Decoding, Fast and Slow: A Case Study on Balancing Trade-Offs in Incremental, Character-level Pragmatic Reasoning
Year: 2021
Type: conference-paper
Abstract: Recent work has adopted models of pragmatic reasoning for the generation of informative language in, e.g., image captioning.We propose a simple but highly effective relaxation of fully rational decoding, based on an existing incremental and character-level approach to pragmatically informative neural image captioning.We implement a mixed, 'fast' and 'slow', speaker that applies pragmatic reasoning occasionally (only word-initially), while unrolling the language model.In our evaluation, we find that increased informativeness through pragmatic decoding generally lowers quality and, somewhat counter-intuitively, increases repetitiveness in captions.Our mixed speaker, however, achieves a good balance between quality and informativeness.
Institutions: Bielefeld University, Artificial Intelligence Research Center
Language: English
Subfield: Computer Vision and Pattern Recognition
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3202614407