Related papers: High-order Refining for End-to-end Chinese Semantic Role Labeling

High-order Refining for End-to-end Chinese Semantic Role Labeling

URL: http://arxiv.org/abs/2009.06957v1
Date: Tue, 15 Sep 2020 10:01:27 GMT
Title: High-order Refining for End-to-end Chinese Semantic Role Labeling
Authors: Hao Fei and Yafeng Ren and Donghong Ji
Abstract summary: We present a high-order refining mechanism to perform interaction between all predicate-argument pairs. Our high-order model achieves state-of-the-art results on Chinese SRL data, including CoNLL09 and Universal Proposition Bank.
Score: 34.74181162627023
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Current end-to-end semantic role labeling is mostly accomplished via graph-based neural models. However, these all are first-order models, where each decision for detecting any predicate-argument pair is made in isolation with local features. In this paper, we present a high-order refining mechanism to perform interaction between all predicate-argument pairs. Based on the baseline graph model, our high-order refining module learns higher-order features between all candidate pairs via attention calculation, which are later used to update the original token representations. After several iterations of refinement, the underlying token representations can be enriched with globally interacted features. Our high-order model achieves state-of-the-art results on Chinese SRL data, including CoNLL09 and Universal Proposition Bank, meanwhile relieving the long-range dependency issues.

Related papers

COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinement [80.18490952057125]
Iterative refinement has emerged as an effective paradigm for enhancing the capabilities of large language models (LLMs) on complex tasks. We propose Context-Wise Order-Agnostic Language Modeling (COrAL) to overcome these challenges. Our approach models multiple token dependencies within manageable context windows, enabling the model to perform iterative refinement internally.
arXiv Detail & Related papers (2024-10-12T23:56:19Z)
Transferring Neural Potentials For High Order Dependency Parsing [0.0]
The present paper uses biaffine scores to provide an estimate of the arc scores and is then propagated into a graphical model. The inference inside the graphical model is solved using dual decomposition.
arXiv Detail & Related papers (2023-06-18T03:58:41Z)
HIORE: Leveraging High-order Interactions for Unified Entity Relation Extraction [85.80317530027212]
We propose HIORE, a new method for unified entity relation extraction. The key insight is to leverage the complex association among word pairs, which contains richer information than the first-order word-by-word interactions. Experiments show that HIORE achieves the state-of-the-art performance on relation extraction and an improvement of 1.11.8 F1 points over the prior best unified model.
arXiv Detail & Related papers (2023-05-07T14:57:42Z)
Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
arXiv Detail & Related papers (2022-03-15T01:24:51Z)
X2Parser: Cross-Lingual and Cross-Domain Framework for Task-Oriented Compositional Semantic Parsing [51.81533991497547]
Task-oriented compositional semantic parsing (TCSP) handles complex nested user queries. We present X2 compared a transferable Cross-lingual and Cross-domain for TCSP. We propose to predict flattened intents and slots representations separately and cast both prediction tasks into sequence labeling problems.
arXiv Detail & Related papers (2021-06-07T16:40:05Z)
End-to-end Semantic Role Labeling with Neural Transition-based Model [25.921541005563856]
End-to-end semantic role labeling (SRL) has been received increasing interest. Recent work is mostly focused on graph-based neural models. We present the first work of transition-based neural models for end-to-end SRL.
arXiv Detail & Related papers (2021-01-02T07:35:54Z)
High-order Semantic Role Labeling [86.29371274587146]
This paper introduces a high-order graph structure for the neural semantic role labeling model. It enables the model to explicitly consider not only the isolated predicate-argument pairs but also the interaction between the predicate-argument pairs. Experimental results on 7 languages of the CoNLL-2009 benchmark show that the high-order structural learning techniques are beneficial to the strong performing SRL models.
arXiv Detail & Related papers (2020-10-09T15:33:54Z)
Improving Coreference Resolution by Leveraging Entity-Centric Features with Graph Neural Networks and Second-order Inference [12.115691569576345]
Coreferent mentions usually spread far apart in an entire text, making it difficult to incorporate entity-level features. We propose a graph neural network-based coreference resolution method that can capture the entity-centric information. A global inference algorithm up to second-order features is also presented to optimally cluster mentions into consistent groups.
arXiv Detail & Related papers (2020-09-10T02:22:21Z)
Guider l'attention dans les modeles de sequence a sequence pour la prediction des actes de dialogue [10.171893967006017]
We leverage seq2seq approaches widely adopted in Neural Machine Translation to improve the modelling of tag sequentiality. In this work, we introduce a seq2seq model tailored for DA classification using: a hierarchical encoder, a novel guided attention mechanism and beam search applied to both training and inference. The proposed approach achieves an unmatched accuracy score of 85% on SwDA, and state-of-the-art accuracy score of 91.6% on MRDA.
arXiv Detail & Related papers (2020-02-21T17:09:19Z)

This list is automatically generated from the titles and abstracts of the papers in this site.