# Effective Token Graph Modeling using a Novel Labeling Strategy for Structured Sentiment Analysis arXiv: https://arxiv.org/abs/2203.10796 ยท HTML: https://mlsanity.com/paper/2203.10796/ ## Key facts - Cited by 22 papers in the map (data through 14 Oct 2026). - Builds on 13 of its 22 references that are in the map. - First posted on arXiv 21 Mar 2022. ## Builds on (most cited first, 13 of 13) - [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018) - [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017) - [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016) - [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021) - [Circle Loss: A Unified Perspective of Pair Similarity Optimization](https://mlsanity.com/paper/2002.10857/) (2020) - [A Convolutional Neural Network for Modelling Sentences](https://mlsanity.com/paper/1404.2188/) (2014) - [TPLinker: Single-stage Joint Extraction of Entities and Relations Through Token Pair Linking](https://mlsanity.com/paper/2010.13415/) (2020) - [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1906.06906/) (2019) - [Simpler but More Accurate Semantic Dependency Parsing](https://mlsanity.com/paper/1807.01396/) (2018) - [Recursive Neural Conditional Random Fields for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1603.06679/) (2016) - [Structured Sentiment Analysis as Dependency Graph Parsing](https://mlsanity.com/paper/2105.14504/) (2021) - [A Fine-Grained Sentiment Dataset for Norwegian](https://mlsanity.com/paper/1911.12722/) (2019) - [MultiBooked: A Corpus of Basque and Catalan Hotel Reviews Annotated for Aspect-level Sentiment Classification](https://mlsanity.com/paper/1803.08614/) (2018) ## Built on by (most cited first, 22 of 22) - [LayoutLLM-T2I: Eliciting Layout Guidance from LLM for Text-to-Image Generation](https://mlsanity.com/paper/2308.05095/) (2023) - [Reasoning Implicit Sentiment with Chain-of-Thought Prompting](https://mlsanity.com/paper/2305.11255/) (2023) - [LasUIE: Unifying Information Extraction with Latent Adaptive Structure-aware Generative Language Model](https://mlsanity.com/paper/2304.06248/) (2023) - [DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2211.05705/) (2022) - [Scene Graph as Pivoting: Inference-time Image-free Unsupervised Multimodal Machine Translation with Visual Scene Hallucination](https://mlsanity.com/paper/2305.12256/) (2023) - [Generating Visual Spatial Description via Holistic 3D Scene Understanding](https://mlsanity.com/paper/2305.11768/) (2023) - [Cross2StrA: Unpaired Cross-lingual Image Captioning with Cross-lingual Cross-modal Structure-pivoted Alignment](https://mlsanity.com/paper/2305.12260/) (2023) - [Constructing Holistic Spatio-Temporal Scene Graph for Video Semantic Role Labeling](https://mlsanity.com/paper/2308.05081/) (2023) - [Revisiting Disentanglement and Fusion on Modality and Context in Conversational Multimodal Emotion Recognition](https://mlsanity.com/paper/2308.04502/) (2023) - [Joint Alignment of Multi-Task Feature and Label Spaces for Emotion Cause Pair Extraction](https://mlsanity.com/paper/2209.04112/) (2022) - [Constructing Code-mixed Universal Dependency Forest for Unbiased Cross-lingual Relation Extraction](https://mlsanity.com/paper/2305.12258/) (2023) - [TCAB: A Large-Scale Text Classification Attack Benchmark](https://mlsanity.com/paper/2210.12233/) (2022) - [ECQED: Emotion-Cause Quadruple Extraction in Dialogs](https://mlsanity.com/paper/2306.03969/) (2023) - [TKDP: Threefold Knowledge-enriched Deep Prompt Tuning for Few-shot Named Entity Recognition](https://mlsanity.com/paper/2306.03974/) (2023) - [Revisiting Conversation Discourse for Dialogue Disentanglement](https://mlsanity.com/paper/2306.03975/) (2023) - [A Bi-directional Multi-hop Inference Model for Joint Dialog Sentiment Classification and Act Recognition](https://mlsanity.com/paper/2308.04424/) (2023) - [Structured Sentiment Analysis as Transition-based Dependency Graph Parsing](https://mlsanity.com/paper/2305.05311/) (2023) - [DialogRE^C+: An Extension of DialogRE to Investigate How Much Coreference Helps Relation Extraction in Dialogs](https://mlsanity.com/paper/2308.04498/) (2023) - [Revisiting Structured Sentiment Analysis as Latent Dependency Graph Parsing](https://mlsanity.com/paper/2407.04801/) (2024) - [Dynamic Syntax Mapping: A New Approach to Unsupervised Syntax Parsing](https://mlsanity.com/paper/2312.14966/) (2023) - [Modeling Unified Semantic Discourse Structure for High-quality Headline Generation](https://mlsanity.com/paper/2403.15776/) (2024) - [GADFA: Generator-Assisted Decision-Focused Approach for Opinion Expressing Timing Identification](https://mlsanity.com/paper/2410.01169/) (2024) ## Abstract (arXiv) The state-of-the-art model for structured sentiment analysis casts the task as a dependency parsing problem, which has some limitations: (1) The label proportions for span prediction and span relation prediction are imbalanced. (2) The span lengths of sentiment tuple components may be very large in this task, which will further exacerbate the imbalance problem. (3) Two nodes in a dependency graph cannot have multiple arcs, therefore some overlapped sentiment tuples cannot be recognized. In this work, we propose nichetargeting solutions for these issues. First, we introduce a novel labeling strategy, which contains two sets of token pair labels, namely essential label set and whole label set. The essential label set consists of the basic labels for this task, which are relatively balanced and applied in the prediction layer. The whole label set includes rich labels to help our model capture various token relations, which are applied in the hidden layer to softly influence our model. Moreover, we also propose an effective model to well collaborate with our labeling strategy, which is equipped with the graph attention networks to iteratively refine token representations, and the adaptive multi-label classifier to dynamically predict multiple relations between token pairs. We perform extensive experiments on 5 benchmark datasets in four languages. Experimental results show that our model outperforms previous SOTA models by a large margin.