3 months ago

CTLR@WiC-TSV: Target Sense Verification using Marked Inputs andPre-trained Models

{Gaël Dias Elvys Linhares Pontes José G. Moreno}

Abstract

This paper describes the CTRL participation in the Target Sense Verification of the Words in Context challenge (WiC-TSV) at SemDeep6. Our strategy is based on a simplistic annotation scheme of the target words to later be classified by well-known pre-trained neural models. In particular, the marker allows to include position information to help models to correctly identify the word to disambiguate. Results on the challenge show that our strategy outperforms other participants (+11, 4 Accuracy points) and strong baselines (+1, 7 Accuracy points).

Benchmarks

Benchmark	Methodology	Metrics
entity-linking-on-wic-tsv	CTLR	Task 1 Accuracy: all: 76.8 Task 1 Accuracy: domain specific: 79.6 Task 1 Accuracy: general purpose: 74.5 Task 2 Accuracy: all: 72.7 Task 2 Accuracy: domain specific: 81.5 Task 2 Accuracy: general purpose: 65.6 Task 3 Accuracy: all: 78.3 Task 3 Accuracy: domain specific: 85.7 Task 3 Accuracy: general purpose: 72.1

Build AI with AI

From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.

AI Co-coding

Ready-to-use GPUs

Best Pricing

Get Started

Hyper Newsletters

Subscribe to our latest updates

We will deliver the latest updates of the week to your inbox at nine o'clock every Monday morning