# Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction

arXiv: https://arxiv.org/abs/2107.12214 · HTML: https://mlsanity.com/paper/2107.12214/

## Key facts

- Cited by 60 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 50 references that are in the map.
- First posted on arXiv 26 Jul 2021.

## Builds on (most cited first, 21 of 21)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding](https://mlsanity.com/paper/1804.07461/) (2018)
- [XLNet: Generalized Autoregressive Pretraining for Language Understanding](https://mlsanity.com/paper/1906.08237/) (2019)
- [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://mlsanity.com/paper/1909.11942/) (2019)
- [AllenNLP: A Deep Semantic Natural Language Processing Platform](https://mlsanity.com/paper/1803.07640/) (2018)
- [Entity, Relation, and Event Extraction with Contextualized Span Representations](https://mlsanity.com/paper/1909.03546/) (2019)
- [End-to-end Neural Coreference Resolution](https://mlsanity.com/paper/1707.07045/) (2017)
- [Knowing What, How and Why: A Near Complete Solution for Aspect-based Sentiment Analysis](https://mlsanity.com/paper/1911.01616/) (2019)
- [A General Framework for Information Extraction using Dynamic Span Graphs](https://mlsanity.com/paper/1904.03296/) (2019)
- [Position-Aware Tagging for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2010.02609/) (2020)
- [A Unified Model for Opinion Target Extraction and Target Sentiment Prediction](https://mlsanity.com/paper/1811.05082/) (2018)
- [An Interactive Multi-Task Learning Network for End-to-End Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/1906.06906/) (2019)
- [Transformation Networks for Target-Oriented Sentiment Classification](https://mlsanity.com/paper/1805.01086/) (2018)
- [Aspect Term Extraction with History Attention and Selective Transformation](https://mlsanity.com/paper/1805.00760/) (2018)
- [Jointly Predicting Predicates and Arguments in Neural Semantic Role Labeling](https://mlsanity.com/paper/1805.04787/) (2018)
- [Neural Aspect and Opinion Term Extraction with Mined Rules as Weak Supervision](https://mlsanity.com/paper/1907.03750/) (2019)
- [A Multi-task Learning Framework for Opinion Triplet Extraction](https://mlsanity.com/paper/2010.01512/) (2020)
- [Progressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis](https://mlsanity.com/paper/1906.01213/) (2019)
- [Unsupervised Word and Dependency Path Embeddings for Aspect Term Extraction](https://mlsanity.com/paper/1605.07843/) (2016)
- [Learning Explicit and Implicit Structures for Targeted Sentiment Analysis](https://mlsanity.com/paper/1909.07593/) (2019)

## Built on by (most cited first, 30 of 60)

- [Unified Structure Generation for Universal Information Extraction](https://mlsanity.com/paper/2203.12277/) (2022)
- [Is GPT-3 a Good Data Annotator?](https://mlsanity.com/paper/2212.10450/) (2022)
- [A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges](https://mlsanity.com/paper/2203.01054/) (2022)
- [RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction](https://mlsanity.com/paper/2203.09101/) (2022)
- [Universal Information Extraction as Unified Semantic Matching](https://mlsanity.com/paper/2301.03282/) (2023)
- [DiaASQ : A Benchmark of Conversational Aspect-based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2211.05705/) (2022)
- [SentiPrompt: Sentiment Knowledge Enhanced Prompt-Tuning for Aspect-Based Sentiment Analysis](https://mlsanity.com/paper/2109.08306/) (2021)
- [A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach](https://mlsanity.com/paper/2211.10018/) (2022)
- [A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2204.12674/) (2022)
- [UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning](https://mlsanity.com/paper/2211.10986/) (2022)
- [STAGE: Span Tagging and Greedy Inference Scheme for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2211.15003/) (2022)
- [RexUIE: A Recursive Method with Explicit Schema Instructor for Universal Information Extraction](https://mlsanity.com/paper/2304.14770/) (2023)
- [FSUIE: A Novel Fuzzy Span Mechanism for Universal Information Extraction](https://mlsanity.com/paper/2306.14913/) (2023)
- [The Limits of ChatGPT in Extracting Aspect-Category-Opinion-Sentiment Quadruples: A Comparative Analysis](https://mlsanity.com/paper/2310.06502/) (2023)
- [Easy-to-Hard Learning for Information Extraction](https://mlsanity.com/paper/2305.09193/) (2023)
- [MiniConGTS: A Near Ultimate Minimalist Contrastive Grid Tagging Scheme for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2406.11234/) (2024)
- [Dynamic Multi-Scale Context Aggregation for Conversational Aspect-Based Sentiment Quadruple Analysis](https://mlsanity.com/paper/2309.15476/) (2023)
- [Self-Training with Pseudo-Label Scorer for Aspect Sentiment Quad Prediction](https://mlsanity.com/paper/2406.18078/) (2024)
- [DFM: Dialogue Foundation Model for Universal Large-Scale Dialogue-Oriented Task Learning](https://mlsanity.com/paper/2205.12662/) (2022)
- [Domain-Expanded ASTE: Rethinking Generalization in Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2305.14434/) (2023)
- [A Pairing Enhancement Approach for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2306.10042/) (2023)
- [UniPCM: Universal Pre-trained Conversation Model with Task-aware Automatic Prompt](https://mlsanity.com/paper/2309.11065/) (2023)
- [CONTRASTE: Supervised Contrastive Pre-training With Aspect-based Prompts For Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2310.15577/) (2023)
- [Structural Bias for Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2209.00820/) (2022)
- [AX-MABSA: A Framework for Extremely Weakly Supervised Multi-label Aspect Based Sentiment Analysis](https://mlsanity.com/paper/2211.03837/) (2022)
- [Bidirectional Generative Framework for Cross-domain Aspect-based Sentiment Analysis](https://mlsanity.com/paper/2305.09509/) (2023)
- [Better Sampling of Negatives for Distantly Supervised Named Entity Recognition](https://mlsanity.com/paper/2305.13142/) (2023)
- [Measuring Your ASTE Models in The Wild: A Diversified Multi-domain Dataset For Aspect Sentiment Triplet Extraction](https://mlsanity.com/paper/2305.17448/) (2023)
- [A semantically enhanced dual encoder for aspect sentiment triplet extraction](https://mlsanity.com/paper/2306.08373/) (2023)
- [iACOS: Advancing Implicit Sentiment Extraction with Informative and Adaptive Negative Examples](https://mlsanity.com/paper/2311.03896/) (2023)

## Abstract (arXiv)

Aspect Sentiment Triplet Extraction (ASTE) is the most recent subtask of ABSA which outputs triplets of an aspect target, its associated sentiment, and the corresponding opinion term. Recent models perform the triplet extraction in an end-to-end manner but heavily rely on the interactions between each target word and opinion word. Thereby, they cannot perform well on targets and opinions which contain multiple words. Our proposed span-level approach explicitly considers the interaction between the whole spans of targets and opinions when predicting their sentiment relation. Thus, it can make predictions with the semantics of whole spans, ensuring better sentiment consistency. To ease the high computational cost caused by span enumeration, we propose a dual-channel span pruning strategy by incorporating supervision from the Aspect Term Extraction (ATE) and Opinion Term Extraction (OTE) tasks. This strategy not only improves computational efficiency but also distinguishes the opinion and target spans more properly. Our framework simultaneously achieves strong performance for the ASTE as well as ATE and OTE tasks. In particular, our analysis shows that our span-level approach achieves more significant improvements over the baselines on triplets with multi-word targets or opinions.