Neural Multi-task Learning for Citation Function and Provenance

Citation function and provenance are two cornerstone tasks in citation analysis. Given a citation, the former task determines its rhetorical role, while the latter locates the text in the cited paper that contains the relevant cited information. We hypothesize that these two tasks are synergistically related, and build a model that validates this claim. For both tasks, we show that a single-layer convolutional neural network (CNN) outperforms existing state-of-the-art baselines. More importantly, we show that the two tasks are indeed synergistic: by jointly training both tasks using multi-task learning, we demonstrate additional performance gains.

[1]  Zhu Liu,et al.  Automatic question-answering using a deep similarity neural network , 2017, 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

[2]  Robert E. Mercer,et al.  Towards an Automated Citation Classifier , 2000, Canadian Conference on AI.

[3]  Dragomir R. Radev,et al.  Purpose and Polarity of Citation: Towards NLP-based Bibliometrics , 2013, NAACL.

[4]  Stephen Wan,et al.  Designing a Citation-Sensitive Research Tool: An Initial Study of Browsing-Specific Information Needs , 2009 .

[5]  Marek Rei,et al.  Semi-supervised Multitask Learning for Sequence Labeling , 2017, ACL.

[6]  M. Moravcsik,et al.  Some Results on the Function and Quality of Citations , 1975 .

[7]  Shashank Agarwal,et al.  Automatically classifying the role of citations in biomedical articles. , 2010, AMIA ... Annual Symposium proceedings. AMIA Symposium.

[8]  Hong Yu,et al.  Citation Analysis with Neural Attention Models , 2016, Louhi@EMNLP.

[9]  Dragomir R. Radev,et al.  The ACL Anthology Reference Corpus: A Reference Dataset for Bibliographic Research in Computational Linguistics , 2008, LREC.

[10]  Dragomir R. Radev,et al.  NLP-driven citation analysis for scientometrics , 2016, Natural Language Engineering.

[11]  Barbara Plank,et al.  When is multitask learning effective? Semantic sequence prediction under varying data conditions , 2016, EACL.

[12]  Barbara Plank,et al.  Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss , 2016, ACL.

[13]  Yann LeCun,et al.  Signature Verification Using A "Siamese" Time Delay Neural Network , 1993, Int. J. Pattern Recognit. Artif. Intell..

[14]  Rich Caruana,et al.  Multitask Learning , 1997, Machine-mediated learning.

[15]  Min-Yen Kan,et al.  Overview of the CL-SciSumm 2016 Shared Task , 2016, BIRNDL@JCDL.

[16]  Joachim Bingel,et al.  Identifying beneficial task relations for multi-task learning in deep neural networks , 2017, EACL.

[17]  Min-Yen Kan,et al.  Insights from CL-SciSumm 2016: the faceted scientific document summarization Shared Task , 2017, International Journal on Digital Libraries.

[18]  Simone Teufel,et al.  Automatic classification of citation function , 2006, EMNLP.

[19]  Animesh Prasad.  WING-NUS at CL-SciSumm 2017: Learning from Syntactic and Semantic Similarity for Citation Contextualization , 2017, BIRNDL@SIGIR.

[20]  Wenpeng Yin,et al.  Convolutional Neural Network for Paraphrase Identification , 2015, NAACL.