Sense Vocabulary Compression through the Semantic Knowledge of WordNet for Neural Word Sense Disambiguation
In this article, we tackle the issue of the limited quantity of manually sense annotated corpora for the task of word sense disambiguation, by exploiting the semantic relationships between senses such as synonymy, hypernymy and hyponymy, in order to compress the sense vocabulary of Princeton WordNet, and thus reduce the number of different sense tags that must be observed to disambiguate all words of the lexical database. We propose two different methods that greatly reduces the size of neural WSD models, with the benefit of improving their coverage without additional training data, and without impacting their precision. In addition to our method, we present a WSD system which relies on pre-trained BERT word vectors in order to achieve results that significantly outperform the state of the art on all WSD evaluation tasks.
Code (2)
Tasks
Word Sense DisambiguationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Compression de vocabulaire de sens gr\^ace aux relations s\'emantiques pour la d\'esambigu\"\isation lexicale (Sense Vocabulary Compression through Semantic Knowledge for Word Sense Disambiguation)
En D{\'e}sambigu{\"\i}sation Lexicale (DL), les syst{\`e}mes supervis{\'e}s dominent largement les campagnes d{'}{\'e}valuation. La performance et la couverture de ces syst{\`e}mes sont cependant rapidement limit{\'e}s p…
Word Sense DisambiguationCommon Sense Knowledge Learning for Open Vocabulary Neural Reasoning: A First View into Chronic Disease Literature
In this paper, we address reasoning tasks from open vocabulary Knowledge Bases (openKBs) using state-of-the-art Neural Language Models (NLMs) with applications in scientific literature. For this purpose, self-attention b…
Common Sense ReasoningSENSE: Stereo OpEN Vocabulary SEmantic Segmentation
Open-vocabulary semantic segmentation enables models to segment objects or image regions beyond fixed class sets, offering flexibility in dynamic environments. However, existing methods often rely on single-view images a…
Open Vocabulary Semantic SegmentationScene UnderstandingSpatial ReasoningProbing Commonsense Knowledge in Pre-trained Language Models with Sense-level Precision and Expanded Vocabulary
Progress on commonsense reasoning is usually measured from performance improvements on Question Answering tasks designed to require commonsense knowledge. However, fine-tuning large Language Models (LMs) on these specifi…
Question AnsweringA Framework for Enriching Lexical Semantic Resources with Distributional Semantics
We present an approach to combining distributional semantic representations induced from text corpora with manually constructed lexical-semantic networks. While both kinds of semantic resources are available with high le…
SpecificityWord Sense Disambiguation