Better Boundary Prediction Does Not Guarantee Better Structural Representation
Michael Zhou, Markus Frohmann, Junghyun Min, En-Shiun Annie Lee
原文摘要
Punctuation marks often mark phrase boundaries, carrying linguistic information. Therefore, punctuation marks' abundance and feasibility as proxies of linguistic structure has led to suggestions that using punctuation marks to optimise on phrasal structure may help language models (LMs) improve their representations of argument, semantic, and syntactic structures. In this paper, we test the above claim in English across three primary LM architectures: decoder-only, encoder-only, and encoder-decoder LMs, by complementing traditional token prediction with punctuation restoration (PR). Our evidence, collected at the <1B parameter scale, suggests that optimising for boundary prediction does not necessarily guarantee higher-quality structural representation in decoder-only, encoder-decoder, and encoder-only LMs, failing to improve performance on downstream tasks that require understanding structure in linguistic input.
cs.CL