Abstract | ||
---|---|---|
Multi-task learning (MTL) models, which pool examples arisen out of several tasks, have achieved remarkable results in language processing. However, multi-task learning is not always effective when compared with the single-task methods in sequence tagging. One possible reason is that existing methods to multi-task sequence tagging often reply on lower layer parameter sharing to connect different tasks. The lack of interactions between different tasks results in limited performance improvement. In this paper, we propose a novel multi-task learning architecture which could iteratively utilize the prediction results of each task explicitly. We train our model for part-of-speech (POS) tagging, chunking and named entity recognition (NER) tasks simultaneously. Experimental results show that without any task-specific features, our model obtains the state-of-the-art performance on both chunking and NER. |
Year | DOI | Venue |
---|---|---|
2018 | 10.1007/978-3-319-99501-4_25 | Lecture Notes in Artificial Intelligence |
Keywords | Field | DocType |
Multi-task learning,Interactions,Sequence tagging | Multi-task learning,End-to-end principle,Learning architecture,Computer science,Chunking (psychology),Artificial intelligence,Named-entity recognition,Machine learning,Performance improvement,Scalability | Conference |
Volume | ISSN | Citations |
11109 | 0302-9743 | 1 |
PageRank | References | Authors |
0.40 | 14 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lin Gui | 1 | 18 | 6.43 |
Du Jiachen | 2 | 36 | 9.02 |
Zhishan Zhao | 3 | 3 | 0.75 |
Yulan He | 4 | 1934 | 123.88 |
Xu Ruifeng | 5 | 432 | 53.04 |
Chuang Fan | 6 | 4 | 1.45 |