Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Peizhu Gong"'
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 1, Pp 577-594 (2023)
Abstract Abstractive summarization (AS) aims to generate more flexible and informative descriptions than extractive summarization. Nevertheless, it often distorts or fabricates facts in the original article. To address this problem, some existing app
Externí odkaz:
https://doaj.org/article/b9fc7790bc874871b074263797899eae
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 6, Pp 6191-6209 (2023)
Abstract Question classification is an essential task in question answering (QA) systems. An effective and efficient question classification model can not only restrict the search space for answers, but also guide the QA system in selecting the optim
Externí odkaz:
https://doaj.org/article/7fe2c16d8957423dbb67c97cbad44d62
Publikováno v:
Complex & Intelligent Systems, Vol 9, Iss 5, Pp 4995-5012 (2023)
Abstract Dense video captioning (DVC) aims at generating description for each scene in a video. Despite attractive progress for this task, previous works usually only concentrate on exploiting visual features while neglecting audio information in the
Externí odkaz:
https://doaj.org/article/c077acec0ce14cd09db77ae66c88199a
Publikováno v:
PLoS ONE, Vol 18, Iss 2, p e0281275 (2023)
Vector-based retrieval have been widely adopted to process online users' diverse interests for recommendations. However, most of them utilize a single vector to represent user multiple interests (UMI), inevitably impairing the accuracy and diversity
Externí odkaz:
https://doaj.org/article/448b4952e287486494342688a6d1a3e8
Publikováno v:
IEEE Access, Vol 8, Pp 224837-224851 (2020)
Machine reading comprehension is a crucial and challenging task in natural language processing (NLP). Recently, knowledge graph (KG) embedding has gained massive attention as it can effectively provide side information for downstream tasks. However,
Externí odkaz:
https://doaj.org/article/f5d6e62da9bd44119a54697d59004022
Publikováno v:
IEEE Access, Vol 8, Pp 205216-205230 (2020)
Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwrit
Externí odkaz:
https://doaj.org/article/0227f8b0e0ff4db482889869c8a64264
Publikováno v:
Computers, Materials & Continua. 74:4203-4220
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Publikováno v:
IEEE Access, Vol 8, Pp 205216-205230 (2020)
Segmenting characters in an image is a classic yet challenging task in computer vision. Correctly determining boundaries of adhesive characters with various scales and shapes is essential for character segmentation, especially for separating handwrit
Publikováno v:
Journal of Information Hiding and Privacy Protection. 2:155-163