Results 31 to 40 of about 16,624 (311)
A Gloss Composition and Context Clustering Based Distributed Word Sense Representation Model
Entropy, 2015 In recent years, there has been an increasing interest in learning a distributed representation of word sense. Traditional context clustering based models usually require careful tuning of model parameters, and typically perform worse on infrequent word ...
Tao Chen +3 more
doaj +1 more source
When FastText Pays Attention: Efficient Estimation of Word Representations using Constrained Positional Weighting [PDF]
Journal of Universal Computer Science, 2022 In 2018, Mikolov et al. introduced the positional language model, which has characteristics of attention-based neural machine translation models and which achieved state-of-the-art performance on the intrinsic word analogy task.
Vít Novotný +4 more
doaj +3 more sources
Proceedings of the 25th ACM International on Conference on Information and Knowledge Management, 2016 Distilling knowledge from a well-trained cumbersome network to a small one has recently become a new research topic, as lightweight neural networks with high performance are particularly in need in various resource-restricted systems. This paper addresses the problem of distilling word embeddings for NLP tasks.
Mou, Lili +5 more
openaire +2 more sources
Applied Sciences, 2019 To resolve lexical disagreement problems between queries and frequently asked questions (FAQs), we propose a reliable sentence classification model based on an encoder-decoder neural network.
Youngjin Jang, Harksoo Kim
doaj +1 more source
Cultural Cartography with Word Embeddings [PDF]
Poetics, 2020 Using the frequency of keywords is a classic approach in the formal analysis of text, but has the drawback of glossing over the relationality of word meanings. Word embedding models overcome this problem by constructing a standardized and continuous “meaning-space” where words are assigned a location based on relations of similarity to other words ...
Stoltz, Dustin, Taylor, Marshall
openaire +4 more sources
Information, 2015 Semantic features are very important for machine learning-based drug name recognition (DNR) systems. The semantic features used in most DNR systems are based on drug dictionaries manually constructed by experts.
Shengyu Liu +3 more
doaj +1 more source
Understanding and Creating Word Embeddings
The Programming HistorianWord embeddings allow you to analyze the usage of different terms in a corpus of texts by capturing information about their contextual usage. Through a primarily theoretical lens, this lesson will teach you how to prepare a corpus and train a word ...
Avery Blankenship +2 more
doaj +1 more source
GLTM: A Global and Local Word Embedding-Based Topic Model for Short Texts
IEEE Access, 2018 Short texts have become a kind of prevalent source of information, and discovering topical information from short text collections is valuable for many applications.
Wenxin Liang +4 more
doaj +1 more source
Gloss Alignment using Word Embeddings
2023 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops (ICASSPW), 2023 Capturing and annotating Sign language datasets is a time consuming and costly process. Current datasets are orders of magnitude too small to successfully train unconstrained \acf{slt} models. As a result, research has turned to TV broadcast content as a source of large-scale training data, consisting of both the sign language interpreter and the ...
Walsh, Harry +3 more
openaire +2 more sources
Learning Chinese Word Embeddings With Words and Subcharacter N-Grams
IEEE Access, 2019 Co-occurrence information between words is the basis of training word embeddings; besides, Chinese characters are composed of subcharacters, words made up by the same characters or subcharacters usually have similar semantics, but this internal ...
Ruizhi Kang +4 more
doaj +1 more source