no code implementations • 9 Aug 2022 • Mughilan Muthupari, Samrat Halder, Asad Sayeed, Yuval Marton
Observing that for certain NLP tasks, such as semantic role prediction or thematic fit estimation, random embeddings perform as well as pretrained embeddings, we explore what settings allow for this and examine where most of the learning is encoded: the word embeddings, the semantic role embeddings, or ``the network''.