Papers by Kasra Hosseini
DeezyMatch: A Flexible Deep Learning Approach to Fuzzy String Matching (2020.emnlp-demos)
Copied to clipboard
| Challenge: | DeezyMatch is a free, open-source software library written in Python for fuzzy string matching and candidate ranking. |
| Approach: | They propose to use DeezyMatch to train new classifiers and fine-tune a pretrained model to generate rich vector representations from string inputs. |
| Outcome: | The proposed algorithm can be used to find the best matching candidates in large knowledge bases and query sets. |
When Time Makes Sense: A Historically-Aware Approach to Targeted Sense Disambiguation (2021.findings-acl)
Copied to clipboard
Kaspar Beelen, Federico Nanni, Mariona Coll Ardanuy, Kasra Hosseini, Giorgia Tolfo, Barbara McGillivray
| Challenge: | a new paper examines whether making NLP models sensitive to time improves their performance . timesensitive Sense Disambiguation is a variation on Word Sense disambiguation . authors present a task to determine whether a token in a text is related to a specific sense . |
| Approach: | They propose a task to determine whether a token in a text is related to a specific sense of a lemma. |
| Outcome: | The proposed model improves when time sensitive, rather than historically-aware, models . the proposed model is a variation on Word Sense Disambiguation (WSD) the proposed method is of more practical relevance to digital history and cultural analysis . |
Living Machines: A study of atypical animacy (2020.coling-main)
Copied to clipboard
Mariona Coll Ardanuy, Federico Nanni, Kaspar Beelen, Kasra Hosseini, Ruth Ahnert, Jon Lawrence, Katherine McDonough, Giorgia Tolfo, Daniel CS Wilson, Barbara McGillivray
| Challenge: | atypical animacy is the property of being alive, but discrepancies are not uncommon . a typical animate is represented as either animate or inanimate in a text . |
| Approach: | They propose a method for determining whether an entity is represented as animate in a text . they use a nineteenth-century English text to analyze animacy . |
| Outcome: | The proposed method improves on an established animacy dataset and a newly introduced resource. |