# Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling

Source: [Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labeling](<https://www.sota2.com/research/paper/68fa6b6a1e209131cea2e34f>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:36:04.767Z

Authors: Shengqiong Wu, Hao Fei, Fei Li, Donghong Ji, Meishan Zhang, Yijiang Liu, Chong Teng

Published: 2021-10-05T12:45:59.000Z

## Abstract

Unified opinion role labeling (ORL) aims to detect all possible opinion structures of 'opinion-holder-target' in one shot, given a text. The existing transition-based unified method, unfortunately, is subject to longer opinion terms and fails to solve the term overlap issue. Current top performance has been achieved by employing the span-based graph model, which however still suffers from both high model complexity and insufficient interaction among opinions and roles. In this work, we investigate a novel solution by revisiting the transition architecture, and augmenting it with a pointer network (PointNet). The framework parses out all opinion structures in linear-time complexity, meanwhile breaks through the limitation of any length of terms with PointNet. To achieve the explicit opinion-role interactions, we further propose a unified dependency-opinion graph (UDOG), co-modeling the syntactic dependency structure and the partial opinion-role structure. We then devise a relation-centered graph aggregator (RCGA) to encode the multi-relational UDOG, where the resulting high-order representations are used to promote the predictions in the vanilla transition system. Our model achieves new state-of-the-art results on the MPQA benchmark. Analyses further demonstrate the superiority of our methods on both efficacy and efficiency.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Opinion Role Labeling on MPQA Target 2.0 (test)](<https://www.sota2.com/research/sota/opinion-role-labeling-on-mpqa-target-2-0-test.md>): Opinion Role Labeling; MPQA Target 2.0 (test); O-R F1 (hd): 62.34.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2110.02001>)

[PDF](<https://arxiv.org/pdf/2110.02001.pdf>)

[Implementation](<https://github.com/ChocoWu/SyPtrTrans-ORL>)