Popular word embedding methods such as word2vec and GloVe assign a single vector representation to each word, even if a word has multiple distinct meanings. Multi-sense embeddings instead provide different vectors for each sense of a word. However, they typically cannot serve as a drop-in replacement for conventional single-sense embeddings, because the correct sense vector needs to be selected for each word. In this work, we study the effect of multi-sense embeddings on the task of reverse dictionaries. We propose a technique to easily integrate them into an existing neural network architecture using an attention mechanism. Our experiments demonstrate that large improvements can be obtained when employing multi-sense embeddings both in the input sequence as well as for the target representation. An analysis of the sense distributions and of the learned attention is provided as well.
Coarse-Grained Sense Inventories Based on Semantic Matching between English Dictionaries
Nagoya Institute of Technology(名古屋工业大学);Muroran Institute of Technology(室兰工业大学);Chitose Institute of Science and Technology(千岁科学技术大学);Hokkaido University(北海道大学)
我们提出了一种方法来分组的同义词的一个词根据其字典意义。这些意义由一个大型的法语机器可读词典TLFi(Trésor de la langue française informatisé)定义,而同义词则由5个同义词词典(也适用于法语)给出。为了评估所提出的方法,我们手动构建了一个黄金标准,对于每个(单词,定义)对,并给出由5个同义词词典定义的同义词集合,4个词典编纂者指定他们判断为足够的同义词集合。虽然注释者之间的协议范围从67%到最好的88%,这取决于注释者对和正在考虑的同义词词典,我们提出的自动程序得分的精度为67%,召回率为71%。该方法与相关的工作,即,词义消歧,同义词词典的获取和WordNet的建设进行了比较。
How Do Lexical Senses Correspond Between Spoken German and German Sign Language?
Institute for Computational Linguistics, University of Heidelberg(计算语言学研究所,海德堡大学);Department of Computing Science, University of Aberdeen(计算机科学系,阿伯丁大学)
WordAlchemy: A transformer-based Reverse Dictionary
Dept. of Computer Engineering and Dept. of Computer Engineering and Information Technology Information Technology College of Engineering, Pune College of Engineering, Pune Maharashtra, India Maharashtra, India(计算机工程系和计算机工程与信息技术系,工程学院,比拉尔,马哈拉施特拉邦,印度)
Learning to Describe Phrases with Local and Global Contexts
The University of Tokyo(东京大学);Carnegie Mellon University(卡内基梅隆大学);Institute of Industrial Science, the University of Tokyo(东京大学生产技术研究所);National Institute of Informatics(国立信息学研究所)
LexMatcher: Dictionary-centric Data Collection for LLM-based Machine Translation
Zhejiang University(浙江大学);School of Engineering, Westlake University(西湖大学工程学院);Pattern Recognition Center, WeChat AI, Tencent Inc(腾讯公司微信AI模式识别中心);Institute of Advanced Technology, Westlake Institute for Advanced Study(西湖高等研究院先进技术研究所)