no code implementations • 19 Dec 2022 • Asish Ghoshal, Arash Einolghozati, Ankit Arun, Haoran Li, Lili Yu, Vera Gor, Yashar Mehdad, Scott Wen-tau Yih, Asli Celikyilmaz
Lack of factual correctness is an issue that still plagues state-of-the-art summarization systems despite their impressive progress on generating seemingly fluent summaries.
no code implementations • 10 Dec 2021 • Marjan Ghazvininejad, Vladimir Karpukhin, Vera Gor, Asli Celikyilmaz
We show that soft-prompt based conditional text generation can be improved with simple and efficient methods that simulate modeling the discourse structure of human written text.