Johannes Bjerva
Biographic Data
| ID | 3449872 |
|---|---|
| NAME | Johannes Bjerva |
| GIVEN NAMES | Johannes |
| FAMILY NAME | Bjerva |
| SIGNATURE | BJERVA J |
| AFFILIATIONS | Department of Computer Science, Aalborg University. [email protected] |
| ORCID | 0000-0002-9512-0739 |
| VERIFIED | Yes |
| TOTAL WORKS | 3 |
| TOTAL CITATIONS | 0 |
| AUTHOR COUNT | 3 |
| EDITOR COUNT | 0 |
| FIRST PUBLICATION YEAR | 2019 |
| LATEST PUBLICATION YEAR | 2025 |
| H-INDEX | 0 |
A Principled Framework for Evaluating on Typologically Diverse Languages
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform well across languages generally. However, evaluating these systems on all the world’s languages is practically infeasible. To attain generalizability, representative language sampling is essential. Previous work argues that generalizable multilingual evaluation sets should contain languages with diverse typological…
The Role of Typological Feature Prediction in NLP and Linguistics
Computational typology has gained traction in the field of Natural Language Processing (NLP) in recent years, as evidenced by the increasing number of papers on the topic and the establishment of a Special Interest Group on the topic (SIGTYP), including the organization of successful workshops and shared tasks. A considerable amount of work in this sub-field is concerned with prediction of typological features, for example, for databases such as …
What Do Language Representations Really Represent
A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the corpus is multilingual, the same model can be used to learn distributed representations of languages, such that similar languages end up with similar representations. We show that this holds even when the multilingual corpus has been translated into English, by picking up …
No prominent works on this page.
What Do Language Representations Really Represent
A neural language model trained on a text corpus can be used to induce distributed representations of words, such that similar words end up with similar representations. If the corpus is multilingual, the same model can be used to learn distributed representations of languages, such that similar languages end up with similar representations. We show that this holds even when the multilingual corpus has been translated into English, by picking up …
The Role of Typological Feature Prediction in NLP and Linguistics
Computational typology has gained traction in the field of Natural Language Processing (NLP) in recent years, as evidenced by the increasing number of papers on the topic and the establishment of a Special Interest Group on the topic (SIGTYP), including the organization of successful workshops and shared tasks. A considerable amount of work in this sub-field is concerned with prediction of typological features, for example, for databases such as …
A Principled Framework for Evaluating on Typologically Diverse Languages
Beyond individual languages, multilingual natural language processing (NLP) research increasingly aims to develop models that perform well across languages generally. However, evaluating these systems on all the world’s languages is practically infeasible. To attain generalizability, representative language sampling is essential. Previous work argues that generalizable multilingual evaluation sets should contain languages with diverse typological…
Natural Language Processing Techniques (3 works) · Computational linguistics (2 works) · Computer Science (2 works) · Linguistics (2 works) · Natural language processing (2 works) · Philosophy (2 works) · Philosophy (2 works) · Topic Modeling (2 works) · Artificial Intelligence (1 works) · Computational and Text Analysis Methods (1 works)