Papers by John E. Ortega
Evaluating Self-Supervised Speech Representations for Indigenous American Languages (2024.lrec-main)
Copied to clipboard
| Challenge: | a recent study focused on the use of self-supervised learning to learn speech representations for indigenous languages . aaron e. scott: the vast linguistic diversity represented by indigenous languages remains unexplored . by expanding the scope of language processing to include indigenous languages, we can foster linguistic inclusivity, he says . |
| Approach: | They benchmark the efficacy of large-scale self-supervised learning models on indigenous American languages. |
| Outcome: | The proposed model can generalize to real-world data, showing strong performance . evaluators found that the model performed better than monolingual models on indigenous languages . |
Semantic Role Labeling of NomBank Partitives (2025.coling-main)
Copied to clipboard
| Challenge: | Semantic role labeling (SRL) is a way to represent semantic concepts via labeled predicate/argument pairs. |
| Approach: | They describe a semantic role labeling task that uses a set of predicate/argument pairs to represent semantic concepts. |
| Outcome: | The highest scoring system achieves an F1 of 91.74% using “gold” parses from the Penn Treebank and 91.12% when using the Berkeley Neural parser. |
Lexicography Saves Lives (LSL): Automatically Translating Suicide-Related Language (2025.coling-main)
Copied to clipboard
| Challenge: | Recent years have seen a marked increase in research that aims to identify or predict risk, intention or ideation of suicide in the context of Western culture. |
| Approach: | They propose to translate an existing dictionary related to suicide into 200 different languages and conduct human evaluations on a subset of translated dictionaries. |
| Outcome: | The proposed project aims to identify or predict risk, intention or ideation of suicide in the context of Western culture and reduce suicide rate by 2030 is one of the UN’s Sustainable Development Goals. |
Related Work Is All You Need (2024.lrec-main)
Copied to clipboard
| Challenge: | a corpus of 400k annotations of related work is used to generate a "related work" section . authors and researchers often turn to tools like Google Scholar to find related research for their papers . |
| Approach: | They propose to use a corpus with 400k annotations to generate a "related work" section . they propose to automate the process by using a newly-released corpus that contains human annotations . |
| Outcome: | The proposed technique can be automated by using human annotations of related work sections. |
Is Peer-Reviewing Worth the Effort? (2025.coling-main)
Copied to clipboard
| Challenge: | Using early returns and venue, we can predict which papers will be highly cited in the future. |
| Approach: | They ask whether early returns are predictive of papers' citations . |
| Outcome: | The authors show early returns are more predictive than venue . early returns also predicts which papers will be highly cited in the future . |
WordNet-QU: Development of a Lexical Database for Quechua Varieties (2022.coling-1)
Copied to clipboard
| Challenge: | Quechua is a low-resource language from south America but lacks resources to build high-performance computational systems. |
| Approach: | They propose to include Quechua in a lexical database called wordnet . they propose a synset alignment algorithm to compare Quechuan to its nearest high-resource language . |
| Outcome: | The proposed system compares Quechua to its nearest high-resource language, Spanish . it uses a synset alignment algorithm to find Quechuan resources in a lexical database . |
Meeting the Needs of Low-Resource Languages: The Value of Automatic Alignments via Pretrained Models (2023.eacl-main)
Copied to clipboard
Abteen Ebrahimi, Arya D. McCarthy, Arturo Oncevay, John E. Ortega, Luis Chiruzzo, Gustavo Giménez-Lugo, Rolando Coto-Solano, Katharina Kann
| Challenge: | Large multilingual models have inspired a new class of word alignment methods, which work well for pretraining languages. |
| Approach: | They propose to use transformer-based word alignment methods to extract alignments from massive pretrained models. |
| Outcome: | The proposed methods outperform traditional methods for languages unseen to pretraining models, and are competitive with each other. |