# Dynamic Integration of Background Knowledge in Neural NLU Systems

arXiv: https://arxiv.org/abs/1706.02596 · HTML: https://mlsanity.com/paper/1706.02596/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jun 2017.

## Built on by (most cited first, 7 of 7)

- [Benchmarking Knowledge-Enhanced Commonsense Question Answering via Knowledge-to-Text Transformation](https://mlsanity.com/paper/2101.00760/) (2021)
- [Reasoning Over Virtual Knowledge Bases With Open Predicate Relations](https://mlsanity.com/paper/2102.07043/) (2021)
- [ComFact: A Benchmark for Linking Contextual Commonsense Knowledge](https://mlsanity.com/paper/2210.12678/) (2022)
- [ArT: All-round Thinker for Unsupervised Commonsense Question-Answering](https://mlsanity.com/paper/2112.13428/) (2021)
- [CO-NNECT: A Framework for Revealing Commonsense Knowledge Paths as Explicitations of Implicit Knowledge in Texts](https://mlsanity.com/paper/2105.03157/) (2021)
- [Understanding in Artificial Intelligence](https://mlsanity.com/paper/2101.06573/) (2021)
- [Knowledge-Aware Neural Networks for Medical Forum Question Classification](https://mlsanity.com/paper/2109.13141/) (2021)

## Abstract (arXiv)

Common-sense and background knowledge is required to understand natural language, but in most neural natural language understanding (NLU) systems, this knowledge must be acquired from training corpora during learning, and then it is static at test time. We introduce a new architecture for the dynamic integration of explicit background knowledge in NLU models. A general-purpose reading module reads background knowledge in the form of free-text statements (together with task-specific text inputs) and yields refined word representations to a task-specific NLU architecture that reprocesses the task inputs with these representations. Experiments on document question answering (DQA) and recognizing textual entailment (RTE) demonstrate the effectiveness and flexibility of the approach. Analysis shows that our model learns to exploit knowledge in a semantically appropriate way.