Learn Before
Negative Likelihood Loss in Sequence Labeling
A sequence labeling model, such as one used for Named Entity Recognition (NER), outputs a probability distribution over the possible tag set at each position, generating a sequence of distributions . The training or fine-tuning of the model can be performed over these distributions. For example, if represents the model's assigned probability for the correct tag at position , the training loss can be defined as the negative likelihood.
0
1
Tags
Foundations of Large Language Models
Ch.1 Pre-training - Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Part-of-Speech (POS) Tagging
BERT-based Architecture for Sequence Labeling
Span Prediction in NLP
Definition of Named Entity Recognition
A model is designed to perform a sequence labeling task by identifying organizations and locations within a text. For each word (token), it must assign one of the following labels:
O(not an entity),B-ORG(beginning of an organization),I-ORG(inside an organization),B-LOC(beginning of a location), orI-LOC(inside a location). Given the sentence 'The United Nations headquarters in New York City is a major landmark', which of the following represents the correct sequence of labels?Applicability of Sequence Labeling
Analyzing a Sequence Labeling Model's Output
Negative Likelihood Loss in Sequence Labeling