TL;DR
This paper introduces a BERT-based method for ranking scalar adjectives by intensity, demonstrating BERT's rich semantic knowledge and outperforming previous models in intensity ranking tasks.
Contribution
The paper presents a novel approach using contextualised BERT representations to directly model and rank scalar adjective intensities, advancing natural language understanding.
Findings
BERT encodes detailed scalar adjective semantics.
The proposed method outperforms static embeddings.
Models perform well on both intrinsic and extrinsic tasks.
Abstract
Adjectives like pretty, beautiful and gorgeous describe positive properties of the nouns they modify but with different intensity. These differences are important for natural language understanding and reasoning. We propose a novel BERT-based approach to intensity detection for scalar adjectives. We model intensity by vectors directly derived from contextualised representations and show they can successfully rank scalar adjectives. We evaluate our models both intrinsically, on gold standard datasets, and on an Indirect Question Answering task. Our results demonstrate that BERT encodes rich knowledge about the semantics of scalar adjectives, and is able to provide better quality intensity rankings than static embeddings and previous models with access to dedicated resources.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
MethodsLinear Layer · Dense Connections · Layer Normalization · WordPiece · Multi-Head Attention · Dropout · Linear Warmup With Linear Decay · Attention Dropout · Weight Decay · Attention Is All You Need
