Extending Implicit Discourse Relation Recognition to the PDTB-3

The PDTB-3 contains many more Implicit discourse relations than the previous PDTB-2. This is in part because implicit relations have now been annotated within sentences as well as between them. In addition, some now co-occur with explicit discourse relations, instead of standing on their own. Here we show that while this can complicate the problem of identifying the location of implicit discourse relations, it can in turn simplify the problem of identifying their senses. We present data to support this claim, as well as methods that can serve as a non-trivial baseline for future state-of-the-art recognizers for implicit discourse relations.

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

[2]  Rashmi Prasad,et al.  Realization of Discourse Relations by Other Means: Alternative Lexicalizations , 2010, COLING.

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

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

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

[6]  Vera Demberg,et al.  On the Need of Cross Validation for Discourse Relation Classification , 2017, EACL 2017.

[7]  Dan Klein,et al.  Constituency Parsing with a Self-Attentive Encoder , 2018, ACL.

[8]  Nianwen Xue,et al.  Robust Non-Explicit Neural Discourse Parser in English and Chinese , 2016, CoNLL Shared Task.

[9]  Claire Cardie,et al.  Improving Implicit Discourse Relation Recognition Through Feature Set Optimization , 2012, SIGDIAL Conference.

[10]  Holger Schwenk,et al.  Supervised Learning of Universal Sentence Representations from Natural Language Inference Data , 2017, EMNLP.

[11]  Shafiq R. Joty,et al.  Combining Intra- and Multi-sentential Rhetorical Parsing for Document-level Discourse Analysis , 2013, ACL.

[12]  Hwee Tou Ng,et al.  CoNLL 2016 Shared Task on Multilingual Shallow Discourse Parsing , 2016, CoNLL.

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

[14]  Ruihong Huang,et al.  Improving Implicit Discourse Relation Classification by Modeling Inter-dependencies of Discourse Units in a Paragraph , 2018, NAACL.

[15]  Steven Bird,et al.  NLTK: The Natural Language Toolkit , 2002, ACL.

[16]  Nathan Schneider,et al.  Discourse Coherence: Concurrent Explicit and Implicit Relations , 2018, ACL.

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

[18]  Vera Demberg,et al.  Examples and Specifications that Prove a Point: Identifying Elaborative and Argumentative Discourse Relations , 2017, Dialogue Discourse.

[19]  Shafiq R. Joty,et al.  CODRA: A Novel Discriminative Framework for Rhetorical Analysis , 2015, CL.

[20]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[21]  Nianwen Xue,et al.  A Systematic Study of Neural Discourse Models for Implicit Discourse Relation , 2017, EACL.

[22]  Hai Zhao,et al.  Deep Enhanced Representation for Implicit Discourse Relation Recognition , 2018, COLING.

[23]  Hwee Tou Ng,et al.  The CoNLL-2015 Shared Task on Shallow Discourse Parsing , 2015, CoNLL.

[24]  Tomas Mikolov,et al.  Enriching Word Vectors with Subword Information , 2016, TACL.

[25]  Nathan Schneider,et al.  Exploring Substitutability through Discourse Adverbials and Multiple Judgments , 2017, IWCS.