Papers by Maria Sukhareva
Context-Aware Text Normalisation for Historical Dialects (2020.coling-main)
Copied to clipboard
| Challenge: | Context-aware historical text normalisation is a severely under-researched area . a new approach to normalise historical spellings relies on the state-of-the-art methods . |
| Approach: | They propose a multidialect normaliser with a context-aware reranking approach . they incorporate dialectal information into the training and use a word-level n-gram language model . |
| Outcome: | The proposed approach improves accuracy on historical datasets and further improves on baseline. |
Analyzing Middle High German Syntax with RDF and SPARQL (L18-1)
Copied to clipboard
| Challenge: | Using CoNLL-RDF and SPARQL Update, we analyze the diachronic changes of Middle High German syntax. |
| Approach: | They propose a rule-based shallow parser and an enrichment pipeline grounded in CoNLL-RDF and SPARQL Update for parsing. |
| Outcome: | The proposed pipeline is based on CoNLL-RDF and SPARQL Update for syntactic annotation and semantic enrichment of Middle High German. |
A Streamlined Method for Sourcing Discourse-level Argumentation Annotations from the Crowd (N19-1)
Copied to clipboard
| Challenge: | Existing methods for analyzing discourse-level argument annotations require expensive labor and data. |
| Approach: | They propose a method that breaks down a popular but complex discourse-level argument annotation scheme into a simple iterative procedure that can be applied even by untrained annotators. |
| Outcome: | The proposed method can be applied even by untrained annotators. |