Maximum Spanning Trees Are Invariant to Temperature Scaling in Graph-based Dependency Parsing
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Dependency ParsingSentenceSimilar Papers 제목 키워드 기반
Spatial Scaling of Satellite Soil Moisture using Temporal Correlations and Ensemble Learning
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 LearningregressionOn Finding the K-best Non-projective Dependency Trees
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 ParsingSentenceOn Finding the $K$-best Non-projective Dependency Trees
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 ParsingSentenceSimulating Hard Attention Using Soft Attention
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 AttentionEfficient Learning of Optimal Markov Network Topology with k-Tree Modeling
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…