====== Label Bias Problem ======

===== Papers =====
  * [[https://repository.upenn.edu/cgi/viewcontent.cgi?article=1162&context=cis_papers|Lafferty et al 2001 - Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data]] Introduced the label bias problem, which is present in Maximum-Entropy Markov Models (MEMMs) but not Conditional Random Fields (CRFs).  This drawback of MEMMs was one of the main reasons for inventing CRFs
  * [[https://arxiv.org/pdf/1808.10006.pdf|Murray & Chiang 2018 - Correcting Length Bias in Neural Machine Translation]] Argues that the beam search problem in NMT occurs because of the label bias problem (see section 2)
  * [[https://arxiv.org/pdf/1603.06042.pdf|Andor et al 2016 - Globally Normalized Transition-Based Neural Networks]] Proves that global models can be strictly more expressive than local models.
  * [[https://www.aclweb.org/anthology/N19-1171.pdf|Goyal et al 2019 - An Empirical Investigation of Global and Local Normalization for Recurrent Neural Sequence Models Using a Continuous Relaxation to Beam Search]]

===== Related Pages =====
  * [[Structured Prediction]]