تقرير
'LazImpa': Lazy and Impatient neural agents learn to communicate efficiently
| العنوان: | 'LazImpa': Lazy and Impatient neural agents learn to communicate efficiently |
|---|---|
| المؤلفون: | Rita, Mathieu, Chaabouni, Rahma, Dupoux, Emmanuel |
| المصدر: | Proceedings of CoNLL 2020 |
| سنة النشر: | 2020 |
| المجموعة: | Computer Science |
| مصطلحات موضوعية: | Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Multiagent Systems, I.2 |
| الوصف: | Previous work has shown that artificial neural agents naturally develop surprisingly non-efficient codes. This is illustrated by the fact that in a referential game involving a speaker and a listener neural networks optimizing accurate transmission over a discrete channel, the emergent messages fail to achieve an optimal length. Furthermore, frequent messages tend to be longer than infrequent ones, a pattern contrary to the Zipf Law of Abbreviation (ZLA) observed in all natural languages. Here, we show that near-optimal and ZLA-compatible messages can emerge, but only if both the speaker and the listener are modified. We hence introduce a new communication system, "LazImpa", where the speaker is made increasingly lazy, i.e. avoids long messages, and the listener impatient, i.e.,~seeks to guess the intended content as soon as possible. Comment: Accepted to CoNLL 2020 |
| نوع الوثيقة: | Working Paper |
| URL الوصول: | http://arxiv.org/abs/2010.01878 |
| رقم الأكسشن: | edsarx.2010.01878 |
| قاعدة البيانات: | arXiv |
| الوصف غير متاح. |