Fine-grained Entity Typing via Label Reasoning

Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize interdependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose Label Reasoning Network(LRN), which sequentially reasons finegrained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-toset, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.

[1]  Mo Yu,et al.  Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing , 2019, NAACL.

[2]  Wenkai Zhang,et al.  De-biasing Distantly Supervised Named Entity Recognition via Causal Intervention , 2021, ACL.

[3]  Kentaro Inui,et al.  Neural Architectures for Fine-grained Entity Type Classification , 2016, EACL.

[4]  Harold W. Kuhn,et al.  The Hungarian method for the assignment problem , 1955, 50 Years of Integer Programming.

[5]  Hongyu Guo,et al.  Modeling Noisy Hierarchical Types in Fine-Grained Entity Typing: A Content-Based Weighting Approach , 2019, IJCAI.

[6]  Haoyu Zhang,et al.  Learning with Noise: Improving Distantly-Supervised Fine-grained Entity Typing via Automatic Relabeling , 2020, IJCAI.

[7]  Yangqiu Song,et al.  Improving Fine-grained Entity Typing with Entity Linking , 2019, EMNLP/IJCNLP.

[8]  Zhiyuan Liu,et al.  Put It Back: Entity Typing with Language Model Enhancement , 2018, EMNLP.

[9]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[10]  Gerhard Weikum,et al.  FINET: Context-Aware Fine-Grained Named Entity Typing , 2015, EMNLP.

[11]  Andrew McCallum,et al.  Hierarchical Losses and New Resources for Fine-grained Entity Typing and Linking , 2018, ACL.

[12]  Xiaoli Z. Fern,et al.  Description-Based Zero-shot Fine-Grained Entity Typing , 2019, NAACL.

[13]  Maosong Sun,et al.  ERNIE: Enhanced Language Representation with Informative Entities , 2019, ACL.

[14]  Omer Levy,et al.  Ultra-Fine Entity Typing , 2018, ACL.

[15]  Philip Yu,et al.  MZET: Memory Augmented Zero-Shot Fine-grained Named Entity Typing , 2020, COLING.

[16]  Jeffrey Pennington,et al.  GloVe: Global Vectors for Word Representation , 2014, EMNLP.

[17]  Bing Li,et al.  Fine-Grained Named Entity Typing over Distantly Supervised Data Based on Refined Representations , 2020, AAAI.

[18]  Ying Lin,et al.  An Attentive Fine-Grained Entity Typing Model with Latent Type Representation , 2019, EMNLP.

[19]  Heng Ji,et al.  AFET: Automatic Fine-Grained Entity Typing by Hierarchical Partial-Label Embedding , 2016, EMNLP.

[20]  Ivan Bratko,et al.  Learning by Discovering Concept Hierarchies , 1999, Artif. Intell..

[21]  Nevena Lazic,et al.  Context-Dependent Fine-Grained Entity Type Tagging , 2014, ArXiv.

[22]  Jun Zhou,et al.  Neural Zero-Shot Fine-Grained Entity Typing , 2020, WWW.

[23]  Hongyu Lin,et al.  Denoising Distantly Supervised Named Entity Recognition via a Hypergeometric Probabilistic Model , 2021, AAAI.

[24]  Yaojie Lu,et al.  Sequence-to-Nuggets: Nested Entity Mention Detection via Anchor-Region Networks , 2019, ACL.

[25]  Erik Cambria,et al.  Label Embedding for Zero-shot Fine-grained Named Entity Typing , 2016, COLING.

[26]  Doug Downey,et al.  OTyper: A Neural Architecture for Open Named Entity Typing , 2018, AAAI.

[27]  Mudhakar Srivatsa,et al.  Improving Semantic Parsing via Answer Type Inference , 2016, EMNLP.

[28]  Yasumasa Onoe,et al.  Learning to Denoise Distantly-Labeled Data for Entity Typing , 2019, NAACL.

[29]  Heng Ji,et al.  Building a Fine-Grained Entity Typing System Overnight for a New X (X = Language, Domain, Genre) , 2016, ArXiv.

[30]  Jun Zhao,et al.  Joint Entity and Relation Extraction with Set Prediction Networks , 2020, IEEE transactions on neural networks and learning systems.

[31]  Wei Wu,et al.  SGM: Sequence Generation Model for Multi-label Classification , 2018, COLING.

[32]  Quan Ren.  Fine-Grained Entity Typing with Hierarchical Inference , 2020, 2020 IEEE 4th Information Technology, Networking, Electronic and Automation Control Conference (ITNEC).

[33]  Ping Guo,et al.  An Empirical Study of Pre-trained Embedding on Ultra-Fine Entity Typing , 2020, 2020 IEEE International Conference on Systems, Man, and Cybernetics (SMC).

[34]  Heike Adel,et al.  Noise Mitigation for Neural Entity Typing and Relation Extraction , 2016, EACL.

[35]  Xianpei Han,et al.  A Rigourous Study on Named Entity Recognition: Can Fine-tuning Pretrained Model Lead to the Promised Land? , 2020, ArXiv.

[36]  Benjamin Van Durme,et al.  Hierarchical Entity Typing via Multi-level Learning to Rank , 2020, ACL.

[37]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[38]  Hinrich Schütze,et al.  End-to-End Trainable Attentive Decoder for Hierarchical Entity Classification , 2017, EACL.

[39]  Ashish Anand,et al.  Fine-Grained Entity Type Classification by Jointly Learning Representations and Label Embeddings , 2017, EACL.

[40]  Michael Strube,et al.  A Fully Hyperbolic Neural Model for Hierarchical Multi-class Classification , 2020, FINDINGS.

[41]  Dan Klein,et al.  Fine-Grained Entity Typing with High-Multiplicity Assignments , 2017, ACL.

[42]  Heng Ji,et al.  Label Noise Reduction in Entity Typing by Heterogeneous Partial-Label Embedding , 2016, KDD.

[43]  Dan Roth,et al.  Zero-Shot Open Entity Typing as Type-Compatible Grounding , 2019, EMNLP.

[44]  Yasumasa Onoe,et al.  Fine-Grained Entity Typing for Domain Independent Entity Linking , 2020, AAAI.