Papers by Sandra Kübler
Offensive Language Detection Using Brown Clustering (2020.lrec-1)
Copied to clipboard
| Challenge: | a recent study shows that Brown clustering is of little use when distinguishing word polarity in sentiment analysis tasks. |
| Approach: | They investigate the use of Brown clustering for offensive language detection . they train Brown clusters separately on positive and negative sentiment data, then combine it into a single complex feature per word . |
| Outcome: | The proposed method improves offensive language detection when used as the only feature or with words or character n-grams. |
Bits and Pieces: Investigating the Effects of Subwords in Multi-task Parsing across Languages and Domains (2024.lrec-main)
Copied to clipboard
| Challenge: | Neural parsing is dependent on the underlying language model, but little is known about how choices affect parser performance. |
| Approach: | They examine how subword sharing is responsible for gains or negative transfer in multi-task learning . they find a preference for averaged or last subwords across languages and domains . |
| Outcome: | The proposed model favors averaged or last subwords across languages and domains . specific POS tags may require different subword, and distribution overlap is more important than discrepancies in the data sizes. |
OCNLI: Original Chinese Natural Language Inference (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent efforts to extend natural language understanding to other languages have focused on (automatically) translating existing English datasets. |
| Approach: | They propose to use a Chinese dataset to generate annotated sentences from native speakers specializing in linguistics to elicit annotations. |
| Outcome: | The proposed dataset does not rely on automatic translation or non-expert annotation. instead, it elicits annotations from native speakers specializing in linguistics. |
UniMorph 2.0: Universal Morphology (L18-1)
Copied to clipboard
Christo Kirov, Ryan Cotterell, John Sylak-Glassman, Géraldine Walther, Ekaterina Vylomova, Patrick Xia, Manaal Faruqui, Sabrina J. Mielke, Arya McCarthy, Sandra Kübler, David Yarowsky, Jason Eisner, Mans Hulden
| Challenge: | The Universal Morphology project is a collaborative effort to improve how NLP handles complex morphology across the world's languages. |
| Approach: | They propose to use a universal tagset to annotate morphological data using a schema that includes a lemma and a bundle of morphology features. |
| Outcome: | The project releases annotated morphological data using a universal tagset, the UniMorph schema. |
Practical Parsing for Downstream Applications (C18-3)
Copied to clipboard
| Challenge: | . - (EN) |
| Approach: | . - (EN) |
| Outcome: | . - (EN) |
How to Parse a Creole: When Martinican Creole Meets French (2022.coling-1)
Copied to clipboard
| Challenge: | a lack of annotated gold standard data is a major challenge for underresourced languages. |
| Approach: | They propose to use a French treebank to develop a dependency parser for Martinican Creole. |
| Outcome: | The proposed model is based on a French treebank and has 80 Martinican Creole sentences. |