Computational Models of the Emergence and Diachronic Change of Multi-Word Expression Meanings

多词表达意义的出现和历时变化的计算模型

• 批准号: 462212526
• 负责人: Professorin Dr. Sabine Schulte im Walde
• 金额: --
• 依托单位: Institut für Maschinelle Sprachverarbeitung (IMS)
• 依托单位国家: 德国
• 项目类别: Research Grants
• 资助国家: 德国
• 项目状态: 未结题
• 来源: https://gepris.dfg.de/gepris/projekt/462212526?language=en
• 关键词: Computational; Models; Emergence; Diachronic; Change

In Natural Language Processing (NLP), combinations of words are considered multi-word expressions (MWEs) if they are semantically idiosyncratic to some degree, i.e., the meaning of the combination is not entirely (or even not at all) predictable from the meanings of the constituents. MWEs subsume multiple morpho-syntactic types, including noun compounds (such as "flea market") and particle verbs (such as "give up"). They have been explored extensively and across research disciplines from synchronic perspectives, but state-of-the-art studies are lacking empirical large-scale approaches towards diachronic models of MWE meaning.Our project SemChangeMWE goes beyond the restricted synchronic concept of MWE meaning and provides a novel perspective on MWE emergence, MWE meaning changes and MWE compositionality (i.e., meaning transparency) by computationally modelling their diachronic properties and changes of properties. We selected the two multifaceted MWE types noun compounds and particle verbs to explore them cross-linguistically for German and English. The project brings together our expertises in (a) computational models of MWE compositionality and meaning analogy, (b) computational models of diachronic meaning changes and meaning divergences in language variation, and (c) datasets of meaning components and meaning relatedness, in order to address the interdisciplinary lack of computational diachronic models of MWE meaning.Methodologically, we will exploit qualitative and quantitative approaches (such as statistical measures of productivity; distributional, information-theoretic and topic- and graph-based probabilistic models; visualisation of collocational strength) and enhance vector representations and computational algorithms to shed light on (i) synchronically salient empirical characteristics of MWEs at the time of emergence (such as frequency, generality, grammatical variation), (ii) diachronic MWE meaning changes, (iii) the role of synchronic and diachronic polysemy in MWE sense innovation and reduction, and (iv) analogical developments of MWE meanings with regard to their present-day compositionality. To enable extensive interdisciplinary assessment and validation for theoretical and computational research, we will evaluate our empirical knowledge and computational models not only on general semantic-change benchmarks and MWE-specific novel change datasets, but also (i) by validating them against theory-driven categorisations of MWEs; (ii) by applying them to further language variation tasks (i.e., domain-/register- and dialect-specific sense divergences), and (iii) by integrating them into statistical machine translation as an external NLP application.

在自然语言处理（NLP）中，如果单词组合在语义上具有一定程度的特殊性，即组合的含义不能完全（甚至根本不能）从成分的含义中预测，则它们被视为多词表达（MWE）。 MWE 包含多种形态句法类型，包括名词复合词（例如“跳蚤市场”）和助词动词（例如“放弃”）。它们已经从共时的角度跨研究学科进行了广泛的探索，但最先进的研究缺乏对 MWE 意义的历时模型的大规模实证方法。我们的项目 SemChangeMWE 超越了 MWE 意义的受限共时概念，并通过对 MWE 的历时模型进行计算建模，为 MWE 的出现、MWE 意义变化和 MWE 组合性（即意义透明度）提供了新颖的视角。 属性和属性的变化。我们选择了两种多方面的 MWE 类型名词复合词和助词动词来跨语言地探索德语和英语。该项目汇集了我们在以下方面的专业知识：(a) MWE 组成性和意义类比的计算模型，(b) 语言变异中历时意义变化和意义分歧的计算模型，以及 (c) 意义成分和意义相关性的数据集，以解决跨学科缺乏 MWE 意义计算历时模型的问题。在方法上，我们将利用定性和定量方法（例如统计测量） 生产力；分布、信息论以及基于主题和图的概率模型；搭配强度的可视化）并增强向量表示和计算算法，以阐明（i）MWE出现时的同步显着经验特征（例如频率、普遍性、语法变异），（ii）历时MWE含义变化，（iii）共时和历时的作用 MWE 中的多义性意味着创新和简化，以及 (iv) MWE 含义在当今组合性方面的类比发展。为了对理论和计算研究进行广泛的跨学科评估和验证，我们将不仅根据一般语义变化基准和 MWE 特定的新颖变化数据集来评估我们的经验知识和计算模型，而且（i）通过根据理论驱动的 MWE 分类来验证它们； (ii) 将它们应用于进一步的语言变异任务（即域/语域和方言特定的意义分歧），以及 (iii) 将它们作为外部 NLP 应用程序集成到统计机器翻译中。