Papers with machine learning algorithm
Improving Toponym Resolution by Predicting Attributes to Constrain Geographical Ontology Entries (2024.naacl-short)
Copied to clipboard
| Challenge: | Existing approaches to geocoding only encode location mentions and their context . |
| Approach: | They propose a prompt-based approach to geocoding where the machine learning algorithm encodes only the location mention and its context. |
| Outcome: | The proposed model achieves state-of-the-art performance on multiple datasets. |
Collective Entity Disambiguation with Structured Gradient Tree Boosting (N18-1)
Copied to clipboard
| Challenge: | Existing work on structured gradient tree boosting for collective entity disambiguation is limited to regular classification or regression problems. |
| Approach: | They propose a structured learning model that uses gradient tree boosting to disambiguate named entities in a document. |
| Outcome: | The proposed model outperforms the previous state-of-the-art neural system by near 1% absolute accuracy on the popular AIDA-CoNLL dataset. |
The Search for Agreement on Logical Fallacy Annotation of an Infodemic (2022.lrec-1)
Copied to clipboard
Claire Bonial, Austin Blodgett, Taylor Hudson, Stephanie M. Lukin, Jeffrey Micher, Douglas Summers-Stay, Peter Sutor, Clare Voss
| Challenge: | a parallel "infodemic" has emerged with the COVID-19 pandemic . logical fallacies can be subtly encoded in the structure of a document across multiple sentences . |
| Approach: | They evaluate an annotation schema for labeling logical fallacy types using linguist annotations . they propose to use a machine learning algorithm to train annotators for fallacy detection . |
| Outcome: | The proposed annotation schema is clear and non-overlapping for manual and system assignment. |
Comparing Methods for Measuring Dialect Similarity in Norwegian (2020.lrec-1)
Copied to clipboard
| Challenge: | a coarse-grained transcription of speech is sufficient to replicate dialectal boundaries, but it can be generalised over by an automatic method. |
| Approach: | They propose to use two different methods to measure dialect similarity in Norwegian . they use the Levenshtein method and the neural long short term memory algorithm . the paper shows that coarse-grained transcriptions of speech can generate dialect maps . |
| Outcome: | The proposed method can generalise over coarse-grained transcriptions, but it needs a large dataset . the proposed method is compared with canonical maps found in the dialect literature . |