An Analysis of Sentential Neighbors in Implicit Discourse Relation Prediction
This work addresses a challenge in natural language processing for researchers, but it is incremental as it builds on existing methods to test context effects.
The paper tackled the problem of implicit discourse relation prediction by analyzing the impact of incorporating broader context beyond two neighboring sentences, finding that such inclusion is harmful to classification performance.
Discourse relation classification is an especially difficult task without explicit context markers (Prasad et al., 2008). Current approaches to implicit relation prediction solely rely on two neighboring sentences being targeted, ignoring the broader context of their surrounding environments (Atwell et al., 2021). In this research, we propose three new methods in which to incorporate context in the task of sentence relation prediction: (1) Direct Neighbors (DNs), (2) Expanded Window Neighbors (EWNs), and (3) Part-Smart Random Neighbors (PSRNs). Our findings indicate that the inclusion of context beyond one discourse unit is harmful in the task of discourse relation classification.