| 1 |
Improving Short Text Classification Through Global Augmentation Methods
|
|
|
|
In: Lecture Notes in Computer Science ; 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE) ; https://hal.inria.fr/hal-03414750 ; 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2020, Dublin, Ireland. pp.385-399, ⟨10.1007/978-3-030-57321-8_21⟩ (2020)
|
|
BASE
|
|
Show details
|
|
|
| 2 |
Data Augmenting Contrastive Learning of Speech Representations in the Time Domain
|
|
|
|
In: SLT 2020 - IEEE Spoken Language Technology Workshop ; https://hal.archives-ouvertes.fr/hal-03070321 ; SLT 2020 - IEEE Spoken Language Technology Workshop, Dec 2020, Shenzhen / Virtual, China (2020)
|
|
BASE
|
|
Show details
|
|
|
| 3 |
Characterization and classification of semantic image-text relations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 4 |
Characterization and classification of semantic image-text relations ...
|
|
|
|
BASE
|
|
Show details
|
|
|
| 5 |
Using Complexity-Identical Human- and Machine-Directed Utterances to Investigate Addressee Detection for Spoken Dialogue Systems
|
|
|
|
In: Sensors ; Volume 20 ; Issue 9 (2020)
|
|
BASE
|
|
Show details
|
|
|
| 6 |
NAT: Noise-Aware Training for Robust Neural Sequence Labeling
|
|
|
|
In: Fraunhofer IAIS (2020)
|
|
Abstract:
Sequence labeling systems should perform reliably not only under ideal conditions but also with corrupted inputs as these systems often process user-generated text or follow an error-prone upstream component. To this end, we formulate the noisy sequence labeling problem, where the input may undergo an unknown noising process and propose two Noise-Aware Training (NAT) objectives that improve robustness of sequence labeling performed on perturbed input: Our data augmentation method trains a neural model using a mixture of clean and noisy samples, whereas our stability training algorithm encourages the model to create a noise-invariant latent representation. We employ a vanilla noise model at training time. For evaluation, we use both the original data and its variants perturbed with real O CR errors and misspellings. Extensive experiments on English and German named entity recognition benchmarks confirmed that NAT consistently improved robustness of popular sequence labeling models, preserving accuracy on the original input. We make our code and data publicly available for the research community.
|
|
Keyword:
data augmentation; information extraction; Named Entity Recognition (NER); Natural Language Processing (NLP); Optical Character Recognition (OCR); robustness; sequence labeling; stability training
|
|
URL: http://publica.fraunhofer.de/documents/N-596978.html
|
|
BASE
|
|
Hide details
|
|
|
| 7 |
MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity
|
|
|
|
In: Proceedings of the Society for Computation in Linguistics (2020)
|
|
BASE
|
|
Show details
|
|
|
|
|
