Using Syntax to Disambiguate Explicit Discourse Connectives in Text

@inproceedings{Pitler2009UsingST,
  title={Using Syntax to Disambiguate Explicit Discourse Connectives in Text},
  author={Emily Pitler and A. Nenkova},
  booktitle={ACL},
  year={2009}
}
Discourse connectives are words or phrases such as once, since, and on the contrary that explicitly signal the presence of a discourse relation. [...] Key Result We report state-of-the-art results for identifying discourse vs. non-discourse usage and human-level performance on sense disambiguation.Expand
Automatic Disambiguation of French Discourse Connectives
TLDR
The results with the French Discourse Treebank show that syntactic and lexical features developed for English texts are as effective for French and allow the disambiguation of French discourse connectives with an accuracy of 94.2%. Expand
Multilingual Annotation and Disambiguation of Discourse Connectives for Machine Translation
TLDR
New approaches for improving the accuracy of manual annotation of three discourse connectives by using parallel corpora, with results for automatic disambiguation are state-of-the-art, at up to 85% accuracy using surface features. Expand
Inducing Discourse Connectives from Parallel Texts
TLDR
A new method is proposed that exploits parallel corpora and collocation extraction techniques to automatically induce discourse connectives from an English-French parallel text, based on identifying candidates and ranking them using Log-Likelihood Ratio. Expand
Identifying Explicit Discourse Connectives in Text
TLDR
Improvements to the state-of-the-art for identifying explicit discourse connectives in the Penn Discourse Treebank and the Biomedical Discourse Relation Bank are reported. Expand
Exploiting a lexical resource for discourse connective disambiguation in German
TLDR
This paper improves over published results for connective identification and sense classification for explicit discourse relations in German, as two individual sub-tasks of the overarching Shallow Discourse Parsing task, and introduces first results for German sense classification. Expand
Using a Discourse Bank and a Lexicon for the Automatic Identification of Discourse Connectives
We describe two new resources that have been prepared for European Portuguese and how they are used for discourse parsing: the Portuguese subpart of the TED-MDB corpus, a multilingual corpus of TEDExpand
Identification and Disambiguation of Lexical Cues of Rhetorical Relations across Different Text Genres
TLDR
Evaluation results are reported for various cues of the CIRCUMSTANCE relation, confirming the value of syntactic features for the task of cue disambiguation in the context of Rhetorical Structure Theory. Expand
Disambiguating Explicit Discourse Connectives without Oracles
TLDR
A very simple model using only lexical and predicted part- of-speech features actually performs slightly better than Pitler and Nenkova (2009) and not significantly different from a state-of-the-art model, which combines lexical, part-ofspeech, and parse features. Expand
Discourse Relations and Conjoined VPs: Automated Sense Recognition
TLDR
This work demonstrates a sequential classification pipeline for multi-label sense classification of discourse relations using a newly available corpus of discourse-annotated intra-sentential conjoined verb phrases. Expand
Multilabel Tagging of Discourse Relations in Ambiguous Temporal Connectives
TLDR
This work argues that the information contained in these ‘additional’ relations is indeed useful and presents an approach to tag multiple fine-grained discourse relations in ambiguous connectives from the German T¨ uBa-D/Z corpus and shows that good accuracy is possible even for inferred relations that are not part of the connective’s ‘core’ meaning. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 15 REFERENCES
Experiments on Sense Annotations and Sense Disambiguation of Discourse Connectives
Discourse connectives can be analyzed as discourse level predicates which projectpredicate-argument structure on a par with verbs at the sentence level. The PennDiscourse Treebank (PDTB) reflects thisExpand
Empirical Studies on the Disambiguation of Cue Phrases
TLDR
This paper reports results of empirical studies on discourse and sentential uses of cue phrases, in which both text-based and prosodic features were examined for disambiguating power. Expand
Easily Identifiable Discourse Relations
We present a corpus study of local discourse relations based on the Penn Discourse Tree Bank, a large manually annotated corpus of explicitly or implicitly realized relations. We show that whileExpand
Discourse Connective Argument Identification with Connective Specific Rankers
TLDR
This work shows that using models for specific connective and types of connectives and interpolating them with a general model improves performance, and describes additional features that provide greater sensitivity to morphological, syntactic, and discourse patterns, and less sensitivity to parse quality. Expand
The rhetorical parsing of unrestricted texts: a surface-based approach
TLDR
The extent to which well-formed rhetorical structures can be automatically derived by means of surface-form-based algorithms is explored and shows that automatically derived rhetorical structure trees can be successfully exploited in the context of text summarization. Expand
Sentence Level Discourse Parsing using Syntactic and Lexical Information
TLDR
Two probabilistic models that can be used to identify elementary discourse units and build sentence-level discourse parse trees are introduced and shown to be sophisticated enough to yield discourse trees at an accuracy level that matches near-human levels of performance. Expand
The Penn Discourse TreeBank 2.0
We present the second version of the Penn Discourse Treebank, PDTB-2.0, describing its lexically-grounded annotations of discourse relations and their two abstract object arguments over the 1 millionExpand
Using automatically labelled examples to classify rhetorical relations: an assessment
TLDR
Whether automatically labelled, lexically marked examples are really suitable training material for classifiers that are then applied to unmarked examples is tested and some evidence that this behaviour is largely independent of the classifiers used and seems to lie in the data itself is found. Expand
The utility of parse-derived features for automatic discourse segmentation
TLDR
It is demonstrated that the SPADE-inspired context-free features are critical to achieving this level of accuracy on this task, and counters recent results suggesting that purely finite-state approaches can perform competitively. Expand
Classification of Discourse Coherence Relations: An Exploratory Study using Multiple Knowledge Sources
TLDR
This approach considers, and determines the contributions of, a variety of syntactic and lexico-semantic features in discourse coherence relations and achieves 81% accuracy on the task of discourse relation type classification and 70% accuracy in relation identification. Expand
...
1
2
...