Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction
Not on the map. Why?
Abstract (arXiv)
Latest efforts on cross-lingual relation extraction (XRE) aggressively leverage the language-consistent structural features from the universal dependency (UD) resource, while they may largely suffer from biased transfer (e.g., either target-biased or source-biased) due to the inevitable linguistic disparity between languages. In this work, we investigate an unbiased UD-based XRE transfer by constructing a type of code-mixed UD forest. We first translate the sentence of the source language to the parallel target-side language, for both of which we parse the UD tree respectively. Then, we merge the source-/target-side UD structures as a unified code-mixed UD forest. With such forest features, the gaps of UD-based XRE between the training and predicting phases can be effectively closed. We conduct experiments on the ACE XRE benchmark datasets, where the results demonstrate that the proposed code-mixed UD forests help unbiased UD-based XRE transfer, with which we achieve significant XRE performance gains.
Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 30 of its 66 references that are in the map. First posted on arXiv 20 May 2023.
Builds on
30 of 66 references.
References · 30
- 2017Graph Attention Networkscited by 8,923
- 2016Deep Biaffine Attention for Neural Dependency Parsingcited by 334
- 2016End-to-End Relation Extraction using LSTMs on Sequences and Tree Structurescited by 161
- 2018Graph Convolution over Pruned Dependency Trees Improves Relation Extractioncited by 146
- 2021Unified Named Entity Recognition as Word-Word Relation Classificationcited by 90
- 2020CoSDA-ML: Multi-Lingual Code-Switching Data Augmentation for Zero-Shot Cross-Lingual NLPcited by 79
- 2020Cross-Lingual Semantic Role Labeling with High-Quality Translated Training Corpuscited by 49
- 2020GATE: Graph Attention Transformer Encoder for Cross-lingual Relation and Event Extractioncited by 43
- 2023LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Modelcited by 43
- 2016Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Textcited by 31
- 2021Learn from Syntax: Improving Pair-wise Aspect and Opinion Terms Extractionwith Rich Syntactic Knowledgecited by 31
- 2021Mastering the Explicit Opinion-role Interaction: Syntax-aided Neural Transition System for Unified Opinion Role Labelingcited by 25
18 more
- 2020Retrofitting Structure-aware Transformer Language Model for End Taskscited by 24
- 2021End-to-end Semantic Role Labeling with Neural Transition-based Modelcited by 22
- 2022Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysiscited by 22
- 2023On the Robustness of Aspect-based Sentiment Analysis: Rethinking Model, Data, and Trainingcited by 20
- 2022OneEE: A One-Stage Framework for Fast Overlapping and Nested Event Extractioncited by 18
- 2022Entity-centered Cross-document Relation Extractioncited by 18
- 2018A Dataset for Building Code-Mixed Goal Oriented Conversation Systemscited by 16
- 2020Mimic and Conquer: Heterogeneous Tree Structure Distillation for Syntactic NLPcited by 15
- 2022Conversational Semantic Role Labeling with Predicate-Oriented Latent Graphcited by 14
- 2019Neural Cross-Lingual Relation Extraction Based on Bilingual Word Embedding Mappingcited by 12
- 2014Cross-lingual Annotation Projection for Semantic Rolescited by 11
- 2020Cross-lingual Semantic Role Labeling with Model Transfercited by 11
- 2019Cross-Lingual Dependency Parsing Using Code-Mixed TreeBankcited by 10
- 2022Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extractioncited by 10
- 2019Improved Sentiment Detection via Label Transfer from Monolingual to Synthetic Code-Switched Textcited by 8
- 2019Translate and Label! An Encoder-Decoder Approach for Cross-lingual Semantic Role Labelingcited by 7
- 2018Polyglot Semantic Role Labelingcited by 5
- 2020Cross-Lingual Adaptation Using Universal Dependenciescited by 2
Built on by
Citing papers per year: 2023: 4; 2024: 0; 2025: 0; 2026: 2.
6 papers.
- 2023Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labelingcited by 15
- 2023Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognitioncited by 13
- 2023A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognitioncited by 2
- 2023DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogscited by 1
- 2026AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languagescited by 1
- 2026Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMscited by 0
- 2026AfriSUD: A Dependency Treebank Collection for Evaluating Models on African Languages10 Jun 2026
- 2026Code Mixologist : A Practitioner's Guide to Building Code-Mixed LLMs21 Jan 2026
- 2023Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling9 Aug 2023
- 2023Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition8 Aug 2023
- 2023DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs8 Aug 2023
- 2023A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition8 Aug 2023