Minimize Exposure Bias of Seq2Seq Models in Joint Entity and Relation Extraction
Joint entity and relation extraction aims to extract relation triplets from plain text directly. Prior work leverages Sequence-to-Sequence (Seq2Seq) models for triplet sequence generation. However, Seq2Seq enforces an unnecessary order on the unordered triplets and involves a large decoding length associated with error accumulation. These introduce exposure bias, which may cause the models overfit to the frequent label combination, thus deteriorating the generalization. We propose a novel Sequence-to-Unordered-Multi-Tree (Seq2UMTree) model to minimize the effects of exposure bias by limiting the decoding length to three within a triplet and removing the order among triplets. We evaluate our model on two datasets, DuIE and NYT, and systematically study how exposure bias alters the performance of Seq2Seq models. Experiments show that the state-of-the-art Seq2Seq model overfits to both datasets while Seq2UMTree shows significantly better generalization. Our code is available at https://github.com/WindChimeRan/OpenJERE .
Code (1)
Tasks
Joint Entity and Relation ExtractionRelationRelation ExtractionTripletMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking
Extracting entities and relations from unstructured text has attracted increasing attention in recent years but remains challenging, due to the intrinsic difficulty in identifying overlapping relations with shared entiti…
RelationRelation ExtractionJointly De-biasing Face Recognition and Demographic Attribute Estimation
We address the problem of bias in automated face recognition and demographic attribute estimation algorithms, where errors are lower on certain cohorts belonging to specific demographic groups. We present a novel de-bias…
AttributeFace RecognitionEliminating Exposure Bias and Loss-Evaluation Mismatch in Multiple Object Tracking
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their training can b…
Multiple Object TrackingObject TrackingEliminating Exposure Bias and Metric Mismatch in Multiple Object Tracking
Identity Switching remains one of the main difficulties Multiple Object Tracking (MOT) algorithms have to deal with. Many state-of-the-art approaches now use sequence models to solve this problem but their …
Multiple Object TrackingObject TrackingMitigating Exposure Bias in Risk-Aware Time Series Forecasting with Soft Tokens
Autoregressive forecasting is central to predictive control in diabetes and hemodynamic management, where different operating zones carry different clinical risks. Standard models trained with teacher forcing suffer from…
Time Series ForecastingTrajectory Forecasting