DE eng

Search in the Catalogues and Directories

Hits 1 – 12 of 12

1
Morphological Processing of Low-Resource Languages: Where We Are and What's Next ...
BASE
Show details
2
Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languages ...
BASE
Show details
3
An FST morphological analyzer for the Gitksan language ...
BASE
Show details
4
Do RNN States Encode Abstract Phonological Alternations? ...
NAACL 2021 2021; Hulden, Mans; Nicolai, Garrett. - : Underline Science Inc., 2021
BASE
Show details
5
Do RNN States Encode Abstract Phonological Processes? ...
BASE
Show details
6
SIGMORPHON 2020 Shared Task 0: Typologically Diverse Morphological Inflection ...
BASE
Show details
7
Noise Isn't Always Negative: Countering Exposure Bias in Sequence-to-Sequence Inflection Models ...
Abstract: Morphological inflection, like many sequence-to-sequence tasks, sees great performance from recurrent neural architectures when data is plentiful, but performance falls off sharply in lower-data settings. We investigate one aspect of neural seq2seq models that we hypothesize contributes to overfitting - teacher forcing. By creating different training and test conditions, exposure bias increases the likelihood that a system too closely models its training data. Experiments show that teacher-forced models struggle to recover when they enter unknown territory. However, a simple modification to the training algorithm to more closely mimic test conditions creates models that are better able to generalize to unseen environments. ...
Keyword: Computer and Information Science; Natural Language Processing; Neural Network
URL: https://dx.doi.org/10.48448/3zab-w963
https://underline.io/lecture/6227-noise-isn't-always-negative-countering-exposure-bias-in-sequence-to-sequence-inflection-models
BASE
Hide details
8
UniMorph 3.0: Universal Morphology
In: Proceedings of the 12th Language Resources and Evaluation Conference (2020)
BASE
Show details
9
Cross-Linguistic Syntactic Evaluation of Word Prediction Models ...
BASE
Show details
10
UniMorph 3.0: Universal Morphology ...
BASE
Show details
11
The SIGMORPHON 2019 Shared Task: Morphological Analysis in Context and Cross-Lingual Transfer for Inflection ...
BASE
Show details
12
Modeling Inflectional Complexity in Natural Language Processing
Nicolai, Garrett J. - : University of Alberta. Department of Computing Science., 2017
BASE
Show details

Catalogues
0
0
0
0
0
0
0
Bibliographies
0
0
0
0
0
0
0
0
0
Linked Open Data catalogues
0
Online resources
0
0
0
0
Open access documents
12
0
0
0
0
© 2013 - 2024 Lin|gu|is|tik | Imprint | Privacy Policy | Datenschutzeinstellungen ändern