{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/unifiedabsa-a-unified-absa-framework-based-on","title":"UnifiedABSA: A Unified ABSA Framework Based on Multi-task Instruction Tuning","arxiv_id":"2211.10986","date":"2022-11-20","proceeding":null,"authors":["Zengzhi Wang","Rui Xia","Jianfei Yu"],"abstract":"Aspect-Based Sentiment Analysis (ABSA) aims to provide fine-grained aspect-level sentiment information. There are many ABSA tasks, and the current dominant paradigm is to train task-specific models for each task. However, application scenarios of ABSA tasks are often diverse. This solution usually requires a large amount of labeled data from each task to perform excellently. These dedicated models are separately trained and separately predicted, ignoring the relationship between tasks. To tackle these issues, we present UnifiedABSA, a general-purpose ABSA framework based on multi-task instruction tuning, which can uniformly model various tasks and capture the inter-task dependency with multi-task learning. Extensive experiments on two benchmark datasets show that UnifiedABSA can significantly outperform dedicated models on 11 ABSA tasks and show its superiority in terms of data efficiency.","url_abs":"https://arxiv.org/abs/2211.10986v1","url_pdf":"https://arxiv.org/pdf/2211.10986v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"aspect-extraction","task_name":"Aspect Extraction"},{"task_slug":"aspect-sentiment-triplet-extraction","task_name":"Aspect Sentiment Triplet Extraction"},{"task_slug":"aspect-term-extraction-and-sentiment","task_name":"Aspect Term Extraction and Sentiment Classification"},{"task_slug":"aspect-based-sentiment-analysis-1","task_name":"Aspect-Based Sentiment Analysis"},{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"aspect-category-opinion-sentiment-quadruple","task_name":"Aspect-Category-Opinion-Sentiment Quadruple Extraction"},{"task_slug":"aspect-oriented-opinion-extraction","task_name":"Aspect-oriented  Opinion Extraction"},{"task_slug":"multi-task-learning","task_name":"Multi-Task Learning"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"}],"methods":[{"method_slug":"adafactor","method_name":"Adafactor"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"glu","method_name":"Gated Linear Unit"},{"method_slug":"inverse-square-root-schedule","method_name":"Inverse Square Root Schedule"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"sentencepiece","method_name":"SentencePiece"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"t5","method_name":"T5"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-absa-on-acos","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"ACOS","model":"UnifiedABSA (multi-task)","rank_in_archive_order":5,"of":9,"metrics":{"F1 (Laptop)":"42.58","F1 (Restaurant)":"60.60"},"uses_additional_data":true}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2211.10986","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}