1 code implementation • EMNLP (ACL) 2021 • Shunyo Kawamoto, Yu Sawai, Kohei Wakimoto, Peinan Zhang
Working with a wide range of annotators with the same attributes is crucial, as in real-world applications.
1 code implementation • 4 Oct 2024 • Akihiko Kato, Masato Mita, Soichiro Murakami, Ukyo Honda, Sho Hoshino, Peinan Zhang
In this study, we collaborate with in-house ad creators to refine the CAMERA references and develop an alternative ATG evaluation dataset called FaithCAMERA, in which the faithfulness of references is guaranteed.
1 code implementation • 12 Aug 2024 • Peinan Zhang, Yusuke Sakai, Masato Mita, Hiroki Ouchi, Taro Watanabe
With the increase in the more fluent ad texts automatically created by natural language generation technology, it is in the high demand to verify the quality of these creatives in a real-world setting.
1 code implementation • 17 Jun 2024 • Ukyo Honda, Tatsushi Oka, Peinan Zhang, Masato Mita
Recent models for natural language understanding are inclined to exploit simple patterns in datasets, commonly known as shortcuts.
no code implementations • 8 Mar 2024 • Sho Hoshino, Akihiko Kato, Soichiro Murakami, Peinan Zhang
Rather, we find a superiority of the Wikipedia domain over the NLI domain for these languages, in contrast to prior studies that focused on NLI as training data.
1 code implementation • 10 Jan 2024 • Yuu Jinnai, Ukyo Honda, Tetsuro Morimura, Peinan Zhang
We propose two variants of MBR, Diverse MBR (DMBR) and $k$-medoids MBR (KMBR), methods to generate a set of sentences with high quality and diversity.
1 code implementation • 21 Sep 2023 • Masato Mita, Soichiro Murakami, Akihiko Kato, Peinan Zhang
In response to the limitations of manual ad creation, significant research has been conducted in the field of automatic ad text generation (ATG).
no code implementations • 22 Jun 2023 • Soichiro Murakami, Sho Hoshino, Peinan Zhang
Natural language generation methods have emerged as effective tools to help advertisers increase the number of online advertisements they produce.
no code implementations • 2 Jun 2022 • Tetsuro Morimura, Kazuhiro Ota, Kenshi Abe, Peinan Zhang
In this work, we first introduce Monte Carlo Tree Learning (MCTL), an adaptation of MCTS for online RL setups.
no code implementations • NAACL (ACL) 2022 • Soichiro Murakami, Peinan Zhang, Sho Hoshino, Hidetaka Kamigaito, Hiroya Takamura, Manabu Okumura
Writing an ad text that attracts people and persuades them to click or act is essential for the success of search engine advertising.
no code implementations • NAACL 2021 • Hidetaka Kamigaito, Peinan Zhang, Hiroya Takamura, Manabu Okumura
Although there are many studies on neural language generation (NLG), few trials are put into the real world, especially in the advertising domain.