Work

Token Titans at BEA 2026 Shared Task 1: Multilingual Lexical Complexity Prediction via Fine-Tuned XLM-RoBERTa with Ensemble Decoding

Year: 2026

Type: conference-paper

Abstract: In this paper, we describe our submission to the BEA 2026 Shared Task on Multilingual Lexical Complexity Prediction.Our system fine-tunes XLM-RoBERTa Large separately for Spanish, German, and Chinese, feeding each instance as a concatenation of the source word, its context in a sentence, an English clue, and the English target word.Training uses Z-score label normalization and two independent runs that differ in learning rate, random seed, etc.On the official test set, the system scores RMSE = 1.170 and Pearson Correlation = 0.812.

Source: Workshop on Innovative Use of NLP for Building Educational Applications

DOI: 10.18653/v1/2026.bea-1.80

Authors: Anubhab Parashar, Sandeep Mathias

Institution: Presidency University

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7166856899

FWCI:

Cites:

Cited by:

Related to: 10