TreeMix: Compositional constituency-based data augmentation for natural language understanding

L Zhang, Z Yang, D Yang - ar**
A Nagy, DP Lakatos, B Barta, P Nanys, J Ács - ar**
that is applicable to machine translation. We extract corresponding subtrees from the …

Learning a grammar inducer from massive uncurated instructional videos

S Zhang, L Song, L **, H Mi, K Xu, D Yu… - arxiv preprint arxiv …, 2022 - arxiv.org
Video-aided grammar induction aims to leverage video information for finding more accurate
syntactic grammars for accompanying text. While previous work focuses on building systems …

Revisiting the practical effectiveness of constituency parse extraction from pre-trained language models

T Kim - arxiv preprint arxiv:2211.00479, 2022 - arxiv.org
Constituency Parse Extraction from Pre-trained Language Models (CPE-PLM) is a recent
paradigm that attempts to induce constituency parse trees relying only on the internal …

Unsupervised discontinuous constituency parsing with mildly context-sensitive grammars

S Yang, RP Levy, Y Kim - arxiv preprint arxiv:2212.09140, 2022 - arxiv.org
We study grammar induction with mildly context-sensitive grammars for unsupervised
discontinuous parsing. Using the probabilistic linear context-free rewriting system (LCFRS) …