Sound-Word2Vec: Learning Word Representations Grounded in Sounds
نویسندگان
چکیده
To be able to interact better with humans, it is crucial for machines to understand sound – a primary modality of human perception. Previous works have used sound to learn embeddings for improved generic textual similarity assessment. In this work, we treat sound as a first-class citizen, studying downstream textual tasks which require aural grounding. To this end, we propose sound-word2vec – a new embedding scheme that learns specialized word embeddings grounded in sounds. For example, we learn that two seemingly (semantically) unrelated concepts, like leaves and paper are similar due to the similar rustling sounds they make. Our embeddings prove useful in textual tasks requiring aural reasoning like text-based sound retrieval and discovering foley sound effects (used in movies). Moreover, our embedding space captures interesting dependencies between words and onomatopoeia and outperforms prior work on aurallyrelevant word relatedness datasets such as AMEN and ASLex.
منابع مشابه
Evaluating distributed word representations for capturing semantics of biomedical concepts
Recently there is a surge in interest in learning vector representations of words using huge corpus in unsupervised manner. Such word vector representations, also known as word embedding, have been shown to improve the performance of machine learning models in several NLP tasks. However efficiency of such representation has not been systematically evaluated in biomedical domain. In this work ou...
متن کاملAcquiring distributed representations for verb-object pairs by using word2vec
We propose three methods for obtaining distributed representations for verb-object pairs in predicated argument structures by using word2vec. Word2vec is a method for acquiring distributed representations for a word by retrieving a weight matrix in neural networks. First, we analyze a large amount of text with an HPSG parser; then, we obtain distributed representations for the verb-object pairs...
متن کاملMultiVec: a Multilingual and Multilevel Representation Learning Toolkit for NLP
We present MultiVec, a new toolkit for computing continuous representations for text at different granularity levels (word-level or sequences of words). MultiVec includes Mikolov et al. [2013b]’s word2vec features, Le and Mikolov [2014]’s paragraph vector (batch and online) and Luong et al. [2015]’s model for bilingual distributed representations. MultiVec also includes different distance measu...
متن کاملSparse Word Embeddings Using ℓ1 Regularized Online Learning
Recently, Word2Vec tool has attracted a lot of interest for its promising performances in a variety of natural language processing (NLP) tasks. However, a critical issue is that the dense word representations learned in Word2Vec are lacking of interpretability. It is natural to ask if one could improve their interpretability while keeping their performances. Inspired by the success of sparse mo...
متن کاملSPINE: SParse Interpretable Neural Embeddings
Prediction without justification has limited utility. Much of the success of neural models can be attributed to their ability to learn rich, dense and expressive representations. While these representations capture the underlying complexity and latent trends in the data, they are far from being interpretable. We propose a novel variant of denoising k-sparse autoencoders that generates highly ef...
متن کامل