Out-of-distribution generalization in natural language processing: Past, present, and future
Abstract Machine learning (ML) systems in natural language processing (NLP) face
significant challenges in generalizing to out-of-distribution (OOD) data, where the test …
significant challenges in generalizing to out-of-distribution (OOD) data, where the test …
CROP: zero-shot cross-lingual named entity recognition with multilingual labeled sequence translation
Named entity recognition (NER) suffers from the scarcity of annotated training data,
especially for low-resource languages without labeled data. Cross-lingual NER has been …
especially for low-resource languages without labeled data. Cross-lingual NER has been …
Pssat: A perturbed semantic structure awareness transferring method for perturbation-robust slot filling
Most existing slot filling models tend to memorize inherent patterns of entities and
corresponding contexts from training data. However, these models can lead to system failure …
corresponding contexts from training data. However, these models can lead to system failure …
Data augmentation for name entity recognition
ZT Kyaw - 2022 - dr.ntu.edu.sg
The objective of this thesis is to develop text augmentation approaches for Name Entity
Recognition tasks under low-resource domain settings. The field of Name Entity Recognition …
Recognition tasks under low-resource domain settings. The field of Name Entity Recognition …
[PDF][PDF] Data augmentation for named entity recognition in the German legal domain
R Erd - 2022 - db-thueringen.de
Abstract Named Entity Recognition over texts from the legal domain aims to recognize legal
entities such as references to legal norms or court decisions. This task is commonly …
entities such as references to legal norms or court decisions. This task is commonly …