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 …
Towards building more robust ner datasets: An empirical study on ner dataset bias from a dataset difficulty view
Recently, many studies have illustrated the robustness problem of Named Entity
Recognition (NER) systems: the NER models often rely on superficial entity patterns for …
Recognition (NER) systems: the NER models often rely on superficial entity patterns for …
Span-based named entity recognition by generating and compressing information
The information bottleneck (IB) principle has been proven effective in various NLP
applications. The existing work, however, only used either generative or information …
applications. The existing work, however, only used either generative or information …
Linkner: Linking local named entity recognition models to large language models using uncertainty
Named Entity Recognition (NER) serves as a fundamental task in natural language
understanding, bearing direct implications for web content analysis, search engines, and …
understanding, bearing direct implications for web content analysis, search engines, and …
Farewell to aimless large-scale pretraining: Influential subset selection for language model
Pretrained language models have achieved remarkable success in various natural
language processing tasks. However, pretraining has recently shifted toward larger models …
language processing tasks. However, pretraining has recently shifted toward larger models …