Papers by Anna Breit
WiC-TSV: An Evaluation Benchmark for Target Sense Verification of Words in Context (2021.eacl-main)
Copied to clipboard
| Challenge: | Existing benchmarks for Word Sense Disambiguation are limited to those systems in which sense distinctions are defined according to an underlying sense inventory. |
| Approach: | They propose a framework for Target Sense Verification of Words in Context which grounds its uniqueness as binary classification task and independent of external sense inventories. |
| Outcome: | The proposed framework is highly flexible for evaluation of diverse models and systems in and across domains. |
WiC-TSV-de: German Word-in-Context Target-Sense-Verification Dataset and Cross-Lingual Transfer Analysis (2022.lrec-1)
Copied to clipboard
| Challenge: | Target Sense Verification is a binary disambiguation task that requires a sense-inventory-independent model to be developed. |
| Approach: | They propose a multi-domain dataset for German Target Sense Verification . they use a domain-independent instance to train and develop sense-inventory-independence models . |
| Outcome: | The proposed model fails to solve the German target Sense Verification dataset . the multi-domain dataset contains domain-bound subsets from four different domains . |