A hierarchical neural autoencoder for paragraphs and documents

J Li, MT Luong, D Jurafsky - arxiv preprint arxiv:1506.01057, 2015 - arxiv.org
Natural language generation of coherent long texts like paragraphs or longer documents is
a challenging problem for recurrent networks models. In this paper, we explore an important …

Summarizing opinions: Aspect extraction meets sentiment prediction and they are both weakly supervised

S Angelidis, M Lapata - arxiv preprint arxiv:1808.08858, 2018 - arxiv.org
We present a neural framework for opinion summarization from online product reviews
which is knowledge-lean and only requires light supervision (eg, in the form of product …

Rhetorical structure theory: A comprehensive review of theory, parsing methods and applications

S Hou, S Zhang, C Fei - Expert Systems with Applications, 2020 - Elsevier
Rhetorical structure theory (RST) is a significant theory about discourse organization. With
an increasing number of research interests focus on RST, many novel parsing approaches …

Better document-level sentiment analysis from rst discourse parsing

P Bhatia, Y Ji, J Eisenstein - arxiv preprint arxiv:1509.01599, 2015 - arxiv.org
Discourse structure is the hidden link between surface features and document-level
properties, such as sentiment polarity. We show that the discourse analyses produced by …

Learning structured text representations

Y Liu, M Lapata - Transactions of the Association for Computational …, 2018 - direct.mit.edu
In this paper, we focus on learning structure-aware document representations from data
without recourse to a discourse parser or additional annotations. Drawing inspiration from …

Codra: A novel discriminative framework for rhetorical analysis

S Joty, G Carenini, RT Ng - Computational Linguistics, 2015 - direct.mit.edu
Clauses and sentences rarely stand on their own in an actual discourse; rather, the
relationship between them carries important information that allows the discourse to express …

[PDF][PDF] Towards news verification: Deception detection methods for news discourse

VL Rubin, NJ Conroy, Y Chen - Hawaii international conference …, 2015 - sites.socsci.uci.edu
News verification is a process of determining whether a particular news report is truthful or
deceptive. Deliberately deceptive (fabricated) news creates false conclusions in the readers' …

[PDF][PDF] A linear-time bottom-up discourse parser with constraints and post-editing

VW Feng, G Hirst - Proceedings of the 52nd Annual Meeting of the …, 2014 - aclanthology.org
Text-level discourse parsing remains a challenge. The current state-of-the-art overall
accuracy in relation assignment is 55.73%, achieved by Joty et al.(2013). However, their …

Multiple instance learning networks for fine-grained sentiment analysis

S Angelidis, M Lapata - Transactions of the Association for …, 2018 - direct.mit.edu
We consider the task of fine-grained sentiment analysis from the perspective of multiple
instance learning (MIL). Our neural model is trained on document sentiment labels, and …

Truth and deception at the rhetorical structure level

VL Rubin, T Lukoianova - Journal of the Association for …, 2015 - Wiley Online Library
This paper furthers the development of methods to distinguish truth from deception in textual
data. We use rhetorical structure theory (RST) as the analytic framework to identify …