Context-Based Text-Graph Embeddings in Word-Sense Induction Tasks

Sherstyuk, Leonid; Makarov, Ilya

doi:10.1007/978-3-031-15168-2_7

Search citation statements

Order By: Relevance

Paper Sections

Select...

Graph-based Wsi Datasets1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

2024

Publication Types

Select...

Other3

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

(1 citation statement)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such co-occurence graphs are calculated automatically. The similarity networks are afterwards clustered to induce word senses (Hope and Keller, 2013;Sherstuk, 2020). McCarthy et al (2016) highlighted the problem of using fixed sets of senses for word sense inventory representation.…”

Section: Graph-based Wsi Datasetsmentioning

confidence: 99%

RuDSI: graph-based word sense induction dataset for Russian

Аксенова¹,

Gavrishina²,

Rykov³

et al. 2022

Preprint

View full text Add to dashboard Cite

We present RuDSI, a new benchmark for word sense induction (WSI) in Russian. The dataset was created using manual annotation and semiautomatic clustering of Word Usage Graphs (WUGs). Unlike prior WSI datasets for Russian, RuDSI is completely data-driven (based on texts from Russian National Corpus), with no external word senses imposed on annotators. Depending on the parameters of graph clustering, different derivative datasets can be produced from raw annotation. We report the performance that several baseline WSI methods obtain on RuDSI and discuss possibilities for improving these scores.

show abstract

Section: Graph-based Wsi Datasetsmentioning

confidence: 99%