KEML: A Knowledge-Enriched Meta-Learning Framework for Lexical Relation Classification
This addresses the problem of accurately predicting semantic relations between concepts for natural language processing applications, representing an incremental improvement.
The paper tackles the challenge of lexical relation classification, which is difficult due to sparse patterns, by proposing the Knowledge-Enriched Meta-Learning (KEML) framework, and experiments show it outperforms state-of-the-art methods on multiple datasets.
Lexical relations describe how concepts are semantically related, in the form of relation triples. The accurate prediction of lexical relations between concepts is challenging, due to the sparsity of patterns indicating the existence of such relations. We propose the Knowledge-Enriched Meta-Learning (KEML) framework to address the task of lexical relation classification. In KEML, the LKB-BERT (Lexical Knowledge Base-BERT) model is presented to learn concept representations from massive text corpora, with rich lexical knowledge injected by distant supervision. A probabilistic distribution of auxiliary tasks is defined to increase the model's ability to recognize different types of lexical relations. We further combine a meta-learning process over the auxiliary task distribution and supervised learning to train the neural lexical relation classifier. Experiments over multiple datasets show that KEML outperforms state-of-the-art methods.