Skip to content
conftrace_
2022 ACL ACL 2022

Direct parsing to sentiment graphs

Abstract

AbstractThis paper demonstrates how a graph-based semantic parser can be applied to the task of structured sentiment analysis, directly predicting sentiment graphs from text. We advance the state of the art on 4 out of 5 standard benchmark sets. We release the source code, models and predictions.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

David Samuel, Jeremy Barnes, Robin Kurtz, Stephan Oepen, Lilja Øvrelid, Erik Velldal

Topics

Natural Language Processing > Understanding > Parsing Natural Language Processing > Understanding > Semantic Analysis Machine Learning > Core Methods > Graphical Models Natural Language Processing > Applications > Sentiment Analysis

Keywords

structured prediction sentiment analysis semantic parsing structured sentiment analysis graph-based parsing graph-based parser sentiment graph
Download PDF

More from ACL 2022

All ACL 2022 papers →
Augmenting Document Representations for Dense Retrieval with Interpolation and Perturbation
WLASL-LEX: a Dataset for Recognising Phonological Properties in American Sign Language
Investigating person-specific errors in chat-oriented dialogue systems
XDBERT: Distilling Visual Information to BERT from Cross-Modal Systems to Improve Language Understanding
As Little as Possible, as Much as Necessary: Detecting Over- and Undertranslations with Contrastive Conditioning
How Distributed are Distributed Representations? An Observation on the Locality of Syntactic Information in Verb Agreement Tasks