A Joint Model for Structure-based News Genre Classification with Application to Text Summarization

Journalists usually organize and present the contents of a news article following a welldefined structure. In this paper, we propose a novel joint model for structure-based news genre classification that simultaneously identifies one of four commonly used news structures (including Inverted Pyramid and three other structures) for a news article as well as recognizes a sequence of news elements within the article that define the corresponding news structure. Experiments show that the joint model consistently outperforms its variants that perform two tasks independently, which supports our motivation that preserving the two-way dependencies and constraints between a type of news structure and its sequence of news elements enables the model to better predict both of them. Although being not perfect, the system predicted news structure type and news elements have improved the performance of text summarization when incorporated into a recent neural network system.

[1]  Georg Rehm,et al.  Towards automatic Web genre identification: a corpus-based approach in the domain of academia by example of the Academic's Personal Homepage , 2002, Proceedings of the 35th Annual Hawaii International Conference on System Sciences.

[2]  Chin-Yew Lin,et al.  ROUGE: A Package for Automatic Evaluation of Summaries , 2004, ACL 2004.

[3]  William C. Mann,et al.  Rhetorical Structure Theory: Toward a functional theory of text organization , 1988 .

[4]  Dan Roth,et al.  Design Challenges and Misconceptions in Named Entity Recognition , 2009, CoNLL.

[5]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[6]  Ruihong Huang,et al.  Identifying the Most Dominant Event in a News Article by Mining Event Coreference Relations , 2018, NAACL-HLT.

[7]  Parminder Bhatia,et al.  Better Document-level Sentiment Analysis from RST Discourse Parsing , 2015, EMNLP.

[8]  Inderjeet Mani,et al.  Computational Modeling of Narrative , 2013, Computational Modeling of Narrative.

[9]  Mirella Lapata,et al.  Text Summarization with Pretrained Encoders , 2019, EMNLP.

[10]  Marina Santini,et al.  Automatic identification of genre in Web pages , 2011 .

[11]  Junyi Jessy Li,et al.  Assessing the Discourse Factors that Influence the Quality of Machine Translation , 2014, ACL.

[12]  Regina Barzilay,et al.  Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization , 2004, NAACL.

[13]  Daniel Marcu,et al.  From discourse structures to text summaries , 1997 .

[14]  Xiaodong Liu,et al.  Unified Language Model Pre-training for Natural Language Understanding and Generation , 2019, NeurIPS.

[15]  Livio Robaldo,et al.  The Penn Discourse TreeBank 2.0. , 2008, LREC.

[16]  Jason Weston,et al.  A unified architecture for natural language processing: deep neural networks with multitask learning , 2008, ICML '08.

[17]  Regina Barzilay,et al.  Incorporating Content Structure into Text Analysis Applications , 2010, EMNLP.

[18]  Teun A. Van Dijκ.  Structures of News in the Press , 1985 .

[19]  E. Lavelle.  Writing style and the narrative essay , 1997 .

[20]  Mirella Lapata,et al.  Single Document Summarization as Tree Induction , 2019, NAACL.

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

[22]  Phil Blunsom,et al.  Teaching Machines to Read and Comprehend , 2015, NIPS.

[23]  Kuldip K. Paliwal,et al.  Bidirectional recurrent neural networks , 1997, IEEE Trans. Signal Process..

[24]  Ruihong Huang,et al.  Fine-grained Structure-based News Genre Categorization , 2018, EventStory@Coling.

[25]  E. Ytreberg.  Moving out of the Inverted Pyramid: narratives and descriptions in television news , 2001 .

[26]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[27]  Alexander Mehler,et al.  Genres on the Web: Computational Models and Empirical Studies , 2010 .

[28]  T. V. Dijk.  Discourse and communication : new approaches to the analysis of mass media discourse and communication , 1985 .

[29]  Marti A. Hearst.  Multi-Paragraph Segmentation Expository Text , 1994, ACL.

[30]  Zhou Yu,et al.  Unsupervised Dialog Structure Learning , 2019, NAACL.

[31]  Stefan Feuerriegel,et al.  Improving Sentiment Analysis with Document-Level Semantic Relationships from Rhetoric Discourse Structures , 2017, HICSS.

[32]  Preslav Nakov,et al.  Using Discourse Structure Improves Machine Translation Evaluation , 2014, ACL.

[33]  Bowen Zhou,et al.  SummaRuNNer: A Recurrent Neural Network Based Sequence Model for Extractive Summarization of Documents , 2016, AAAI.

[34]  Luke S. Zettlemoyer,et al.  Deep Contextualized Word Representations , 2018, NAACL.

[35]  Ani Nenkova,et al.  Discourse indicators for content selection in summarization , 2010, SIGDIAL Conference.

[36]  Horst Po¨ttker.  News and its communicative quality: the inverted pyramid—when and why did it appear? , 2003 .

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