Results 41 to 50 of about 32,474 (200)
Techno.Com, 2023 Tranportasi merupakan hal yang penting bagi masyarakat dalam mobilitas sehari-hari. Karena memiliki peranan penting dan dapat memudahkan kehidupan masyarakat, pemerintah mulai mengoptimalkan pembangunan sarana transportasi dan memulai inovasi digital ...
Mega Vebika Shyahrin +2 more
doaj +1 more source
Word embedding for social sciences: an interdisciplinary survey [PDF]
PeerJ Computer ScienceMachine learning models learn low-dimensional representations from complex high-dimensional data. Not only computer science but also social science has benefited from the advancement of these powerful tools.
Akira Matsui, Emilio Ferrara
doaj +2 more sources
Connection Science, 2022 The word embedding model word2vec tends to ignore the importance of a single word to the entire document, which affects the accuracy of the news text classification method.
Weidong Zhao +4 more
doaj +1 more source
Opening the Black Box: Finding Osgood’s Semantic Factors in Word2vec Space
Информатика и автоматизация, 2022 State-of-the-art models of artificial intelligence are developed in the black-box paradigm, in which sensitive information is limited to input-output interfaces, while internal representations are not interpretable.
Ilya Surov
doaj +1 more source
Corpus specificity in LSA and Word2vec: the role of out-of-domain documents
, 2017 Latent Semantic Analysis (LSA) and Word2vec are some of the most widely used word embeddings. Despite the popularity of these techniques, the precise mechanisms by which they acquire new semantic relations between words remain unclear.
Altszyler, Edgar +2 more
core +1 more source
Transactions of the Karelian Research Centre of the Russian Academy of Sciences, 2018 The problem of word sense disambiguation (WSD) is considered in the article. Set of synonyms (synsets) and sentences with these synonyms are taken. It is necessary to automatically select the meaning of the word in the sentence.
Andrew Krizhanovsky +2 more
doaj +1 more source
Scaling Word2Vec on Big Corpus [PDF]
Data Science and Engineering, 2019 Abstract Word embedding has been well accepted as an important feature in the area of natural language processing (NLP). Specifically, the Word2Vec model learns high-quality word embeddings and is widely used in various NLP tasks. The training of Word2Vec is sequential on a CPU due to strong dependencies between word–context pairs.
Bofang Li +5 more
openaire +2 more sources
Spoken Language Intent Detection using Confusion2Vec
, 2019 Decoding speaker's intent is a crucial part of spoken language understanding (SLU). The presence of noise or errors in the text transcriptions, in real life scenarios make the task more challenging.
Georgiou, Panayiotis +2 more
core +1 more source
SPINE: SParse Interpretable Neural Embeddings
, 2017 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.
Berg-Kirkpatrick, Taylor +4 more
core +1 more source
Semi-Supervised Instance Population of an Ontology using Word Vector Embeddings
, 2017 In many modern day systems such as information extraction and knowledge management agents, ontologies play a vital role in maintaining the concept hierarchies of the selected domain.
Ayesha, Buddhi +6 more
core +1 more source