Measuring the compositionality of noun-noun compounds over time
Leiden University(莱顿大学);University of Stuttgart(斯图加特大学);University of Malta(马耳他大学)
Prajit Dhar, Janis Pagel, Lonneke van der Plas
备注:
6 pages, 3 figures, To appear in the proceedings of the 1st International Workshop on Computational Approaches to Historical Language Change 2019 @ ACL 2019, Fixed typos, Increased figure sizes
We present work in progress on the temporal progression of compositionality in noun-noun compounds. Previous work has proposed computational methods for determining the compositionality of compounds. These methods try to automatically determine how transparent the meaning of the compound as a whole is with respect to the meaning of its parts. We hypothesize that such a property might change over time. We use the time-stamped Google Books corpus for our diachronic investigations, and first examine whether the vector-based semantic spaces extracted from this corpus are able to predict compositionality ratings, despite their inherent limitations. We find that using temporal information helps predicting the ratings, although correlation with the ratings is lower than reported for other corpora. Finally, we show changes in compositionality over time for a selection of compounds.
On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings
Indian Institute of Technology Kharagpur(印度理工学院卡拉格普尔分校);National Research University Higher School of Economics(国立研究型大学高等经济学院);Skolkovo Institute of Science and Technology(斯科尔科沃科学技术研究院);Universität Hamburg(汉堡大学)
在对名-名复合词(如海星、银行账户、游艇)意义的分布语义学解释中,成分多义的重要作用在很大程度上仍未得到解决(参见第二章)。明星的含义在海星vs.明星集群vs.明星运动员)。我们需要的不是对一个成分的不同含义进行平均的语义向量,而是消除歧义的成分向量,以便了解这些更具体的成分含义对整个复合词的含义有什么贡献。本文提出了一种新的方法来解决这个特定的问题的词义消歧:集扩展。我们以Mahabal等人开发的方法为基础。(2018)最初旨在解决类比问题。我们修改了他们的方法,使其能够解决复合成分的意义消歧问题。使用近9000种化合物的数据集进行的实验结果(LADEC,Gagné et al. 2019)表明,这种方法是成功的,但这种成功对化合物被证明的频率很敏感。
SemEval-2013 Task 4: Free Paraphrases of Noun Compounds
Radboud University Nijmegen(拉德堡德大学);Universidade de Lisboa(里斯本大学);QCRI, Qatar Foundation(卡塔尔基金会卡塔尔计算研究所);University of Ottawa(渥太华大学);Polish Academy of Sciences(波兰科学院);University of Southern California(南加州大学);University of Cambridge(剑桥大学);University College Dublin(都柏林大学学院)
Zero-Shot Generalization using Intrinsically Motivated Compositional Emergent Protocols
Indian Institute of Science(印度科学研究所)
人类语言被描述为一个制造\textit{use of finite means to express an unlimited array of thoughts}的系统。特别感兴趣的是组合性方面,由此,复合语言表达的含义可以从其组成部分的含义中推导出来。如果人工智能体能够开发出类似于人类语言的组合通信协议,它们就可以无缝地推广到看不见的组合。研究已经认识到好奇心在促进儿童语言发展方面的作用。在本文中,我们试图使用这种内在的反馈,诱导一个系统的和明确的原语言。我们演示了组合性如何使代理不仅与看不见的对象进行交互,而且还将技能从一个任务转移到另一个任务中的zero-shot设置:\textit{Can an agent, trained to `pull' and `push twice', `pull twice'?}。