paper-with-me

홈 › Papers

An Empirical Exploration of Local Ordering Pre-training for Structured Prediction

2020-11-01 · Findings of the Association for Computational Linguistics 2020 · Zhisong Zhang, Xiang Kong, Lori Levin, Eduard Hovy

Recently, pre-training contextualized encoders with language model (LM) objectives has been shown an effective semi-supervised method for structured prediction. In this work, we empirically explore an alternative pre-training method for contextualized encoders. Instead of predicting words in LMs, we {``}mask out{''} and predict word order information, with a local ordering strategy and word-selecting objectives. With evaluations on three typical structured prediction tasks (dependency parsing, POS tagging, and NER) over four languages (English, Finnish, Czech, and Italian), we show that our method is consistently beneficial. We further conduct detailed error analysis, including one that examines a specific type of parsing error where the head is misidentified. The results show that pre-trained contextual encoders can bring improvements in a structured way, suggesting that they may be able to capture higher-order patterns and feature combinations from unlabeled data.

📄 PDF Abstract BibTeX

Code (1)

zzsfornlp/zmsp 공식 구현

Tasks

Dependency ParsingLanguage ModelingLanguage ModellingNERPOSPOS TaggingStructured Prediction

Similar Papers 제목 키워드 기반

HAMMER: Hamiltonian Curiosity Augmented Large Language Model Reinforcement

2025-09-25 · Ming Yang, Xiaofan Li, Zhiyuan Ma, Dengliang Shi 외 arxiv

Recent curriculum reinforcement learning for large language models (LLMs) typically rely on difficulty-based annotations for data filtering and ordering. However, such methods suffer from local optimization, where contin…

Reinforcement Learning

Can Graph Reordering Speed Up Graph Neural Network Training? An Experimental Study

2024-09-17 · Nikolai Merkel, Pierre Toussing, Ruben Mayer, Hans-Arno Jacobsen

Graph neural networks (GNNs) are a type of neural network capable of learning on graph-structured data. However, training GNNs on large-scale graphs is challenging due to iterative aggregations of high-dimensional featur…

CPUGPUGraph Neural Network

Cached Operator Reordering: A Unified View for Fast GNN Training

2023-08-23 · Julia Bazinska, Andrei Ivanov, Tal Ben-Nun, Nikoli Dryden 외

Graph Neural Networks (GNNs) are a powerful tool for handling structured graph data and addressing tasks such as node classification, graph classification, and clustering. However, the sparse nature of GNN computation po…

Graph AttentionGraph ClassificationNode Classification

Data Ordering Patterns for Neural Machine Translation: An Empirical Study

2019-09-23 · Siddhant Garg

Recent works show that ordering of the training data affects the model performance for Neural Machine Translation. Several approaches involving dynamic data ordering and data sharding based on curriculum learning have be…

Machine TranslationTranslation

Graph Spectral Regularization For Neural Network Interpretability

2019-05-01 · ICLR 2019 5 · Alexander Tong, David van Dijk, Jay Stanley, Guy Wolf 외

Deep neural networks can learn meaningful representations of data. However, these representations are hard to interpret. For example, visualizing a latent layer is generally only possible for at most three dimensions. Ne…