Automatic sense prediction for implicit discourse relations in text

Abstract

We present a series of experiments on automatically identifying the sense of implicit discourse relations, i.e. relations that are not marked with a discourse connective such as "but" or "because". We work with a corpus of implicit relations present in newspaper text and report results on a test set that is representative of the naturally occurring distribution of senses. We use several linguistically informed features, including polarity tags, Levin verb classes, length of verb phrases, modality, context, and lexical features. In addition, we revisit past approaches using lexical pairs from unannotated text as features, explain some of their shortcomings and propose modifications. Our best combination of features outperforms the baseline from data intensive approaches by 4% for comparison and 16% for contingency.

Cross-lingual RST Discourse Parsing

“…We use the first three words and the last word along with their POS, features that have proven useful for discourse (Pitler et al, 2009), and the words in the head set (Sagae, 2009) -i.e. words whose head in the dependency graph is not in the EDU -, here limited to the first three.…”

“…Number/date/percent/money We also use 4 indicators of the presence of a date, a number, an amount of money and a percentage, features that have proven to be useful for discourse (Pitler et al, 2009). We build these features using simple regular expressions.…”

Text-level Discourse Dependency Parsing

“…Then the discourse relation between each pair of sentences is annotated independently to characterize its predication. A majority of researches regard discourse parsing as a classification task and mainly focus on exploiting various linguistic features and classifiers when using PDTB (Wellner et al, 2006;Pitler et al, 2009;Wang et al, 2010). However, the predicatearguments annotation scheme itself has such a limitation that one can only obtain the local discourse relations without knowing the rich context.…”

The DCU Discourse Parser: A Sense Classification Task

“…The word grows their bigram in terms of Cartesian product of elements in different Arg1 and Arg2 which has a order from Arg1 to Arg2 where this bi-gram is embedded in the word embedding. Followed by Pitler et al (Pitler et al, 2008) we use the 100 frequent wordpairs in training set for each category of relation. We did not delete function words/stop-words.…”