# CokeBERT: Contextual Knowledge Selection and Embedding towards Enhanced Pre-Trained Language Models

arXiv: https://arxiv.org/abs/2009.13964 · HTML: https://mlsanity.com/paper/2009.13964/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Sep 2020.

## Built on by (most cited first, 11 of 11)

- [Graph Machine Learning in the Era of Large Language Models (LLMs)](https://mlsanity.com/paper/2404.14928/) (2024)
- [Ontology-enhanced Prompt-tuning for Few-shot Learning](https://mlsanity.com/paper/2201.11332/) (2022)
- [Knowledge Perceived Multi-modal Pretraining in E-commerce](https://mlsanity.com/paper/2109.00895/) (2021)
- [DKPLM: Decomposable Knowledge-enhanced Pre-trained Language Model for Natural Language Understanding](https://mlsanity.com/paper/2112.01047/) (2021)
- [Billion-scale Pre-trained E-commerce Product Knowledge Graph Model](https://mlsanity.com/paper/2105.00388/) (2021)
- [KGPool: Dynamic Knowledge Graph Context Selection for Relation Extraction](https://mlsanity.com/paper/2106.00459/) (2021)
- [Structure Inducing Pre-Training](https://mlsanity.com/paper/2103.10334/) (2021)
- [Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking](https://mlsanity.com/paper/2204.11673/) (2022)
- [Large Language Models Can Better Understand Knowledge Graphs Than We Thought](https://mlsanity.com/paper/2402.11541/) (2024)
- [A Survey of Knowledge Enhanced Pre-trained Models](https://mlsanity.com/paper/2110.00269/) (2021)
- [PKGM: A Pre-trained Knowledge Graph Model for E-commerce Application](https://mlsanity.com/paper/2203.00964/) (2022)

## Abstract (arXiv)

Several recent efforts have been devoted to enhancing pre-trained language models (PLMs) by utilizing extra heterogeneous knowledge in knowledge graphs (KGs) and achieved consistent improvements on various knowledge-driven NLP tasks. However, most of these knowledge-enhanced PLMs embed static sub-graphs of KGs ("knowledge context"), regardless of that the knowledge required by PLMs may change dynamically according to specific text ("textual context"). In this paper, we propose a novel framework named Coke to dynamically select contextual knowledge and embed knowledge context according to textual context for PLMs, which can avoid the effect of redundant and ambiguous knowledge in KGs that cannot match the input text. Our experimental results show that Coke outperforms various baselines on typical knowledge-driven NLP tasks, indicating the effectiveness of utilizing dynamic knowledge context for language understanding. Besides the performance improvements, the dynamically selected knowledge in Coke can describe the semantics of text-related knowledge in a more interpretable form than the conventional PLMs. Our source code and datasets will be available to provide more details for Coke.