paper-with-me

홈 › Papers

Applying Occam's Razor to Transformer-Based Dependency Parsing: What Works, What Doesn't, and What is Really Necessary

2020-10-23 · Stefan Grünewald, Annemarie Friedrich, Jonas Kuhn

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, previous works differ in various dimensions, including their choice of pre-trained language models and whether they use LSTM layers. With the aims of disentangling the effects of these choices and identifying a simple yet widely applicable architecture, we introduce STEPS, a new modular graph-based dependency parser. Using STEPS, we perform a series of analyses on the UD corpora of a diverse set of languages. We find that the choice of pre-trained embeddings has by far the greatest impact on parser performance and identify XLM-R as a robust choice across the languages in our study. Adding LSTM layers provides no benefits when using transformer-based embeddings. A multi-task training setup outputting additional UD features may contort results. Taking these insights together, we propose a simple but widely applicable parser architecture and configuration, achieving new state-of-the-art results (in terms of LAS) for 10 out of 12 diverse languages.

📄 PDF Abstract BibTeX arXiv:2010.12699

Code (2)

boschresearch/steps-parser 공식 구현 pytorch
sb-b/steps-parser pytorch

Tasks

Dependency ParsingPart-Of-Speech TaggingWord EmbeddingsXLM-R

Methods 이 논문이 사용한 방법론

XLM-R XLM-R
Tanh Activation 설명 없음
Sigmoid Activation 설명 없음
LSTM An LSTM is a type of recurrent neural network that addresses the vanishing gradient problem in vanilla…

Similar Papers 제목 키워드 기반

Applying Occam’s Razor to Transformer-Based Dependency Parsing: What Works, What Doesn’t, and What is Really Necessary

2021-08-01 · ACL (IWPT) 2021 8 · Stefan Grünewald, Annemarie Friedrich, Jonas Kuhn

The introduction of pre-trained transformer-based contextualized word embeddings has led to considerable improvements in the accuracy of graph-based parsers for frameworks such as Universal Dependencies (UD). However, pr…

Dependency ParsingWord EmbeddingsXLM-R

The Geometric Occam's Razor Implicit in Deep Learning

2021-11-30 · Benoit Dherin, Michael Munn, David G. T. Barrett

In over-parameterized deep neural networks there can be many possible parameter configurations that fit the training data exactly. However, the properties of these interpolating solutions are poorly understood. We argue …

ARCDeep Learning

Colab NAS: Obtaining lightweight task-specific convolutional neural networks following Occam's razor

2022-12-15 · Andrea Mattia Garavagno, Daniele Leonardis, Antonio Frisoli

The current trend of applying transfer learning from convolutional neural networks (CNNs) trained on large datasets can be an overkill when the target application is a custom and delimited problem, with enough data to tr…

GPUHardware Aware Neural Architecture SearchNeural Architecture SearchTransfer Learning

In-context learning and Occam's razor

2024-10-17 · Eric Elmoznino, Tom Marty, Tejas Kasetty, Leo Gagnon 외

A central goal of machine learning is generalization. While the No Free Lunch Theorem states that we cannot obtain theoretical guarantees for generalization without further assumptions, in practice we observe that simple…

Data CompressionIn-Context Learning

Do Language Models Follow Occam's Razor? An Evaluation of Parsimony in Inductive and Abductive Reasoning

2025-09-03 · Yunxin Sun, Abulhair Saparov arxiv

Non-deductive reasoning, encompassing inductive and abductive reasoning, is essential in addressing complex real-world questions. One key feature of inductive and abductive reasoning is that there are many valid hypothes…