• Home
  • Search
  • Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph
  • Cite Icon7
  • https://doi.org/10.24963/ijcai.2022/571Copy DOI Icon

Conversational Semantic Role Labeling with Predicate-Oriented Latent Graph

  • Jul 1, 2022
  • Hao Fei +4 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Conversational semantic role labeling (CSRL) is a newly proposed task that uncovers the shallow semantic structures in a dialogue text. Unfortunately several important characteristics of the CSRL task have been overlooked by the existing works, such as the structural information integration, near-neighbor influence. In this work, we investigate the integration of a latent graph for CSRL. We propose to automatically induce a predicate-oriented latent graph (POLar) with a predicate-centered gaussian mechanism, by which the nearer and informative words to the predicate will be allocated with more attention. The POLar structure is then dynamically pruned and refined so as to best fit the task need. We additionally introduce an effective dialogue-level pre-trained language model, CoDiaBERT, for better supporting multiple utterance sentences and handling the speaker coreference issue in CSRL. Our system outperforms best-performing baselines on three benchmark CSRL datasets with big margins, especially achieving over 4% F1 score improvements on the cross-utterance argument detection. Further analyses are presented to better understand the effectiveness of our proposed methods.

Similar Papers
  • Video Transcripts

Syntax Role for Neural Semantic Role Labeling

  • Oct 21, 2021
  • Underline Science Inc.
  • Zuchao Li +3
  • PDF
  • Conference Article
  • Citations28

Towards Semi-Supervised Learning for Deep Semantic Role Labeling

  • Jan 01, 2018
  • Sanket Vaibhav Mehta +2
  • PDF
  • Conference Article
  • Citations2

A Dual-Layer Semantic Role Labeling System

  • Jan 01, 2015
  • Lun-Wei Ku +2
  • Research Article
  • Citations7

Semantic role labelling using transfer learning model

  • Feb 01, 2021
  • Journal of Physics: Conference Series
  • Archana M Nair +1
  • Conference Article
  • Citations1

Expansion of Feature Information for Korean Semantic Role Labeling

  • Dec 19, 2015
  • Advanced science and technology letters
  • Byeong-Cheol Jo +5
  • Book Chapter
  • Citations1

Research on Semantic Role Labeling Method

  • Jan 01, 2019
  • Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
  • Bo Jiang +1
  • Research Article

Towards patent text analysis based on semantic role labelling

  • Jan 01, 2017
  • International Journal of Computational Science and Engineering
  • Hongjiao Xu +3
  • Research Article

Towards patent text analysis based on semantic role labelling

  • Jan 01, 2017
  • International Journal of Computational Science and Engineering
  • Yanqing He +4
  • Conference Article
  • Citations4

Chinese Nominal Entity Recognition with Semantic Role Labeling

  • Dec 01, 2009
  • Wenbo Pang +1
  • Research Article

A Review On Semantic Role Labelling For Indian Languages

  • Jan 01, 2024
  • Educational Administration: Theory and Practice
  • Rashmi R Chouhan +1
  • PDF
  • Conference Article
  • Citations1

A Shortest-path Method for Arc-factored Semantic Role Labeling

  • Jan 01, 2014
  • Xavier Lluís +2
  • Conference Article
  • Citations2

A Study on Semantic Role Labeling of Korean Sentence

  • Dec 01, 2009
  • Yude Bi +1
  • Research Article
  • Citations338

Pre-Trained Language Models and Their Applications

  • Jun 01, 2023
  • Engineering
  • Haifeng Wang +4
  • PDF
  • Conference Article
  • Citations8

ANNA”:" Enhanced Language Representation for Question Answering

  • Jan 01, 2022
  • Changwook Jun +6
  • PDF
  • Research Article
  • Citations64

BIOSMILE: a semantic role labeling system for biomedical verbs using a maximum-entropy model with automatically generated template features.

  • Sep 01, 2007
  • BMC Bioinformatics
  • Richard Tzong-Han Tsai +9
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.