no code implementations • 20 May 2024 • Chen Huang, Yiping Jin, Ilija Ilievski, Wenqiang Lei, Jiancheng Lv
To address this issue, interactive data annotation utilizes an annotation model to provide suggestions for humans to approve or correct.
1 code implementation • 23 Feb 2024 • Yiping Jin, Leo Wanner, Alexander Shvets
A recent proposal in this direction is HateCheck, a suite for testing fine-grained model functionalities on synthesized data generated using templates of the kind "You are just a [slur] to me."
no code implementations • 4 May 2023 • Yiping Jin, Leo Wanner, Vishakha Laxman Kadam, Alexander Shvets
As pointed out by several scholars, current research on hate speech (HS) recognition is characterized by unsystematic data creation strategies and diverging annotation schemata.
1 code implementation • 7 Jun 2022 • Yiping Jin, Vishakha Kadam, Dittaya Wanvarie
We propose generating story plots using off-the-shelf PLMs while maintaining the benefit of content planning to generate cohesive and contentful stories.
1 code implementation • NAACL 2021 • Yiping Jin, Akshay Bhatia, Dittaya Wanvarie
We then train interim models with individual candidate seed words.
1 code implementation • NAACL (TextGraphs) 2021 • Yiping Jin, Vishakha Kadam, Dittaya Wanvarie
The widely used advertising content taxonomy (IAB taxonomy) consists of 23 coarse-grained categories and 355 fine-grained categories.
1 code implementation • 11 Feb 2021 • Yiping Jin, Akshay Bhatia, Dittaya Wanvarie, Phu T. V. Le
We propose a sequence-to-sequence (seq2seq) transformer model to generate slogans from a brief company description.
no code implementations • IJCNLP 2019 • Nontawat Charoenphakdee, Jongyeong Lee, Yiping Jin, Dittaya Wanvarie, Masashi Sugiyama
We consider a document classification problem where document labels are absent but only relevant keywords of a target class and unlabeled documents are given.
no code implementations • IJCNLP 2017 • Yiping Jin, Dittaya Wanvarie, Phu Le
In this paper we propose a lightly-supervised framework to rapidly build text classifiers for contextual advertising.