analiza aiqbench
This research addresses a critical instability in incremental named entity recognition by identifying and mitigating biased contextual associations that cause models to forget old knowledge while overfitting to new types. The proposed Type-Balanced Contextual Learning method utilizes sentence-duplet learning and consistency losses to maintain performance across evolving entity schemas, offering a robust solution for continuous information extraction tasks.
Type-Balanced Contextual Learning for Incremental Named Entity Recognition
arXiv:2608.31038v1 Announce Type: new Abstract: Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity types within unstructured text. Faced with the continuous influx of entity types, INER grapples with two significant challenges: the widespread issue of catastrophic forgetting and the unique shift issue of the non-entity type semantics. While pseudo-labeling-based INER methods have proven effective in addressing these challenges, a previously overlooked issue arises: the biased context problem. Our analysis shows that, in new sentences, the contextual associations of tokens representing old entity types exhibit a significantly stronger bias towards new entity types compared to their contexts in old sentences. This tendency intensifies the degradation of old knowledge while promoting the overfitting of new knowledge. To solve this biased context, we propose a Type-Balanced Contextual Learning (TBCL) method, featuring a sentence-duplet learning scheme and a contextual consistency loss. This approach offers a fresh perspective for INER through context analysis. Extensive experiments across ten INER settings on three highly recognized datasets showcase the efficacy of our TBCL method, highlighting its proficiency in resolving the biased context issue inherent in pseudo-labeling based INER approaches.
Abstract:Incremental Named Entity Recognition (INER) stands as a pivotal task in information extraction, emphasizing the successive identification of new entity types within unstructured text. Faced with the continuous influx of entity types, INER grapples with two significant challenges: the widespread issue of catastrophic forgetting and the unique shift issue of the non-entity type semantics. While pseudo-labeling-based INER methods have proven effective in addressing these challenges, a previously overlooked issue arises: the biased context problem. Our analysis shows that, in new sentences, the contextual associations of tokens representing old entity types exhibit a significantly stronger bias towards new entity types compared to their contexts in old sentences. This tendency intensifies the degradation of old knowledge while promoting the overfitting of new knowledge. To solve this biased context, we propose a Type-Balanced Contextual Learning (TBCL) method, featuring a sentence-duplet learning scheme and a contextual consistency loss. This approach offers a fresh perspective for INER through context analysis. Extensive experiments across ten INER settings on three highly recognized datasets showcase the efficacy of our TBCL method, highlighting its proficiency in resolving the biased context issue inherent in pseudo-labeling based INER approaches.
Computation and Language (cs.CL)
arXiv:2608.31038 [cs.CL]
(or arXiv:2608.31038v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.31038 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 283 cuvinte
Subiecte conexe
Game Design Creativity evals
LessWrong · 12 oct. 2026
Enhancing Scientific Named Entity Recognition via Large Language Models: A Type-driven Multi-task Learning Approach
arXiv · 18 aug. 2026
FSE: Continual Learning for Named Entity Recognition by Fast-Slow Experts
arXiv · 28 iul. 2026
Underwriting Superintelligence: Backing Agents you can Sue — Rune Kvist, AIUC
Latent Space · 16 sept. 2026