paper-with-me

Papers

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders

2019-04-03 · Andrew Drozdov, Pat Verga, Mohit Yadav, Mohit Iyyer, Andrew McCallum

We introduce deep inside-outside recursive autoencoders (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach predicts each word in an input sentence conditioned on the rest of the sentence and uses inside-outside dynamic programming to consider all possible binary trees over the sentence. At test time the CKY algorithm extracts the highest scoring parse. DIORA achieves a new state-of-the-art F1 in unsupervised binary constituency parsing (unlabeled) in two benchmark datasets, WSJ and MultiNLI.

📄 PDF Abstract BibTeX arXiv:1904.02142

Code (3)

iesl/diora 공식 구현 pytorch
i-machine-think/emergent_grammar_induction
rgalhama/diora pytorch

Tasks

Constituency ParsingSentence

Similar Papers 제목 키워드 기반

Unsupervised Latent Tree Induction with Deep Inside-Outside Recursive Auto-Encoders

2019-06-01 · NAACL 2019 6 · Andrew Drozdov, Patrick Verga, Mohit Yadav, Mohit Iyyer 외

We introduce the deep inside-outside recursive autoencoder (DIORA), a fully-unsupervised method for discovering syntax that simultaneously learns representations for constituents within the induced tree. Our approach pre…

Constituency Grammar InductionConstituency ParsingSentence

Unsupervised Labeled Parsing with Deep Inside-Outside Recursive Autoencoders

2019-11-01 · IJCNLP 2019 11 · Andrew Drozdov, Patrick Verga, Yi-Pei Chen, Mohit Iyyer 외

Understanding text often requires identifying meaningful constituent spans such as noun phrases and verb phrases. In this work, we show that we can effectively recover these types of labels using the learned phrase vecto…

Constituency Parsing

Grammar Induction from Visual, Speech and Text

2024-10-01 · Yu Zhao, Hao Fei, Shengqiong Wu, Meishan Zhang 외

Grammar Induction could benefit from rich heterogeneous signals, such as text, vision, and acoustics. In the process, features from distinct modalities essentially serve complementary roles to each other. With such intui…

Unsupervised Parsing with S-DIORA: Single Tree Encoding for Deep Inside-Outside Recursive Autoencoders

2020-11-01 · EMNLP 2020 11 · Andrew Drozdov, Subendhu Rongali, Yi-Pei Chen, Tim O{'}Gorman 외

The deep inside-outside recursive autoencoder (DIORA; Drozdov et al. 2019) is a self-supervised neural model that learns to induce syntactic tree structures for input sentences *without access to labeled training data*. …

Constituency Grammar InductionConstituency ParsingSentence

Improved Latent Tree Induction with Distant Supervision via Span Constraints

2021-09-10 · EMNLP 2021 11 · Zhiyang Xu, Andrew Drozdov, Jay Yoon Lee, Tim O'Gorman 외

For over thirty years, researchers have developed and analyzed methods for latent tree induction as an approach for unsupervised syntactic parsing. Nonetheless, modern systems still do not perform well enough compared to…

Constituency Parsing