Skip to content
conftrace_
2023 EMNLP EMNLP 2023

UWB at Arabic Reverse Dictionary shared task: Computing the meaning of a gloss

Abstract

AbstractTo extract the ‘meaning’ of a gloss phrase, we build a list of sense-IDs for each word in the phrase which is in our vocabulary. We choose one sense-ID from each list so as to maximise similarity of all the IDs in the chosen subset. We take the meaning of the phrase in semantic space to be the weighted sum of the embedding vectors of the IDs.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Knowledge & Reasoning and Natural Language Processing

Authors

Stephen Taylor

Topics

Machine Learning > Core Methods > Embedding Learning Natural Language Processing > Understanding > Semantic Analysis Natural Language Processing > Applications > Information Retrieval Natural Language Processing > Resources & Methods > Lexical Semantics Knowledge & Reasoning > Representation > Knowledge Representation Natural Language Processing > Applications > Natural Language Understanding

Keywords

word sense disambiguation lexical semantics semantic space semantic similarity semantic embedding word embedding weighted sum reverse dictionary gloss interpretation sense identification
Download PDF

More from EMNLP 2023

All EMNLP 2023 papers →
Yet Another Model for Arabic Dialect Identification
VoxArabica: A Robust Dialect-Aware Arabic Speech Recognition System
KSAA-RD Shared Task: Arabic Reverse Dictionary
Qamosy at Arabic Reverse Dictionary shared task: Semi Decoder Architecture for Reverse Dictionary with SBERT Encoder
Abed at KSAA-RD Shared Task: Enhancing Arabic Word Embedding with Modified BERT Multilingual
Rosetta Stone at KSAA-RD Shared Task: A Hop From Language Modeling To Word–Definition Alignment