Zhao et al 2026a - Revision history

Scipediacontent: Scipediacontent moved page Review 515720032295 to Zhao et al 2026a

2026-06-08T08:48:57Z

Scipediacontent moved page Review 515720032295 to Zhao et al 2026a

Scipediacontent at 08:47, 8 June 2026

2026-06-08T08:47:10Z

Scipediacontent: Scipediacontent moved page Draft content 525442323 to Review 515720032295

2026-06-08T08:13:07Z

Scipediacontent moved page Draft content 525442323 to Review 515720032295

Scipediacontent: Created page with " == Abstract ==
Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiti..."

2026-06-08T08:13:04Z

Created page with " == Abstract == <p>Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiti..."

New page

== 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 IA</p>

== Document ==
<pdf>Media:Draft_content_525442323-1156-document.pdf</pdf>

← Older revision	Revision as of 08:48, 8 June 2026
(No difference)

@@ Line 2: / Line 2: @@
 == 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 IA</p>
+<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
 == Document ==
 <pdf>Media:Draft_content_525442323-1156-document.pdf</pdf>

← Older revision	Revision as of 08:13, 8 June 2026
(No difference)

Zhao et al 2026a - Revision history

Scipediacontent: Scipediacontent moved page Review 515720032295 to Zhao et al 2026a

Scipediacontent at 08:47, 8 June 2026

Scipediacontent: Scipediacontent moved page Draft content 525442323 to Review 515720032295

Scipediacontent: Created page with " == Abstract == Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiti..."

Scipediacontent: Created page with " == Abstract ==
Traditional few-shot text classification models focus only on label prediction and cannot extract structured information such as entities or events, limiti..."