paper-with-me

홈 › Papers

Don't Stop Me Now! Using Global Dynamic Oracles to Correct Training Biases of Transition-Based Dependency Parsers

2017-04-01 · EACL 2017 4 · Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon

This paper formalizes a sound extension of dynamic oracles to global training, in the frame of transition-based dependency parsers. By dispensing with the pre-computation of references, this extension widens the training strategies that can be entertained for such parsers; we show this by revisiting two standard training procedures, early-update and max-violation, to correct some of their search space sampling biases. Experimentally, on the SPMRL treebanks, this improvement increases the similarity between the train and test distributions and yields performance improvements up to 0.7 UAS, without any computation overhead.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Active LearningDependency Parsing

Similar Papers 제목 키워드 기반

Early Stopping for Large Reasoning Models via Confidence Dynamics

2026-04-06 · Parsa Hosseini, Sumit Nawathe, Mahdi Salmani, Meisam Razaviyayn 외 arxiv

Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking. A key ch…

Generic Oracles for Structured Prediction

2021-08-01 · ACL (IWPT) 2021 8 · Christoph Teichmann, Antoine Venant

When learned without exploration, local models for structured prediction tasks are subject to exposure bias and cannot be trained without detailed guidance. Active Imitation Learning (AIL), also known in NLP as Dynamic O…

Imitation LearningPredictionStructured Prediction

Training Deterministic Parsers with Non-Deterministic Oracles

2013-01-01 · TACL 2013 1 · Yoav Goldberg, Joakim Nivre

Greedy transition-based parsers are very fast but tend to suffer from error propagation. This problem is aggravated by the fact that they are normally trained using oracles that are deterministic and incomplete in the se…

ARCvalid

Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing

2018-10-25 · Daniel Fernández-González, Carlos Gómez-Rodríguez

We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manag…

Dynamic Oracles for Top-Down and In-Order Shift-Reduce Constituent Parsing

2018-10-01 · EMNLP 2018 10 · Daniel Fern{\'a}ndez-Gonz{\'a}lez, Carlos G{\'o}mez-Rodr{\'\i}guez

We introduce novel dynamic oracles for training two of the most accurate known shift-reduce algorithms for constituent parsing: the top-down and in-order transition-based parsers. In both cases, the dynamic oracles manag…