Fine-grained Entity Typing (FET) has made great progress based on distant supervision but still suffers from label noise.Existing FET noise learning methods rely on prediction distributions in an instance-independent manner, which causes the problem of confirmation bias.In this work, we propose a clustering-based loss correction framework named Feature Cluster Loss Correction (FCLC), to address these two problems.FCLC first train a coarse backbone model as a feature extractor and noise estimator.Loss correction is then applied to each feature cluster, learning directly from the noisy labels.Experimental results on three public datasets show that FCLC achieves the best performance over existing competitive systems.Auxiliary experiments further demonstrate that FCLC is stable to hyperparameters and it does help mitigate confirmation bias.We also find that in the extreme case of no clean data, the FCLC framework still achieves competitive performance.

Multi-label hierarchical text classification (MLHTC) is an essential yet challenging task of natural language processing (NLP). Existing methods lack attention to predicting sibling labels. In addition, methods based on graph convolutional networks (GCN) meet the problem of over-smoothing, which further deepens the difficulty of distinguishing sibling labels. In this paper, we propose a label-dividing gated graph neural network (LD-GGNN), which can better distinguish sibling labels and achieve adaptive interaction between text and labels. We optimize gated graph neural network (GGNN) to accurately capture structural features of label hierarchy and deeply explore label dependence. Stronger nonlinear characteristics of GGNN are used to solve the problem of over-smoothing. Furthermore, we propose a dynamic label dividing mechanism (DLDM), which can guide the model to distinguish sibling labels by introducing a dividing bias. Compared with previous works, LD-GGNN achieves significant and consistent improvements on both Micro-F1 and Macro-F1 score on multiple datasets.

Linzhi Wu, Pengjun Xie, Jie Zhou, Meishan Zhang, Ma Chunping, Guangwei Xu, Min Zhang. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.

Hierarchical text classification is an essential yet challenging subtask of multi-label text classification with a taxonomic hierarchy.Existing methods have difficulties in modeling the hierarchical label structure in a global view.Furthermore, they cannot make full use of the mutual interactions between the text feature space and the label space.In this paper, we formulate the hierarchy as a directed graph and introduce hierarchy-aware structure encoders for modeling label dependencies.Based on the hierarchy encoder, we propose a novel end-to-end hierarchy-aware global model (Hi-AGM) with two variants.A multi-label attention variant (HiAGM-LA) learns hierarchyaware label embeddings through the hierarchy encoder and conducts inductive fusion of labelaware text features.A text feature propagation model (HiAGM-TP) is proposed as the deductive variant that directly feeds text features into hierarchy encoders.Compared with previous works, both HiAGM-LA and HiAGM-TP achieve significant and consistent improvements on three benchmark datasets.

Despite much success has been achieved, neural machine translation (NMT) suffers from exposure bias and evaluation discrepancy. To be specific, the generation inconsistency between the training and inference process further causes error accumulation and distribution disparity. Furthermore, NMT models are generally optimized on word-level cross-entropy loss function but evaluated by sentence-level metrics. This evaluation-level mismatch may mislead the promotion of translation performance. To address these two drawbacks, we propose to challenge training to gradually simulate inference. Namely, the decoder is fed with inferred words rather than ground truth words during training with a dynamic probability. To ensure accuracy and integrity, we adopt alignment and tailoring on the inferred words. Therefore, these words can leverage inferred information to help improve the training process. As for the dynamic simulation, we define a novel loss-sensitive probability that can sense the converge of training and finetune itself in turn. Experimental results on IWSLT 2016 German-English and WMT 2019 English-Chinese datasets demonstrate that our methodology can significantly improve translation quality. The approach of alignment and tailoring outperforms previous works. Meanwhile, the proposed loss-sensitive sampling is also useful for other state-of-the-art scheduled sampling methods to achieve further promotion.