Gajbhiye, Amit and Winterbottom, Thomas and Al Moubayed, Noura and Bradley, Steven (2020) 'Bilinear fusion of commonsense knowledge with attention-based NLI models.', in Artificial Neural Networks and Machine Learning – ICANN 2020. , pp. 633-646. Lecture notes in computer science., 12396
Abstract
We consider the task of incorporating real-world commonsense knowledge into deep Natural Language Inference (NLI) models. Existing external knowledge incorporation methods are limited to lexical-level knowledge and lack generalization across NLI models, datasets, and commonsense knowledge sources. To address these issues, we propose a novel NLI model-independent neural framework, BiCAM. BiCAM incorporates real-world commonsense knowledge into NLI models. Combined with convolutional feature detectors and bilinear feature fusion, BiCAM provides a conceptually simple mechanism that generalizes well. Quantitative evaluations with two state-of-the-art NLI baselines on SNLI and SciTail datasets in conjunction with ConceptNet and Aristo Tuple KGs show that BiCAM considerably improves the accuracy the incorporated NLI baselines. For example, our BiECAM model, an instance of BiCAM, on the challenging SciTail dataset, improves the accuracy of incorporated baselines by 7.0% with ConceptNet, and 8.0% with Aristo Tuple KG.
Item Type: | Book chapter |
---|---|
Full text: | (AM) Accepted Manuscript Download PDF (320Kb) |
Status: | Peer-reviewed |
Publisher Web site: | https://doi.org/10.1007/978-3-030-61609-0_50 |
Publisher statement: | The final authenticated version is available online at https://doi.org/10.1007/978-3-030-61609-0_50 |
Date accepted: | 13 August 2020 |
Date deposited: | 28 October 2020 |
Date of first online publication: | 22 October 2020 |
Date first made open access: | 28 October 2020 |
Save or Share this output
Export: | |
Look up in GoogleScholar |