Multiword expressions are a key problem for the development of large-scale, linguistically
sound natural language processing technology. This paper surveys the problem and some …

A central goal of modern generative grammar has been to discover invariant properties of
human languages that reflect “the innate schematism of mind that is applied to the data of …

This paper investigates the ability of artificial neural networks to judge the grammatical
acceptability of a sentence, with the goal of testing their linguistic competence. We introduce …

Abstract We introduce The Benchmark of Linguistic Minimal Pairs (BLiMP), a challenge set
for evaluating the linguistic knowledge of language models (LMs) on major grammatical …

Neural networks are a family of powerful machine learning models and this book focuses on
their application to natural language data. The first half of the book (Parts I and II) covers the …

One reason pretraining on self-supervised linguistic tasks is effective is that it teaches
models features that are helpful for language understanding. However, we want pretrained …

Construction Grammar explains how knowledge of language is organized in speakers'
minds. The central and radical claim of Construction Grammar is that linguistic knowledge …

This chapter highlights the fundamental assumptions shared by all constructionist
approaches, distinguishing them from mainstream generative grammar. In particular …

This book offers a highly accessible introduction to natural language processing, the field
that supports a variety of language technologies, from predictive text and email filtering to …

Most of the existing Neural Machine Translation (NMT) models focus on the conversion of
sequential data and do not directly use syntactic information. We propose a novel end-to …