paper-with-me

Papers

The Return of Lexical Dependencies: Neural Lexicalized PCFGs

2020-07-29 · Hao Zhu, Yonatan Bisk, Graham Neubig

In this paper we demonstrate that $\textit{context free grammar (CFG) based methods for grammar induction benefit from modeling lexical dependencies}$. This contrasts to the most popular current methods for grammar induction, which focus on discovering $\textit{either}$ constituents $\textit{or}$ dependencies. Previous approaches to marry these two disparate syntactic formalisms (e.g. lexicalized PCFGs) have been plagued by sparsity, making them unsuitable for unsupervised grammar induction. However, in this work, we present novel neural models of lexicalized PCFGs which allow us to overcome sparsity problems and effectively induce both constituents and dependencies within a single model. Experiments demonstrate that this unified framework results in stronger results on both representations than achieved when modeling either formalism alone. Code is available at https://github.com/neulab/neural-lpcfg.

📄 PDF Abstract BibTeX arXiv:2007.15135

Code (3)

neulab/neural-lpcfg 공식 구현 pytorch
sustcsonglin/TN-PCFG pytorch
zhaoyanpeng/xcfg pytorch

Similar Papers 제목 키워드 기반

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

ALP: Data Augmentation using Lexicalized PCFGs for Few-Shot Text Classification

2021-12-16 · Hazel Kim, Daecheol Woo, Seong Joon Oh, Jeong-Won Cha 외

Data augmentation has been an important ingredient for boosting performances of learned models. Prior data augmentation methods for few-shot text classification have led to great performance boosts. However, they have no…

ClassificationData AugmentationFew-Shot Text ClassificationSemi-Supervised Text Classification+3

A Formal Model for Plausible Dependencies in Lexicalized Tree Adjoining Grammar

2012-09-01 · WS 2012 9 · Laura Kallmeyer, Marco Kuhlmann

Delexicalized Word Embeddings for Cross-lingual Dependency Parsing

2017-04-01 · EACL 2017 4 · Mathieu Dehouck, Pascal Denis

This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language. Specifically, this approac…

Cross-Lingual TransferDependency ParsingWord Embeddings

Unlexicalized Transition-based Discontinuous Constituency Parsing

2019-02-24 · TACL 2019 3 · Maximin Coavoux, Benoît Crabbé, Shay B. Cohen

Lexicalized parsing models are based on the assumptions that (i) constituents are organized around a lexical head (ii) bilexical statistics are crucial to solve ambiguities. In this paper, we introduce an unlexicalized t…

Constituency Parsing