What are the Goals of Distributional Semantics?
This work provides a foundational perspective for NLP researchers by highlighting integration challenges across subfields, though it is incremental as it synthesizes existing insights without new empirical results.
The paper addresses the need for explicit long-term goals in distributional semantics to assess progress, concluding that future advancements must balance linguistic expressiveness with computational tractability.
Distributional semantic models have become a mainstay in NLP, providing useful features for downstream tasks. However, assessing long-term progress requires explicit long-term goals. In this paper, I take a broad linguistic perspective, looking at how well current models can deal with various semantic challenges. Given stark differences between models proposed in different subfields, a broad perspective is needed to see how we could integrate them. I conclude that, while linguistic insights can guide the design of model architectures, future progress will require balancing the often conflicting demands of linguistic expressiveness and computational tractability.