Recognizing Implicit Discourse Relations in the Penn Discourse Treebank
By Ziheng Lin, Min-Yen Kan, Hwee Tou Ng. Conference on Empirical Methods in Natural Language Processing, 2009
312 citations recorded by the source corpus.
We present an implicit discourse relation classifier in the Penn Discourse Treebank (PDTB). Our classifier considers the context of the two arguments, word pair information, as well as the arguments' internal constituent and dependency parses. Our results on the PDTB yields a significant 14.1% improvement over the baseline. In our error analysis, we discuss four challenges in recognizing implicit relations in the PDTB.
Subfields: Artificial Intelligence
View Paper: https://www.semanticscholar.org/paper/9a4eda6e694a8b6f0d400e243e2416f9146709d9
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Iryna Gurevych
- Jianfeng Gao
- Mohit Bansal
- Karthik Narasimhan
- Regina Barzilay
- Kyunghyun Cho
- Jacob Eisenstein
- Gholamreza Haffari
Citations in the corpus
- Identifying Argumentative Discourse Structures in Persuasive Essays (2014, methodology): “In addition, we extract production rules from the parse tree as proposed by Lin et al. (2009) to capture syntactic characteristics of an argument component.”
- A Latent Variable Recurrent Neural Network for Discourse-Driven Language Models (2016, background): “Discourse and dialog modeling Early work on discourse relation classification utilizes rich, hand-crafted feature sets (Joty et al., 2012; Lin et al., 2009; Sagae, 2009).”
- Implicit Discourse Relation Classification: We Need to Talk about Evaluation (2020, methodology): “For L2, the standard protocol is to use 11 labels after eliminating five infrequent labels as proposed in Lin et al. (2009). Sometimes ENTREL is also included in the L2 label set (Xue et al.”
- Implicit Discourse Relation Identification for Open-domain Dialogues (2019, background): “For implicit discourse relations however, where there is no discourse clue, relations needs to be inferred on the basis of textual features, making this a challenging problem in discourse parsing (Li and Nenkova, 2014; Lin et al., 2009).”
- Machine Comprehension with Discourse Relations (2015, background): “It has been well documented that identifying discourse relations without explicit markers is significantly harder than with markers (Pitler et al., 2008; Lin et al., 2009; Park and Cardie, 2012).”
- Parsing Argumentation Structures in Persuasive Essays (2016, background): “Lin, Kan, and Ng (2009) showed that production rules collected from parse trees yield good results and Louis et al. (2010) found that features based on named entities do not perform as well as lexical features.”