KI-BERT: Infusing Knowledge Context for Better Language and Domain Understanding

Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models do not use the knowledge context. Knowledge context can be...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2021-09
Main Authors: Faldu, Keyur, Sheth, Amit, Kikani, Prashant, Akbari, Hemang
Format: Article
Language:English
Subjects:
Context
Graphs
Knowledge representation
Model testing
Semantics
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Contextualized entity representations learned by state-of-the-art transformer-based language models (TLMs) like BERT, GPT, T5, etc., leverage the attention mechanism to learn the data context from training data corpus. However, these models do not use the knowledge context. Knowledge context can be understood as semantics about entities and their relationship with neighboring entities in knowledge graphs. We propose a novel and effective technique to infuse knowledge context from multiple knowledge graphs for conceptual and ambiguous entities into TLMs during fine-tuning. It projects knowledge graph embeddings in the homogeneous vector-space, introduces new token-types for entities, aligns entity position ids, and a selective attention mechanism. We take BERT as a baseline model and implement the "Knowledge-Infused BERT" by infusing knowledge context from ConceptNet and WordNet, which significantly outperforms BERT and other recent knowledge-aware BERT variants like ERNIE, SenseBERT, and BERT_CS over eight different subtasks of GLUE benchmark. The KI-BERT-base model even significantly outperforms BERT-large for domain-specific tasks like SciTail and academic subsets of QQP, QNLI, and MNLI.
ISSN:2331-8422