Sentence Level Discourse Parsing using Syntactic and Lexical Information

By Radu Soricut, Daniel Marcu. North American Chapter of the Association for Computational Linguistics, 2003

488 citations recorded by the source corpus.

We introduce two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees. The models use syntactic and lexical features. A discourse parsing algorithm that implements these models derives discourse parse trees with an error reduction of 18.8% over a state-of-the-art decision-based discourse parser. A set of empirical evaluations shows that our discourse parsing model is sophisticated enough to yield discourse trees at an accuracy level that matches near-human levels of performance.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/0b3858c0c31c6f0826c891a42367671f6e76d46c

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

Citations in the corpus

Lexicon-Based Methods for Sentiment Analysis (2011, background): “We also showed how a sentence-level discourse parser, developed by Soricut and Marcu (2003), could be used to differentiate between main and secondary parts of the text.”
A PDTB-styled end-to-end discourse parser (2012, background): “2 http://wing.comp.nus.edu.sg/~linzihen/parser/ Continuing in this vein, Soricut and Marcu (2003) introduced probabilistic models to segment a sentence into edus, and to derive their corresponding sentence-level discourse structure, using lexical and syntactic features.”
Cross-lingual and cross-domain discourse segmentation of entire documents (2017, background): “1% in F1), is as good as the other neural network based system (Subba and Di Eugenio, 2007), and is close to SPADE (Soricut and Marcu, 2003) (85.”
Argument Mining: A Survey (2020, methodology): “One of the first supervised learning approaches to segmentation was introduced by Soricut and Marcu (2003) as a part of the SPADE system, which also operates on lexicalised syntactic trees.”
Parsing Argumentation Structures in Persuasive Essays (2016, methodology): “We adopt the features introduced by Soricut and Marcu (2003).”
Survey on Aspect-Level Sentiment Analysis (2016, methodology): “are acquired using the HILDA [79] discourse parser which returns a coarse-grained set of discourse segments as defined in [80], which are based on the Rhetorical Structure Theory [81].”
Learning-Based Single-Document Summarization with Compression and Anaphoricity Constraints (2016, methodology): “tively slowly. Smart selection of content therefore has room to improve over taking a preﬁx of the document. we use the ﬁrst-order projective parsing model of McDonald et al. (2005) and features from Soricut and Marcu (2003), Hernault et al. (2010), and Joty et al. (2013). When using the same head a”
Catching the Drift: Probabilistic Content Models, with Applications to Generation and Summarization (2004, methodology): “By automatically annotating a large corpus of texts with discourse relations via a rhetorical parser (Marcu, 1997; Soricut and Marcu, 2003), we may be able to incorporate domain-independent relationships into the transition structure of our content models.”
The Effects of Human Variation in DUC Summarization Evaluation (2004, background): “SEE allowed the judges to step through predefined units of the model summary (elementary discourse units/EDUs) (Soricut and Marcu, 2003) and for each unit of that summary, mark the sentences in the peer summary that expressed [all(4), most(3), some(2), hardly any(1) or none(0)] of the content in the”
Automatic sense prediction for implicit discourse relations in text (2009, background): “Soricut and Marcu (2003) address the task of parsing discourse structures within the same sentence .”
From Textbooks to Knowledge: A Case Study in Harvesting Axiomatic Knowledge from Textbooks to Solve Geometry Problems (2017, background): “The features are deﬁned over candidate spans forming the text split, are strongly inspired from rhetorical structure theory (Mann and Thompson, 1988) and previous works on discourse parsing (Marcu, 2000; Soricut and Marcu, 2003).”
Joint Syntacto-Discourse Parsing and the Syntacto-Discourse Treebank (2017, background): “In other cases, one EDU node may correspond to multiple subtrees in PTB, and for these EDUs we use the lowest common ancestor of those subtrees in the PTB as the label of that EDU in the converted tree.”