Zobrazeno 1 - 10
of 394
pro vyhledávání: '"MORTENSEN, DAVID"'
Autor:
Hofmann, Valentin, Weissweiler, Leonie, Mortensen, David, Schütze, Hinrich, Pierrehumbert, Janet
What mechanisms underlie linguistic generalization in large language models (LLMs)? This question has attracted considerable attention, with most studies analyzing the extent to which the language skills of LLMs resemble rules. As of yet, it is not k
Externí odkaz:
http://arxiv.org/abs/2411.07990
Autor:
Chang, Kalvin, Chou, Yi-Hui, Shi, Jiatong, Chen, Hsuan-Ming, Holliday, Nicole, Scharenborg, Odette, Mortensen, David R.
Underperformance of ASR systems for speakers of African American Vernacular English (AAVE) and other marginalized language varieties is a well-documented phenomenon, and one that reinforces the stigmatization of these varieties. We investigate whethe
Externí odkaz:
http://arxiv.org/abs/2408.14262
Autor:
Boldt, Brendon, Mortensen, David
We introduce the Emergent Language Corpus Collection (ELCC): a collection of corpora generated from open source implementations of emergent communication systems across the literature. These systems include a variety of signalling game environments a
Externí odkaz:
http://arxiv.org/abs/2407.04158
Autor:
Boldt, Brendon, Mortensen, David
Publikováno v:
Transactions on Machine Learning Research, February 2024
Emergent communication, or emergent language, is the field of research which studies how human language-like communication systems emerge de novo in deep multi-agent reinforcement learning environments. The possibilities of replicating the emergence
Externí odkaz:
http://arxiv.org/abs/2407.03302
Autor:
Boldt, Brendon, Mortensen, David
Publikováno v:
Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), 1475-1489
In this paper, we introduce a benchmark for evaluating the overall quality of emergent languages using data-driven methods. Specifically, we interpret the notion of the "quality" of an emergent language as its similarity to human language within a de
Externí odkaz:
http://arxiv.org/abs/2407.03456
Positive thinking is thought to be an important component of self-motivation in various practical fields such as education and the workplace. Previous work, including sentiment transfer and positive reframing, has focused on the positive side of lang
Externí odkaz:
http://arxiv.org/abs/2406.16521
Existing zero-shot cross-lingual NER approaches require substantial prior knowledge of the target language, which is impractical for low-resource languages. In this paper, we propose a novel approach to NER using phonemic representation based on the
Externí odkaz:
http://arxiv.org/abs/2406.16030
Autor:
Naik, Atharva, Zhang, Kexun, Robinson, Nathaniel, Mysore, Aravind, Marr, Clayton, Byrnes, Hong Sng Rebecca, Cai, Anna, Chang, Kalvin, Mortensen, David
Historical linguists have long written a kind of incompletely formalized ''program'' that converts reconstructed words in an ancestor language into words in one of its attested descendants that consist of a series of ordered string rewrite functions
Externí odkaz:
http://arxiv.org/abs/2406.12725
Existing work implementing comparative reconstruction of ancestral languages (proto-languages) has usually required full supervision. However, historical reconstruction models are only of practical value if they can be trained with a limited amount o
Externí odkaz:
http://arxiv.org/abs/2406.05930
Proto-form reconstruction has been a painstaking process for linguists. Recently, computational models such as RNN and Transformers have been proposed to automate this process. We take three different approaches to improve upon previous methods, incl
Externí odkaz:
http://arxiv.org/abs/2404.15690