TL;DR
This paper introduces a BART-based approach for span detection and classification in text, transforming input into marked-up versions to identify spans and their classes, with insights into pre-training effects.
Contribution
It presents a novel BART encoder-decoder method for span detection and classification, highlighting its effectiveness and limitations in a SemEval task.
Findings
Effective span detection and classification using BART
Pre-training influences model success and limitations
Participated in SemEval-2021 Task 6
Abstract
A novel solution to span detection and classification is presented in which a BART EncoderDecoder model is used to transform textual input into a version with XML-like marked up spans. This markup is subsequently translated to an identification of the beginning and end of fragments and of their classes. Discussed is how pre-training methodology both explains the relative success of this method and its limitations. This paper reports on participation in task 6 of SemEval-2021: Detection of Persuasion Techniques in Texts and Images.
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 · Softmax · Attention Is All You Need · Layer Normalization · Dropout · Byte Pair Encoding · Adam · Multi-Head Attention · Refunds@Expedia|||How do I get a full refund from Expedia?
