Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing 2017
DOI: 10.18653/v1/d17-1217
|View full text |Cite
|
Sign up to set email alerts
|

Document-Level Multi-Aspect Sentiment Classification as Machine Comprehension

Abstract: Document-level multi-aspect sentiment classification is an important task for customer relation management. In this paper, we model the task as a machine comprehension problem where pseudo questionanswer pairs are constructed by a small number of aspect-related keywords and aspect ratings. A hierarchical iterative attention model is introduced to build aspectspecific representations by frequent and repeated interactions between documents and aspect questions. We adopt a hierarchical architecture to represent b… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
48
0
1

Year Published

2018
2018
2022
2022

Publication Types

Select...
4
1
1

Relationship

0
6

Authors

Journals

citations
Cited by 72 publications
(49 citation statements)
references
References 26 publications
0
48
0
1
Order By: Relevance
“…We conduct our experiments on three public datasets on DASC, i.e., TripUser , TripAdvisor (Wang et al, 2010) and BeerAdvocate (McAuley et al, 2012;Lei et al, 2016). In the experiment, we adopt Discourse Segmentation and those with ‡ are from Yin et al (2017) Tool 3 to segment all reviews in the three datasets into EDUs (i.e., clauses). Moreover, we adopt training/development/testing settings (8:1:1) by following Yin et al (2017); .…”
Section: Experimental Settingsmentioning
confidence: 99%
See 4 more Smart Citations
“…We conduct our experiments on three public datasets on DASC, i.e., TripUser , TripAdvisor (Wang et al, 2010) and BeerAdvocate (McAuley et al, 2012;Lei et al, 2016). In the experiment, we adopt Discourse Segmentation and those with ‡ are from Yin et al (2017) Tool 3 to segment all reviews in the three datasets into EDUs (i.e., clauses). Moreover, we adopt training/development/testing settings (8:1:1) by following Yin et al (2017); .…”
Section: Experimental Settingsmentioning
confidence: 99%
“…In the experiment, we adopt Discourse Segmentation and those with ‡ are from Yin et al (2017) Tool 3 to segment all reviews in the three datasets into EDUs (i.e., clauses). Moreover, we adopt training/development/testing settings (8:1:1) by following Yin et al (2017); . Table 1 shows the statistics of the three datasets.…”
Section: Experimental Settingsmentioning
confidence: 99%
See 3 more Smart Citations