APCNN: Tackling Class Imbalance in Relation Extraction through Aggregated Piecewise Convolutional Neural Networks

One of the major difficulties in applying distant supervision to relation extraction is class imbalance, as the distribution of relations appearing in text is heavily skewed. This is particularly damaging for the multi-instance variant of relation extraction. In this work, we introduce a new model called Aggregated Piecewise Convolutional Neural Networks, or APCNN, to address this problem. APCNN relies on the combination of two neural networks, a novel objective function as well as oversampling techniques to tackle class imbalance. We empirically compare APCNN to state-of-the-art approaches and show that it outperforms previous multi-instance approaches on two standard datasets.

[1]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[2]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[3]  Jun Zhao,et al.  Distant Supervision for Relation Extraction via Piecewise Convolutional Neural Networks , 2015, EMNLP.

[4]  Jun Zhao,et al.  Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions , 2017, AAAI.

[5]  Zhiyuan Liu,et al.  Neural Relation Extraction with Selective Attention over Instances , 2016, ACL.

[6]  Nathalie Japkowicz,et al.  The class imbalance problem: A systematic study , 2002, Intell. Data Anal..

[7]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[8]  Andrew McCallum,et al.  Modeling Relations and Their Mentions without Labeled Text , 2010, ECML/PKDD.

[9]  Philippe Cudré-Mauroux,et al.  Relation Extraction Using Distant Supervision , 2018, ACM Comput. Surv..

[10]  Stéphan Clémençon,et al.  AUC optimization and the two-sample problem , 2009, NIPS.

[11]  Heng Ji,et al.  CoType: Joint Extraction of Typed Entities and Relations with Knowledge Bases , 2016, WWW.

[12]  Ralph Grishman,et al.  Relation Extraction: Perspective from Convolutional Neural Networks , 2015, VS@HLT-NAACL.

[13]  Yang Wang,et al.  Cost-sensitive boosting for classification of imbalanced data , 2007, Pattern Recognit..

[14]  Daniel Jurafsky,et al.  Distant supervision for relation extraction without labeled data , 2009, ACL.

[15]  Rosa Maria Valdovinos,et al.  New Applications of Ensembles of Classifiers , 2003, Pattern Analysis & Applications.

[16]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[17]  悠太 菊池,et al.  大規模要約資源としてのNew York Times Annotated Corpus , 2015 .

[18]  Stephanie M. Strassel,et al.  Overview of Linguistic Resource for the TAC KBP 2014 Evaluations: Planning, Execution, and Results , 2014 .

[19]  Ali Emrouznejad,et al.  Ordered Weighted Averaging Operators 1988–2014: A Citation‐Based Literature Survey , 2014, Int. J. Intell. Syst..

[20]  Zhi-Hua Zhou,et al.  Ieee Transactions on Knowledge and Data Engineering 1 Training Cost-sensitive Neural Networks with Methods Addressing the Class Imbalance Problem , 2022 .