Exploratory Neural Relation Classification for Domain Knowledge Acquisition

The state-of-the-art methods for relation classification are primarily based on deep neural net- works. This kind of supervised learning method suffers from not only limited training data, but also the large number of low-frequency relations in specific domains. In this paper, we propose the task of exploratory relation classification for domain knowledge harvesting. The goal is to learn a classifier on pre-defined relations and discover new relations expressed in texts. A dynamically structured neural network is introduced to classify entity pairs to a continuously expanded relation set. We further propose the similarity sensitive Chinese restaurant process to discover new relations. Experiments conducted on a large corpus show the effectiveness of our neural network, while new relations are discovered with high precision and recall.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

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

[3]  Arindam Banerjee,et al.  Semi-supervised Clustering by Seeding , 2002, ICML.

[4]  Jun Zhao,et al.  Relation Classification via Convolutional Deep Neural Network , 2014, COLING.

[5]  Aoying Zhou,et al.  Transductive Non-linear Learning for Chinese Hypernym Prediction , 2017, ACL.

[6]  D. Aldous.  Exchangeability and related topics , 1985 .

[7]  Razvan C. Bunescu,et al.  A Shortest Path Dependency Kernel for Relation Extraction , 2005, HLT.

[8]  Gemma Boleda,et al.  Inclusive yet Selective: Supervised Distributional Hypernymy Detection , 2014, COLING.

[9]  Oren Etzioni,et al.  Open Information Extraction: The Second Generation , 2011, IJCAI.

[10]  Chengyu Wang,et al.  DKGBuilder: An Architecture for Building a Domain Knowledge Graph from Scratch , 2017, DASFAA.

[11]  Houfeng Wang,et al.  Bidirectional Recurrent Convolutional Neural Network for Relation Classification , 2016, ACL.

[12]  Peter I. Frazier,et al.  Distance dependent Chinese restaurant processes , 2009, ICML.

[13]  Oren Etzioni,et al.  Open Information Extraction from the Web , 2007, CACM.

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

[15]  Carl E. Rasmussen,et al.  The Infinite Gaussian Mixture Model , 1999, NIPS.

[16]  Paramita Mirza,et al.  On the contribution of word embeddings to temporal relation classification , 2016, COLING.

[17]  Ido Dagan,et al.  Improving Hypernymy Detection with an Integrated Path-based and Distributional Method , 2016, ACL.

[18]  Zhi Jin,et al.  Classifying Relations via Long Short Term Memory Networks along Shortest Dependency Paths , 2015, EMNLP.

[19]  Chengyu Wang,et al.  Chinese Hypernym-Hyponym Extraction from User Generated Categories , 2016, COLING.

[20]  Sunil Kumar Sahu,et al.  Learning local and global contexts using a convolutional recurrent network model for relation classification in biomedical text , 2017, CoNLL.

[21]  Daniel S. Weld,et al.  Autonomously semantifying wikipedia , 2007, CIKM '07.

[22]  Ngoc Thang Vu,et al.  Combining Recurrent and Convolutional Neural Networks for Relation Classification , 2016, NAACL.

[23]  Nanda Kambhatla,et al.  Combining lexical, syntactic, and semantic features with maximum entropy models for extracting relations , 2004, ACL 2004.

[24]  Sebastian Thrun,et al.  Text Classification from Labeled and Unlabeled Documents using EM , 2000, Machine Learning.

[25]  Qing Zhang,et al.  Noise-Clustered Distant Supervision for Relation Extraction: A Nonparametric Bayesian Perspective , 2017, EMNLP.

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

[27]  Marti A. Hearst.  Automatic Acquisition of Hyponyms from Large Text Corpora , 1992, COLING.

[28]  Yue Zhang,et al.  ZORE: A Syntax-based System for Chinese Open Relation Extraction , 2014, EMNLP.

[29]  William W. Cohen,et al.  Exploratory Learning , 2013, ECML/PKDD.

[30]  Raffaella Bernardi,et al.  Entailment above the word level in distributional semantics , 2012, EACL.

[31]  Andrew McCallum,et al.  Relation Extraction with Matrix Factorization and Universal Schemas , 2013, NAACL.