In recent years, central components of a new approach to linguistics, the Minimalist Program (MP) have come closer to physics. Features of the Minimalist Program, such as the unconstrained nature of recursive Merge, the operation of the Labeling Algorithm that only operates at the interface of Narrow Syntax with the Conceptual-Intentional and the Sensory-Motor interfaces, the difference between pronounced and un-pronounced copies of elements in a sentence and the build-up of the Fibonacci sequence in the syntactic derivation of sentence structures, are directly accessible to representation in terms of algebraic formalism. Although in our scheme linguistic structures are classical ones, we find that an interesting and productive isomorphism can be established between the MP structure, algebraic structures and many-body field theory opening new avenues of inquiry on the dynamics underlying some central aspects of linguistics.
Zero-shot Cross-Linguistic Learning of Event Semantics
Indiana University(印第安纳大学);Rutgers University(罗格斯大学);University of Pittsburgh(匹兹堡大学);University of Edinburgh(爱丁堡大学);New York University Abu Dhabi(纽约大学阿布扎比分校)
On the Integration of LinguisticFeatures into Statistical and Neural Machine Translation
Dublin City University(都柏林城市大学);School of Computing(计算机学院)
新的机器翻译(MT)技术正在迅速出现,并且伴随着它们,实现人类平等的大胆主张,例如:(i)产生的结果接近“平均双语人类翻译者所实现的准确性”(Wu等人,2017 b)或(ii)“与专业翻译人员相比,翻译质量与人类同等”(Hassan等人,2018)已经看到了曙光(Laubli et al.,2018年)。除了这些论文中的许多人自己对人类平等的定义之外,这些耸人听闻的说法往往没有得到对翻译所涉及的所有方面的完整分析的支持。确定机器翻译统计方法的优势与人类翻译方式之间的差异是我们研究的出发点。通过观察机器翻译输出和语言学理论,我们能够确定一些剩余的问题。这些问题从简单的数字和性别一致错误到更复杂的现象,如体值和时态的正确翻译。我们的实验证实,与其他研究一起(Bentivogli等人,2016年),神经MT在许多方面已经超过了统计MT。然而,一些问题仍然存在,另一些问题已经出现。我们涵盖了一系列与将特定语言特征整合到统计和神经MT中相关的问题,旨在分析其中一些问题并提供解决方案。我们的工作重点是解决围绕语言学和机器翻译之间的复杂关系的三个主要研究问题。我们识别出了自动翻译系统所缺乏的语言信息,以便产生更准确的翻译,并将额外的功能集成到现有的管道中。我们确定过度泛化或“算法偏见”作为神经MT的潜在缺点,并将其与许多剩余的语言问题联系起来。
Investigation of learning abilities on linguistic features in sequence-to-sequence text-to-speech synthesis
National Institute of Informatics(国立信息学研究所);SOKENDAI (The Graduate University for Advanced Studies)(综合研究大学院大学);Centre for Speech Technology Research, University of Edinburgh(爱丁堡大学语音技术研究中心)
Gaussian Smoothen Semantic Features (GSSF) -- Exploring the Linguistic Aspects of Visual Captioning in Indian Languages (Bengali) Using MSCOCO Framework
Computer & Information Science & Engineering Department, University of Florida(佛罗里达大学计算机与信息科学与工程系)
Donostia International Physics Center(多诺斯蒂亚国际物理中心);Ikerbasque Foundation for Science(伊凯巴斯克科学基金会);Institute of Physics, Johannes Gutenberg University(约翰内斯·古腾堡大学物理系);Faculty of Environment and Information Sciences, Yokohama National University(横滨国立大学环境与信息科学学院)
Tracking the emergence of linguistic structure in self-supervised models learning from speech
Institute for Logic, Language and Computation, University of Amsterdam(阿姆斯特丹大学逻辑、语言与计算研究所);Centre for Language Studies, Radboud University(拉德堡德大学语言研究中心);Cognitive Science and Artificial Intelligence, Tilburg University(蒂尔堡大学认知科学与人工智能系)
Aspects of Terminological and Named Entity Knowledge within Rule-Based Machine Translation Models for Under-Resourced Neural Machine Translation Scenarios
Insight Centre for Data Analytics, Data Science Institute, National University of Ireland Galway(爱尔兰国立高威大学数据科学研究所(Insight数据分析中心));United Language Group(联合语言集团)
On Implementing an HPSG theory -- Aspects of the logical architecture, the formalization, and the implementation of head-driven phrase structure grammars
本文介绍了HPSG理论的形式化和实现所涉及的一些方面。在此基础上,对Carpenter(1992)和King(1989,1994)的逻辑结构作为HPSGII(Pollard and Sag 1994)的基础的有效性进行了简要的比较。在HPSGII架构和各种计算系统(ALE,巨魔,CUF和TFS)中表达HPSG理论的可能性进行了讨论。除了对可能性进行形式表征外,本文还考察了具有一定语言理据的约束条件的具体选择,即词汇、结构许可和语法原则。本文以Hinrichs和Nakazawa(1994)提出的一个德语理论的ALE实现为例,并在附录中给出了ALE文法。
Convergent Representations of Linguistic Constructions in Human and Artificial Neural Systems
Department of English and American Studies, University Erlangen-Nuremberg(英语与美国研究系,埃尔朗根-纽伦堡大学);Pattern Recognition Lab, University Erlangen-Nuremberg(模式识别实验室,埃尔朗根-纽伦堡大学);Neuromodulation and Neuroprosthetics, University Hospital Mannheim, University Heidelberg(神经调控与神经假体,曼海姆大学医院,海德堡大学);BGU Ludwigshafen, Germany(吕贝克大学吕贝克分校,德国);Neuroscience Lab, University Hospital Erlangen(神经科学实验室,埃尔朗根大学医院)