arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2301.13083cs.CLcs.AI
收藏

交流驱动神经智能体中语言普遍特征的涌现:来自语序/格标记权衡的证据

Communication Drives the Emergence of Language Universals in Neural Agents: Evidence from the Word-order/Case-marking Trade-off

Xi’an Jiaotong University(西安交通大学);Leiden University(莱顿大学);University of Groningen(格罗宁根大学)

Yuchen Lian, Arianna Bisazza, Tessa Verhoef

AI总结:

本文提出NeLLCom框架,让神经智能体先监督学习微型语言再通过强化学习优化交流,并在无硬编码认知偏差的情况下复现语序/格标记权衡。

摘要:

在基于神经智能体的语言涌现与演变模拟中,人工学习者的行为往往不同于人类学习者。一种常见解释是这些学习者缺乏适当的认知偏差。然而,也有研究提出,更自然的语言学习和使用环境可能产生更接近人类的结果。我们考察后一种观点,重点关注语序/格标记权衡,这是一种被广泛证实的语言普遍特征,但事实证明尤其难以模拟。我们提出了一个新的神经智能体语言学习与交流框架(Neural-agent Language Learning and Communication framework,NeLLCom),在该框架中,成对的说话智能体和倾听智能体首先通过监督学习学习一种微型语言,随后通过强化学习对其进行优化以服务于交流。我们紧密遵循早期人类实验的设置,使用这一新框架成功复现了该权衡,而没有在智能体中硬编码特定偏差。我们认为,这是利用神经学习者研究语言普遍特征的关键一步。

英文摘要:

Artificial learners often behave differently from human learners in the context of neural agent-based simulations of language emergence and change. A common explanation is the lack of appropriate cognitive biases in these learners. However, it has also been proposed that more naturalistic settings of language learning and use could lead to more human-like results. We investigate this latter account focusing on the word-order/case-marking trade-off, a widely attested language universal that has proven particularly hard to simulate. We propose a new Neural-agent Language Learning and Communication framework (NeLLCom) where pairs of speaking and listening agents first learn a miniature language via supervised learning, and then optimize it for communication via reinforcement learning. Following closely the setup of earlier human experiments, we succeed in replicating the trade-off with the new framework without hard-coding specific biases in the agents. We see this as an essential step towards the investigation of language universals with neural learners.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑