m (Scipediacontent moved page Draft content 525442323 to Review 515720032295) |
m (Scipediacontent moved page Review 515720032295 to Zhao et al 2026a) |
||
| (One intermediate revision by the same user not shown) | |||
| Line 2: | Line 2: | ||
== Abstract == | == Abstract == | ||
| − | <p>Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiting their usefulness in real-world, semantics-driven tasks. They also rarely use external knowledge or parameter-efficient tuning, leading to shallow representations and weaker performance. To address this, this paper proposes a knowledge-aware multi-task framework that integrates few-shot classification with entity and event extraction. A single BERT encoder with | + | <p>Traditional few-shot text classification models focus only on label prediction and cannot extract |
| − | + | structured information such as entities or events, limiting their usefulness in real-world, semantics-driven tasks. They | |
| − | + | also rarely use external knowledge or parameter-efficient tuning, leading to shallow representations and weaker | |
| + | performance. To address this, this paper proposes a knowledge-aware multi-task framework that integrates few-shot | ||
| + | classification with entity and event extraction. A single BERT encoder with IA3 | ||
| + | adapters enables efficient tuning, | ||
| + | while semantic triples extracted via spaCy and aligned with WordNet and ConceptNet are encoded using TransE. A | ||
| + | BiLSTM captures sequential context and a softmax decoder performs token-level prediction. Experiments show strong | ||
| + | results—97.97% accuracy, 98.00% precision, 97.95% recall, and 97.96% F1—surpassing state-of-the-art baselines. | ||
| + | Ablation studies confirm the value of the knowledge-enhanced, multi-step design, demonstrating suitability for lowresource, knowledge-centric applications.</p> | ||
== Document == | == Document == | ||
<pdf>Media:Draft_content_525442323-1156-document.pdf</pdf> | <pdf>Media:Draft_content_525442323-1156-document.pdf</pdf> | ||
Latest revision as of 10:48, 8 June 2026
Abstract
Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiting their usefulness in real-world, semantics-driven tasks. They also rarely use external knowledge or parameter-efficient tuning, leading to shallow representations and weaker performance. To address this, this paper proposes a knowledge-aware multi-task framework that integrates few-shot classification with entity and event extraction. A single BERT encoder with IA3 adapters enables efficient tuning, while semantic triples extracted via spaCy and aligned with WordNet and ConceptNet are encoded using TransE. A BiLSTM captures sequential context and a softmax decoder performs token-level prediction. Experiments show strong results—97.97% accuracy, 98.00% precision, 97.95% recall, and 97.96% F1—surpassing state-of-the-art baselines. Ablation studies confirm the value of the knowledge-enhanced, multi-step design, demonstrating suitability for lowresource, knowledge-centric applications.
Document
Document information
Published on 08/06/26
Accepted on 08/06/26
Submitted on 07/06/26
Volume Online First, 2026
DOI: 10.23967/j.rimni.2026.10.77142
Licence: CC BY-NC-SA license
Share this document
Keywords
claim authorship
Are you one of the authors of this document?