Zobrazeno 1 - 10
of 76
pro vyhledávání: '"Wang, Harry Jiannan"'
In this paper, we present a denoising sequence-to-sequence (seq2seq) autoencoder via contrastive learning for abstractive text summarization. Our model adopts a standard Transformer-based architecture with a multi-layer bi-directional encoder and an
Externí odkaz:
http://arxiv.org/abs/2108.11992
Color is an essential component of graphic design, acting not only as a visual factor but also carrying cultural implications. However, existing research on algorithmic color palette generation and colorization largely ignores the cultural aspect. In
Externí odkaz:
http://arxiv.org/abs/2102.05231
With the advancement of deep learning, artificial intelligence (AI) has made many breakthroughs in recent years and achieved superhuman performance in various tasks such as object detection, reading comprehension, and video games. Generative Modeling
Externí odkaz:
http://arxiv.org/abs/2012.00744
Podcast summarization is different from summarization of other data formats, such as news, patents, and scientific papers in that podcasts are often longer, conversational, colloquial, and full of sponsorship and advertising information, which impose
Externí odkaz:
http://arxiv.org/abs/2011.08291
We introduce a new approach for abstractive text summarization, Topic-Guided Abstractive Summarization, which calibrates long-range dependencies from topic-level features with globally salient content. The idea is to incorporate neural topic modeling
Externí odkaz:
http://arxiv.org/abs/2010.10323
Podcast summary, an important factor affecting end-users' listening decisions, has often been considered a critical feature in podcast recommendation systems, as well as many downstream applications. Existing abstractive summarization approaches are
Externí odkaz:
http://arxiv.org/abs/2008.10648
Publikováno v:
In Decision Support Systems August 2019 123
Publikováno v:
In Decision Support Systems January 2017 93:11-25
Publikováno v:
In Information Sciences 20 January 2014 256:57-73
Publikováno v:
Information Systems Research, 2013 Sep 01. 24(3), 731-749.
Externí odkaz:
http://dx.doi.org/10.1287/isre.1120.0450