A Computational Study on Word Meanings and Their Distributed Representations via Polymodal Embedding
نویسندگان
چکیده
A distributed representation has become a popular approach to capturing a word meaning. Besides its success and practical value, however, questions arise about the relationships between a true word meaning and its distributed representation. In this paper, we examine such a relationship via polymodal embedding approach inspired by the theory that humans tend to use diverse sources in developing a word meaning. The result suggests that the existing embeddings lack in capturing certain aspects of word meanings which can be significantly improved by the polymodal approach. Also, we show distinct characteristics of different types of words (e.g. concreteness) via computational studies. Finally, we show our proposed embedding method outperforms the baselines in the word similarity measure tasks and the hypernym prediction tasks.
منابع مشابه
Word Type Effects on L2 Word Retrieval and Learning: Homonym versus Synonym Vocabulary Instruction
The purpose of this study was twofold: (a) to assess the retention of two word types (synonyms and homonyms) in the short term memory, and (b) to investigate the effect of these word types on word learning by asking learners to learn their Persian meanings. A total of 73 Iranian language learners studying English translation participated in the study. For the first purpose, 36 freshmen from an ...
متن کاملA Simple and Efficient Method to Generate Word Sense Representations
Distributed representations of words have boosted the performance of many Natural Language Processing tasks. However, usually only one representation per word is obtained, not acknowledging the fact that some words have multiple meanings. This has a negative effect on the individual word representations and the language model as a whole. In this paper we present a simple model that enables rece...
متن کاملA Multiplicative Model for Learning Distributed Text-Based Attribute Representations
In this paper we propose a general framework for learning distributed representations of attributes: characteristics of text whose representations can be jointly learned with word embeddings. Attributes can correspond to a wide variety of concepts, such as document indicators (to learn sentence vectors), language indicators (to learn distributed language representations), meta-data and side inf...
متن کاملDistributed Word Representations Improve NER for e-Commerce
This paper presents a case study of using distributed word representations, word2vec in particular, for improving performance of Named Entity Recognition for the eCommerce domain. We also demonstrate that distributed word representations trained on a smaller amount of in-domain data are more effective than word vectors trained on very large amount of out-of-domain data, and that their combinati...
متن کاملA Probabilistic Model for Semantic Word Vectors
Vector representations of words capture relationships in words’ functions and meanings. Many existing techniques for inducing such representations from data use a pipeline of hand-coded processing techniques. Neural language models offer principled techniques to learn word vectors using a probabilistic modeling approach. However, learning word vectors via language modeling produces representati...
متن کامل