Masked Conditional Random Fields for Sequence Labeling
Conditional Random Field (CRF) based neural models are among the most performant methods for solving sequence labeling problems. Despite its great success, CRF has the shortcoming of occasionally generating illegal sequences of tags, e.g. sequences containing an "I-" tag immediately after an "O" tag, which is forbidden by the underlying BIO tagging scheme. In this work, we propose Masked Conditional Random Field (MCRF), an easy to implement variant of CRF that impose restrictions on candidate paths during both training and decoding phases. We show that the proposed method thoroughly resolves this issue and brings consistent improvement over existing CRF-based models with near zero additional cost.
Code (3)
Tasks
TAGMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Conditional Random Fields with High-Order Features for Sequence Labeling
Dependencies among neighbouring labels in a sequence is an important source of information for sequence labeling problems. However, only dependencies between adjacent labels are commonly exploited in practice because of …
Vocal Bursts Intensity PredictionHybrid semi-Markov CRF for Neural Sequence Labeling
This paper proposes hybrid semi-Markov conditional random fields (SCRFs) for neural sequence labeling in natural language processing. Based on conventional conditional random fields (CRFs), SCRFs have been designed for t…
named-entity-recognitionNamed Entity RecognitionNamed Entity Recognition (NER)NERImage Labeling with Markov Random Fields and Conditional Random Fields
Most existing methods for object segmentation in computer vision are formulated as a labeling task. This, in general, could be transferred to a pixel-wise label assignment task, which is quite similar to the structure of…
SegmentationSemantic SegmentationNeural Latent Dependency Model for Sequence Labeling
Sequence labeling is a fundamental problem in machine learning, natural language processing and many other fields. A classic approach to sequence labeling is linear chain conditional random fields (CRFs). When combined w…
modelMouse Movement and Probabilistic Graphical Models Based E-Learning Activity Recognition Improvement Possibilistic Model
Automatically recognizing the e-learning activities is an important task for improving the online learning process. Probabilistic graphical models such as hidden Markov models and conditional random fields have been succ…
Activity Recognition