April 1 Colloquium: The Case for Reviving Discourse Relations in NLG -- Michael White

Talk Abstract: Neural methods for natural language generation arrived with much fanfare a few years ago with their promise of flexible, end-to-end trainable models.  However, recent studies have revealed their inability to produce satisfactory output for longer or more complex texts. To address this issue, I will first discuss using tree-structured semantic representations that include discourse relations, like those used in traditional rule-based NLG systems, for better discourse-level structuring and sentence-level planning. I will then introduce a constrained decoding approach for sequence-to-sequence models that leverages this representation to improve semantic correctness on a conversational weather dataset as well as the E2E Challenge dataset.  Next, I will examine whether it is beneficial to include discourse relations in the input to a neural reimplementation of a classic NLG system, Methodius, using both LSTM and pre-trained language models.  Here, we find that these models struggle to correctly express Methodius’s similarity and contrast comparisons unless the corresponding RST relations are included in the inputs. Finally, to investigate whether discourse relations pay off in a broad coverage setting, I will report on experiments using pre-trained models with the Penn Discourse Tree Bank (PDTB) to generate texts with correctly realized discourse relations. Our results suggest that including discourse relation information in the input of the model significantly improves the consistency with which it produces a correctly realized discourse relation in the output, and also better matches the distribution of connective choices in the corpus.

Location: 2:00-3:00 p.m. on Friday, April 1st on Zoom (password: CS2022)

Note: CS2003 students attending in person in Sennott Square room 5317 must sign in and out of the event.

Biosketch: Michael White is a Professor in the Department of Linguistics at The Ohio State University. His research has focused on NLG in dialogue with an emphasis on surface realization, extending also to paraphrasing for ambiguity avoidance and data augmentation in the context of Ohio State's virtual patient dialogue system. He co-organized the NSF Workshop on Shared Tasks in NLG which provided a crucial impetus for the initial shared tasks in NLG, and he was a co-organizer of the first surface realization shared task. Since 2018, Dr. White has been a frequent collaborator with conversational AI researchers at Facebook/Meta.

Host: Daniel Mosse

News Type