摘要
由一名新闻记者-机器人与机器学习日报的工作人员新闻编辑每日新闻-根据新闻报道的预印摘要,我们的记者获得了新闻报道的基本信息以下报价来源于BI orxiv.org：“语言模型(LMs)，它是经过训练的神经序列预测器，用于建模在整个过程中的分布。”自然语言文本在机器等人类语言技术中起着核心作用翻译和信息检索。他们也为人类语言的科学研究做出了贡献它本身，使我们能够在长期存在的问题上取得进展，这些问题涉及到语言的可学习性、最优性和通用性人类语言的主要特征。在人际交往的研究中存在许多类似的问题非人类动物——在许多情况下，我们对这些动物的信号只有初步的了解。结构和用途。神经序列模型能帮助我们理解这些动物通讯系统吗也是？我们利用这些模型来描述抹香鲸的结构和信息含量发声。抹香鲸（Physeter ma crocephalus）从事复杂、协调的行为，如在黑暗的海洋中觅食和航行，同时交换有节奏的咔嗒声不知道作为CODA。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning DailyNews Daily News - According to news reporting based on a preprint abstract, our journalists obtained thefollowing quote sourced from bi orxiv.org:“Language models (LMs), which are neural sequence predictors trained to model di stributions overnatural language texts, have come to play a central role in hum an language technologies like machinetranslation and information retrieval. The y have also contributed to the scientific study of human languageitself, enabli ng progress on long-standing questions about the learnability, optimality, and u niversality ofkey features of human languages. Many analogous questions exist i n the study of communication betweennon-human animals—for which, in many case s, we have only a preliminary understanding of signals\ ’structure and use. Can neural sequence models help us understand these animal communication systemsas well? We use these models to characterize the structure and information content of sperm whalevocalizations. Sperm whales (Physeter ma crocephalus) engage in complex, coordinated behaviours likeforaging and navigat ion in the darkness of the ocean while exchanging sequences of rhythmic clicks known as codas.
NETL
NSTL