paper-with-me

홈 › Papers

Focus on What's Informative and Ignore What's not: Communication Strategies in a Referential Game

2019-11-05 · Roberto Dessì, Diane Bouchacourt, Davide Crepaldi, Marco Baroni

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.

📄 PDF Abstract BibTeX arXiv:1911.01892

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Informative Communication of Robot Plans

2025-11-17 · Michele Persiani, Thomas Hellstrom arxiv

When a robot is asked to verbalize its plan it can do it in many ways. For example, a seemingly natural strategy is incremental, where the robot verbalizes its planned actions in plan order. However, an important aspect …

It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system

2021-05-01 · Sarenne Wallbridge, Peter Bell, Catherine Lai

People convey information extremely effectively through spoken interaction using multiple channels of information transmission: the lexical channel of what is said, and the non-lexical channel of how it is said. We propo…

Information Maximizing Visual Question Generation

2019-03-27 · CVPR 2019 6 · Ranjay Krishna, Michael Bernstein, Li Fei-Fei

Though image-to-sequence generation models have become overwhelmingly popular in human-computer communications, they suffer from strongly favoring safe generic questions ("What is in this picture?"). Generating uninforma…

ClusteringQuestion GenerationQuestion-Generation

Information Theory of Meaningful Communication

2024-11-19 · Doron Sivan, Misha Tsodyks

In Shannon's seminal paper, entropy of printed English, treated as a stationary stochastic process, was estimated to be roughly 1 bit per character. However, considered as a means of communication, language differs consi…

What will it take to generate fairness-preserving explanations?

2021-06-24 · Jessica Dai, Sohini Upadhyay, Stephen H. Bach, Himabindu Lakkaraju

In situations where explanations of black-box models may be useful, the fairness of the black-box is also often a relevant concern. However, the link between the fairness of the black-box model and the behavior of explan…

Fairness