Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser. Previous research usually makes use of one kind of discourse framework such as PDTB or RST to improve the classification performance on discourse relations. Actually, under different discourse annotation frameworks, there exist multiple corpor...

We introduce a simple semi-supervised approach to improve implicit discourse relation identification. This approach harnesses large amounts of automatically extracted discourse connectives along with their arguments to construct new distributional word representations. Specifically, we represent words in the space of discourse connectives as a way to directly encode their rhetorical function. E...

Discourse parsing is considered as one of the most challenging natural language processing (NLP) tasks. Implicit discourse relation classification is the bottleneck for discourse parsing. Without the guide of explicit discourse connectives, the relation of sentence pairs are very hard to be inferred. This paper proposes a stacking neural network model to solve the classification problem in whic...

This paper presents a detailed comparative framework for assessing the usefulness of unsupervised word representations for identifying so-called implicit discourse relations. Specifically, we compare standard one-hot word pair representations against low-dimensional ones based on Brown clusters and word embeddings. We also consider various word vector combination schemes for deriving discourse ...

In the 1970s, memory researchers converged on interesting phenomena observed in Korsakoff-syndrome amnesic patients. These patients' performances on difficult tasks were reliably improved by practice sessions from which they could recall nothing. Related findings of indirect memory effects in college students triggered wide attention to phenomena that, in 1985, were first identified as implicit...

Predicting the sense of a discourse relation is particularly challenging when connective markers are missing. To address this challenge, we propose a simple deep neural network approach that replaces manual feature extraction by introducing event vectors as an alternative representation, which can be pre-trained using a very large corpus, without explicit annotation. We model discourse argument...

Implicit discourse relation recognition is an extremely challenging task, for it lacks of explicit connectives between two arguments. Currently, most methods to address this problem can be regarded as to solve it in two stages, the first is to extract features from two arguments separately, and the next is to apply those features to some standard classifier. However, during the first stage, tho...

We present a reformulation of the word pair features typically used for the task of disambiguating implicit relations in the Penn Discourse Treebank. Our word pair features achieve significantly higher performance than the previous formulation when evaluated without additional features. In addition, we present results for a full system using additional features which achieves close to state of ...

The main aim of this study was to examine whether an assessment of implicit bullying attitudes could add to the prediction of bullying behavior after controlling for explicit bullying attitudes. Primary school children (112 boys and 125 girls, M age = 11 years, 5 months) completed two newly developed measures of implicit bullying attitudes (a general Implicit Association Test on bullying and a ...

In one case Charles River Associates has dealt with, the tax authority asserted that a subsidiary is of such strategic importance to the group’s ultimate parent company that the subsidiary’s “stand-alone” credit rating should be adjusted upwards to the parent’s rating due to implicit support. This is despite the fact that an explicit guarantee had not been provided by the parent and despite the...