Generalization from Sparse Input

Abstract

Over the past decade, there has been an increasing awareness of the extent to which the speaker/hearer's language knowledge reflects the fine details of personal experience. This awareness can be seen in theoretical linguistics (e.g., Construction Grammar, various lexicalist theories, Cognitive Grammar, among others); in psycholinguistics (e.g., the Competition Model, constraint based, probabilistic, and connectionist models); and in computational linguistics (e.g., statistically-based approaches that rely on large-scale electronic corpora). In a curious way this reflects a pendulum swing back to older views that predate the generative era. But it is a pendulum swing with a difference. The emphasis over the past 50 years on the abstract nature of linguistic knowledge, and on ways in which linguistic generalizations often crucially refer to that abstract structure, has upped the ante for usage-based approaches. There is now a richer set of data and a more sophisticated awareness of the kinds of phenomena that want explaining. I am a firm believer in usage-based approaches. But I believe that usage has its place. We do more than simply record our past experiences, say, in some table of

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 37 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.