paper-with-me

Papers

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, Mohit Iyyer, Andrew McCallum

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*. In this paper, we discover that while DIORA exhaustively encodes all possible binary trees of a sentence with a soft dynamic program, its vector averaging approach is locally greedy and cannot recover from errors when computing the highest scoring parse tree in bottom-up chart parsing. To fix this issue, we introduce S-DIORA, an improved variant of DIORA that encodes a single tree rather than a softly-weighted mixture of trees by employing a hard argmax operation and a beam at each cell in the chart. Our experiments show that through *fine-tuning* a pre-trained DIORA with our new algorithm, we improve the state of the art in *unsupervised* constituency parsing on the English WSJ Penn Treebank by 2.2-6{\%} F1, depending on the data used for fine-tuning.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Constituency Grammar InductionConstituency 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 Latent Tree Induction with Deep Inside-Outside Recursive Autoencoders

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

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 predic…

Constituency 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

Rule Augmented Unsupervised Constituency Parsing

2021-05-21 · Findings (ACL) 2021 8 · Atul Sahay, Anshul Nasery, Ayush Maheshwari, Ganesh Ramakrishnan 외

Recently, unsupervised parsing of syntactic trees has gained considerable attention. A prototypical approach to such unsupervised parsing employs reinforcement learning and auto-encoders. However, no mechanism ensures th…

Constituency Parsingreinforcement-learningReinforcement Learning (RL)

Deep Inside-outside Recursive Autoencoder with All-span Objective

2020-12-01 · COLING 2020 8 · Ruyue Hong, Jiong Cai, Kewei Tu

Deep inside-outside recursive autoencoder (DIORA) is a neural-based model designed for unsupervised constituency parsing. During its forward computation, it provides phrase and contextual representations for all spans in…

AllConstituency ParsingSentence