Results 231 to 240 of about 24,198 (261)
, 2023 Some of the next articles are maybe not open access.
Related searches:
Related searches:
2021 Conference on Information Communications Technology and Society (ICTAS), 2021
Word embeddings are currently the most popular vector space model in Natural Language Processing. How we encode words is important because it affects the performance of many downstream tasks such as Machine Translation (MT), Information Retrieval (IR) and Automatic Speech Recognition (ASR).
Sibonelo Dlamini +3 more
openaire +1 more source
Word embeddings are currently the most popular vector space model in Natural Language Processing. How we encode words is important because it affects the performance of many downstream tasks such as Machine Translation (MT), Information Retrieval (IR) and Automatic Speech Recognition (ASR).
Sibonelo Dlamini +3 more
openaire +1 more source
Proceedings of the AAAI Conference on Artificial Intelligence, 2015
Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both ...
Yang Liu 0005 +3 more
openaire +1 more source
Most word embedding models typically represent each word using a single vector, which makes these models indiscriminative for ubiquitous homonymy and polysemy. In order to enhance discriminativeness, we employ latent topic models to assign topics for each word in the text corpus, and learn topical word embeddings (TWE) based on both ...
Yang Liu 0005 +3 more
openaire +1 more source
Word Embedding Evaluation and Combination
Proceedings of the Language Resources and Evaluation Conference, 2016no ...
Ghannay, Sahar +3 more
openaire +3 more sources
Abstract This chapter deals with the mathematical representation of words through vectors or embeddings which are the basis of modern language models. It starts by discussing the limits of the one-hot representation and continues with a section that presents traditional approaches based on the factorization of the word co-occurrence ...
Christophe Gaillac, Jérémy L'Hour
openaire +2 more sources
Christophe Gaillac, Jérémy L'Hour
openaire +2 more sources
Adaptive cross-contextual word embedding for word polysemy with unsupervised topic modeling
Knowledge-Based Systems, 2021Shuangyin Li, Haoyu Luo, Gansen Zhao
exaly
Task-specific dependency-based word embedding methods
Pattern Recognition Letters, 2022C -C Jay Kuo, , Chengwei Wei
exaly
Word Embeddings are Word Story Embeddings (and That's Fine)
2022Katrin Erk, Gabriella Chronis
openaire +1 more source