paper-with-me

Papers

An Empirical Study of Compound PCFGs

2021-03-03 · EACL (AdaptNLP) 2021 4 · Yanpeng Zhao, Ivan Titov

Compound probabilistic context-free grammars (C-PCFGs) have recently established a new state of the art for unsupervised phrase-structure grammar induction. However, due to the high space and time complexities of chart-based representation and inference, it is difficult to investigate C-PCFGs comprehensively. In this work, we rely on a fast implementation of C-PCFGs to conduct an evaluation complementary to that of~\citet{kim-etal-2019-compound}. We start by analyzing and ablating C-PCFGs on English treebanks. Our findings suggest that (1) C-PCFGs are data-efficient and can generalize to unseen sentence/constituent lengths; and (2) C-PCFGs make the best use of sentence-level information in generating preterminal rule probabilities. We further conduct a multilingual evaluation of C-PCFGs. The experimental results show that the best configurations of C-PCFGs, which are tuned on English, do not always generalize to morphology-rich languages.

📄 PDF Abstract BibTeX arXiv:2103.02298

Code (2)

zhaoyanpeng/cpcfg 공식 구현 pytorch
zhaoyanpeng/xcfg 공식 구현 pytorch

Tasks

Sentence

Similar Papers 제목 키워드 기반

Tensor Decomposition for Fast Parsing with Latent-Variable PCFGs

2012-12-01 · NeurIPS 2012 12 · Michael Collins, Shay B. Cohen

We describe an approach to speed-up inference with latent variable PCFGs, which have been shown to be highly effective for natural language parsing. Our approach is based on a tensor formulation recently introduced for …

Tensor Decomposition

PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols

2021-04-28 · NAACL 2021 4 · Songlin Yang, Yanpeng Zhao, Kewei Tu

Probabilistic context-free grammars (PCFGs) with neural parameterization have been shown to be effective in unsupervised phrase-structure grammar induction. However, due to the cubic computational complexity of PCFG repr…

Constituency Grammar InductionForm

Deep networks learn to parse uniform-depth context-free languages from local statistics

2026-01-31 · Jack T. Parley, Francesco Cagnetta, Matthieu Wyart arxiv

Understanding how the structure of language can be learned from sentences alone is a central question in both cognitive science and machine learning. Studies of the internal representations of Large Language Models (LLMs…

VLGrammar: Grounded Grammar Induction of Vision and Language

2021-03-24 · ICCV 2021 10 · Yining Hong, Qing Li, Song-Chun Zhu, Siyuan Huang

Cognitive grammar suggests that the acquisition of language grammar is grounded within visual structures. While grammar is an essential representation of natural language, it also exists ubiquitously in vision to represe…

ClusteringContrastive LearningImage RetrievalRetrieval+1

Neural Bi-Lexicalized PCFG Induction

2021-05-31 · ACL 2021 5 · Songlin Yang, Yanpeng Zhao, Kewei Tu

Neural lexicalized PCFGs (L-PCFGs) have been shown effective in grammar induction. However, to reduce computational complexity, they make a strong independence assumption on the generation of the child word and thus bile…

Constituency Grammar Induction