Name
Title | ||
|---|---|---|
Investigating loss functions and optimization methods for discriminative learning of label sequences |
Abstract | ||
|---|---|---|
Discriminative models have been of interest in the NLP community in recent years. Previous research has shown that they are advantageous over generative models. In this paper, we investigate how different objective functions and optimization methods affect the performance of the classifiers in the discriminative learning framework. We focus on the sequence labelling problem, particularly POS tagging and NER tasks. Our experiments show that changing the objective function is not as effective as changing the features included in the model. |
Year | DOI | Venue |
|---|---|---|
2003 | 10.3115/1119355.1119374 | EMNLP |
Keywords | Field | DocType |
discriminative model,ner task,discriminative learning,loss function,label sequence,pos tagging,generative model,objective function,previous research,recent year,optimization method,nlp community,different objective function,discrimination learning | Computer science,Natural language processing,Artificial intelligence,Generative grammar,Discriminative model,Machine learning,Discriminative learning | Conference |
Volume | Citations | PageRank |
W03-10 | 21 | 1.58 |
References | Authors | |
11 | 3 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| yasemin altun | 1 | 2463 | 150.46 |
| Mark Johnson | 2 | 3533 | 331.42 |
| Thomas Hofmann | 3 | 10064 | 1001.83 |