulianelli, Mario
AU - Pezzelle, Sandro
AU - Sinclair, Arabella
AU - Fernández, Raquel
N1 - published in Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP 2020)
PY - 2020
Y1 - 2020
N2 - Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground accumulated by the interlocutors and hence have several interesting properties, namely, they tend to be shorter and reuse expressions that were effective in previous mentions. In this paper, we tackle the generation of first and subsequent references in visually grounded dialogue. We propose a generation model that produces referring utterances grounded in both the visual and the conversational context. To assess the referring effectiveness of its output, we also implement a reference resolution system. Our experiments and analyses show that the model produces better, more effective referring utterances than a model not grounded in the dialogue context, and generates subsequent references that exhibit linguistic patterns akin to humans.
AB - Dialogue participants often refer to entities or situations repeatedly within a conversation, which contributes to its cohesiveness. Subsequent references exploit the common ground accumulated by the interlocutors and hence have several interesting properties, namely, they tend to be shorter and reuse expressions that were effective in previous mentions. In this paper, we tackle the generation of first and subsequent references in visually grounded dialogue. We propose a generation model that produces referring utterances grounded in both the visual and the conversational context. To assess the referring effectiveness of its output, we also implement a reference resolution system. Our experiments and analyses show that the model produces better, more effective referring utterances than a model not grounded in the dialogue context, and generates subsequent references that exhibit linguistic patterns akin to humans.
U2 - 10.48550/arXiv.2011.04554
DO - 10.48550/arXiv.2011.04554
M3 - Preprint
BT - Refer, reuse, reduce: Generating subsequent references in visual and conversational contexts
PB - ArXiv
ER -