Prathyusha Jwalapuram

Research Scientist, Rakuten, Singapore

Category: Coherence Modeling

[ACL 2022] Rethinking Self-Supervision Objectives for Coherence Modeling

Prathyusha Jwalapuram, Shafiq Joty, Xiang Lin

We build a generalizable coherence model that performs well on several downstream tasks by using contrastive training and a large global negative sample queue encoded by a momentum encoder.

[EACL 2021] Rethinking Coherence Modeling: Synthetic vs. Downstream Tasks

Tasnim Mohiuddin, Prathyusha Jwalapuram, Xiang Lin, Shafiq Joty

We conduct experiments on benchmarking well-known traditional and neural coherence models on synthetic sentence ordering tasks, and contrast this with their performance on three downstream applications: coherence evaluation for MT and summarization, and next utterance prediction in retrieval-based dialog.