Where's the Learning in Representation Learning for Compositional Semantics and the Case of Thematic Fit. (arXiv:2208.04749v1 [cs.CL])

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''. We find nuanced answers, depending on the task and its
relation to the training objective. We examine these representation learning
aspects in multi-task learning, where role prediction and role-filling are
supervised …

arxiv case learning representation representation learning semantics