English Out-of-Vocabulary Lexical Evaluation Task

TL;DR

This paper introduces a novel OOV lexical evaluation task focusing on classifying and predicting attributes of out-of-vocabulary words without prior knowledge, using unsupervised embeddings for baseline experiments.

Contribution

It pioneers an OOV lexical evaluation framework that does not rely on prior knowledge and applies unsupervised embeddings for classification and attribute prediction.

Findings

Baseline experiments with Word2Vec and Word2GM demonstrate effectiveness.

The task provides a new benchmark for OOV lexical evaluation.

Annotator-based attribute inference is feasible without prior knowledge.

Abstract

Unlike previous unknown nouns tagging task, this is the first attempt to focus on out-of-vocabulary (OOV) lexical evaluation tasks that do not require any prior knowledge. The OOV words are words that only appear in test samples. The goal of tasks is to provide solutions for OOV lexical classification and prediction. The tasks require annotators to conclude the attributes of the OOV words based on their related contexts. Then, we utilize unsupervised word embedding methods such as Word2Vec and Word2GM to perform the baseline experiments on the categorical classification task and OOV words attribute prediction tasks.