paper-with-me

Papers

Maximum Spanning Trees Are Invariant to Temperature Scaling in Graph-based Dependency Parsing

2021-06-15 · Stefan Grünewald

Modern graph-based syntactic dependency parsers operate by predicting, for each token within a sentence, a probability distribution over its possible syntactic heads (i.e., all other tokens) and then extracting a maximum spanning tree from the resulting log-probabilities. Nowadays, virtually all such parsers utilize deep neural networks and may thus be susceptible to miscalibration (in particular, overconfident predictions). In this paper, we prove that temperature scaling, a popular technique for post-hoc calibration of neural networks, cannot change the output of the aforementioned procedure. We conclude that other techniques are needed to tackle miscalibration in graph-based dependency parsers in a way that improves parsing accuracy.

📄 PDF Abstract BibTeX arXiv:2106.08159

Code (0)

등록된 구현이 없습니다.

Tasks

Dependency ParsingSentence

Similar Papers 제목 키워드 기반

Spatial Scaling of Satellite Soil Moisture using Temporal Correlations and Ensemble Learning

2016-01-21 · Subit Chakrabarti, Jasmeet Judge, Tara Bongiovanni, Anand Rangarajan 외

A novel algorithm is developed to downscale soil moisture (SM), obtained at satellite scales of 10-40 km by utilizing its temporal correlations to historical auxiliary data at finer scales. Including such correlations dr…

Ensemble Learningregression

On Finding the K-best Non-projective Dependency Trees

2021-08-01 · ACL 2021 5 · Ran Zmigrod, Tim Vieira, Ryan Cotterell

The connection between the maximum spanning tree in a directed graph and the best dependency tree of a sentence has been exploited by the NLP community. However, for many dependency parsing schemes, an important detail o…

Dependency ParsingSentence

On Finding the $K$-best Non-projective Dependency Trees

2021-06-01 · Ran Zmigrod, Tim Vieira, Ryan Cotterell

The connection between the maximum spanning tree in a directed graph and the best dependency tree of a sentence has been exploited by the NLP community. However, for many dependency parsing schemes, an important detail o…

Dependency ParsingSentence

Simulating Hard Attention Using Soft Attention

2024-12-13 · Andy Yang, Lena Strobl, David Chiang, Dana Angluin

We study conditions under which transformers using soft attention can simulate hard attention, that is, effectively focus all attention on a subset of positions. First, we examine several subclasses of languages recogniz…

Hard Attention

Efficient Learning of Optimal Markov Network Topology with k-Tree Modeling

2018-01-21 · Liang Ding, Di Chang, Russell Malmberg, Aaron Martinez 외

The seminal work of Chow and Liu (1968) shows that approximation of a finite probabilistic system by Markov trees can achieve the minimum information loss with the topology of a maximum spanning tree. Our current paper g…