Zobrazeno 1 - 10
of 254
pro vyhledávání: '"Eiichiro Sumita"'
Publikováno v:
IEEE Access, Vol 10, Pp 92467-92480 (2022)
The generation of music lyrics by artificial intelligence (AI) is frequently modeled as a language-targeted sequence-to-sequence generation task. Formally, if we convert the melody into a word sequence, we can consider the lyrics generation task to b
Externí odkaz:
https://doaj.org/article/ef6b6b02aa924437889d74179c6c623f
Publikováno v:
IEEE Access, Vol 9, Pp 141571-141578 (2021)
Cross-lingual transfer is an important technique for low-resource language processing. Temporarily, most research on syntactic parsing works on the dependency structures. This work investigates cross-lingual parsing on another type of important synta
Externí odkaz:
https://doaj.org/article/6d88a42897eb4f50b2e3462f4fb5173d
Publikováno v:
IEEE Transactions on Artificial Intelligence. 3:518-525
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::68f295072ef31513ba4ff142f9a9ed7c
https://doi.org/10.1109/tai.2021.3123931
https://doi.org/10.1109/tai.2021.3123931
Publikováno v:
IEEE/ACM Transactions on Audio, Speech, and Language Processing. 30:330-339
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8055f55228ccbcf512b452df1db4674c
https://doi.org/10.1109/taslp.2021.3138714
https://doi.org/10.1109/taslp.2021.3138714
Publikováno v:
Journal of Natural Language Processing. 29:748-753
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::89c61cf59b108ba7ad9a3bfe98a38a8c
https://doi.org/10.5715/jnlp.29.748
https://doi.org/10.5715/jnlp.29.748
Publikováno v:
Journal of Natural Language Processing. 29:1254-1271
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::619f06fb7d9cadb3c4d2b6f2271044e3
https://doi.org/10.5715/jnlp.29.1254
https://doi.org/10.5715/jnlp.29.1254
Representation learning is the foundation of natural language processing (NLP). This work presents new methods to employ visual information as assistant signals to general NLP tasks. For each sentence, we first retrieve a flexible number of images ei
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::65bb971b0d08c37a6fc2646fa1359b59
http://arxiv.org/abs/2301.03344
http://arxiv.org/abs/2301.03344
Autor:
Hour Kaing, Sethserey Sam, Katsuhito Sudoh, Chenchen Ding, Eiichiro Sumita, Satoshi Nakamura, Masao Utiyama, Sopheap Seng
Publikováno v:
ACM Transactions on Asian and Low-Resource Language Information Processing. 20:1-16
As a highly analytic language, Khmer has considerable ambiguities in tokenization and part-of-speech (POS) tagging processing. This topic is investigated in this study. Specifically, a 20,000-sentence Khmer corpus with manual tokenization and POS-tag
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::e4a3bd576b0ecdaf18f4bc6375b4b81c
https://doi.org/10.1145/3464378
https://doi.org/10.1145/3464378
Publikováno v:
Neurocomputing. 451:46-56
In self-attention networks (SANs), positional embeddings are used to model order dependencies between words in the input sentence and are added with word embeddings to gain an input representation, which enables the SAN-based neural model to perform
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::455d3585c6fa2907244a7ca591aec886
https://doi.org/10.1016/j.neucom.2021.04.055
https://doi.org/10.1016/j.neucom.2021.04.055
Publikováno v:
2022 25th Conference of the Oriental COCOSDA International Committee for the Co-ordination and Standardisation of Speech Databases and Assessment Techniques (O-COCOSDA).
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7c5ab3f7c34ab03f48f3adc5ca1ed67
https://doi.org/10.1109/o-cocosda202257103.2022.9997818
https://doi.org/10.1109/o-cocosda202257103.2022.9997818