Machine Comprehension with Discourse Relations

By Karthik Narasimhan, Regina Barzilay. 2015

67 citations recorded by the source corpus.

This paper proposes a novel approach for incorporating discourse information into machine comprehension applications. Traditionally, such information is computed using off-the-shelf discourse analyzers. This design provides limited opportunities for guiding the discourse parser based on the requirements of the target task. In contrast, our model induces relations between sentences while optimizing a task-specific objective. This approach enables the model to benefit from discourse information without relying on explicit annotations of discourse structure during training. The model jointly identifies relevant sentences, establishes relations between them and predicts an answer. We implement this idea in a discriminative framework with hidden variables that capture relevant sentences and relations unobserved during training. Our experiments demonstrate that the discourse aware model outperforms state-of-the-art machine comprehension systems.1

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

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

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

Looking Beyond the Surface: A Challenge Set for Reading Comprehension over Multiple Sentences (2018, background): “…and multi-sentence questions; models proposed for this task yielded considerably better performance on the single-sentence questions than on the multi- 252 sentence questions (according to Narasimhan and Barzilay (2015) accuracy of about 83% and 60% on these two types of questions, respectively).”
Text Understanding with the Attention Sum Reader Network (2016, background): “This is an advantage compared to smaller machine understanding datasets like MCTest (Richardson et al., 2013) that have only hundreds of training examples and therefore the best performing systems usually rely on hand-crafted features (Sachan et al., 2015; Narasimhan and Barzilay, 2015).”
Machine Comprehension with Syntax, Frames, and Semantics (2015, neutral): “7 We also compare to concurrently-published re-sults (Narasimhan and Barzilay, 2015; Sachan et al., 2015).”
A Parallel-Hierarchical Model for Machine Comprehension on Sparse Data (2016, background): “Among deep models, mechanisms of attention and working memory are common, as in Weston et al. (2014) and Hermann et al. (2015).”
Attention-Based Convolutional Neural Network for Machine Comprehension (2016, background): “In these works, a common route is ﬁrst to deﬁne a regularized loss function based on assumed feature vectors, then the effort focuses on designing effective features based on various rules.”
Self-Training for Jointly Learning to Ask and Answer Questions (2018, background): “Various approaches (Sachan et al., 2015; Wang et al., 2015; Sachan and Xing, 2016b; Sachan et al., 2016; Narasimhan and Barzilay, 2015) have been proposed for solving this task.”
Evidence Sentence Extraction for Machine Reading Comprehension (2019, background): “…resolution, frame semantics, and discourse relations is widely used to improve machine comprehension (Wang et al., 2015; Sachan et al., 2015; Narasimhan and Barzilay, 2015; Sun et al., 2018) especially when there are only hundreds of documents available in a dataset such as MCTest…”
Hierarchical Attention Flow for Multiple-Choice Reading Comprehension (2018, methodology): “Existing models (Richardson, Burges, and Renshaw 2013; Sachan et al. 2015; Narasimhan and Barzilay 2015; Wang et al. 2015; Smith et al. 2015; Trischler et al. 2016; Yin, Ebert, and Schütze 2016; Lai et al. 2017) for multiple-choice reading comprehension score each candidate option independently.”