21 |
A Non-Linear Structural Probe
|
|
|
|
In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2021)
|
|
BASE
|
|
Show details
|
|
22 |
Disambiguatory Signals are Stronger in Word-initial Positions
|
|
|
|
In: Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume (2021)
|
|
BASE
|
|
Show details
|
|
23 |
How (Non-)Optimal is the Lexicon?
|
|
|
|
In: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (2021)
|
|
BASE
|
|
Show details
|
|
24 |
A Bayesian Framework for Information-Theoretic Probing
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
28 |
Disambiguatory Signals are Stronger in Word-initial Positions ...
|
|
|
|
BASE
|
|
Show details
|
|
29 |
Finding Concept-specific Biases in Form--Meaning Associations ...
|
|
|
|
BASE
|
|
Show details
|
|
30 |
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
|
|
Vylomova, Ekaterina; White, Jennifer; Salesky, Elizabeth; Mielke, Sabrina J.; Wu, Shijie; Ponti, Edoardo; Maudslay, Rowan Hall; Zmigrod, Ran; Valvoda, Josef; Toldova, Svetlana; Tyers, Francis; Klyachko, Elena; Yegorov, Ilya; Krizhanovsky, Natalia; Czarnowska, Paula; Nikkarinen, Irene; Krizhanovsky, Andrew; Pimentel, Tiago; Hennigen, Lucas Torroba; Kirov, Christo; Nicolai, Garrett; Williams, Adina; Anastasopoulos, Antonios; Cruz, Hilaria; Chodroff, Eleanor; Cotterell, Ryan; Silfverberg, Miikka; Hulden, Mans. - : arXiv, 2020
|
|
Abstract:
A broad goal in natural language processing (NLP) is to develop a system that has the capacity to process any natural language. Most systems, however, are developed using data from just one language such as English. The SIGMORPHON 2020 shared task on morphological reinflection aims to investigate systems' ability to generalize across typologically distinct languages, many of which are low resource. Systems were developed using data from 45 languages and just 5 language families, fine-tuned with data from an additional 45 languages and 10 language families (13 in total), and evaluated on all 90 languages. A total of 22 systems (19 neural) from 10 teams were submitted to the task. All four winning systems were neural (two monolingual transformers and two massively multilingual RNN-based models with gated attention). Most teams demonstrate utility of data hallucination and augmentation, ensembles, and multilingual training for low-resource languages. Non-neural learners and manually designed grammars showed ... : 39 pages, SIGMORPHON ...
|
|
Keyword:
Computation and Language cs.CL; FOS Computer and information sciences
|
|
URL: https://dx.doi.org/10.48550/arxiv.2006.11572 https://arxiv.org/abs/2006.11572
|
|
BASE
|
|
Hide details
|
|
40 |
Pareto Probing: Trading Off Accuracy for Complexity
|
|
|
|
In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP) (2020)
|
|
BASE
|
|
Show details
|
|
|
|