{"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/interactive-attention-networks-for-aspect","title":"Interactive Attention Networks for Aspect-Level Sentiment Classification","arxiv_id":"1709.00893","date":"2017-09-04","proceeding":null,"authors":["Dehong Ma","Sujian Li","Xiaodong Zhang","Houfeng Wang"],"abstract":"Aspect-level sentiment classification aims at identifying the sentiment\npolarity of specific target in its context. Previous approaches have realized\nthe importance of targets in sentiment classification and developed various\nmethods with the goal of precisely modeling their contexts via generating\ntarget-specific representations. However, these studies always ignore the\nseparate modeling of targets. In this paper, we argue that both targets and\ncontexts deserve special treatment and need to be learned their own\nrepresentations via interactive learning. Then, we propose the interactive\nattention networks (IAN) to interactively learn attentions in the contexts and\ntargets, and generate the representations for targets and contexts separately.\nWith this design, the IAN model can well represent a target and its collocative\ncontext, which is helpful to sentiment classification. Experimental results on\nSemEval 2014 Datasets demonstrate the effectiveness of our model.","url_abs":"http://arxiv.org/abs/1709.00893v1","url_pdf":"http://arxiv.org/pdf/1709.00893v1.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":[{"paper_slug":"interactive-attention-networks-for-aspect","repo_url":"https://github.com/NUSTM/ABSC","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}},{"paper_slug":"interactive-attention-networks-for-aspect","repo_url":"https://github.com/mindspore-courses/ABSA-MindSpore","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"mindspore","reach":{"status":"gone","observed_at":"2026-09-17","how":"tree_404+repo_404"}},{"paper_slug":"interactive-attention-networks-for-aspect","repo_url":"https://github.com/sag111/cabsar","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}},{"paper_slug":"interactive-attention-networks-for-aspect","repo_url":"https://github.com/songyouwei/ABSA-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"interactive-attention-networks-for-aspect","repo_url":"https://github.com/tori22/sentiment_torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"aspect-based-sentiment-analysis","task_name":"Aspect-Based Sentiment Analysis (ABSA)"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/aspect-based-sentiment-analysis-on-semeval","task":"Aspect-Based Sentiment Analysis (ABSA)","dataset":"SemEval-2014 Task-4","model":"IAN","rank_in_archive_order":37,"of":48,"metrics":{"Laptop (Acc)":"72.10","Mean Acc (Restaurant + Laptop)":"75.35","Restaurant (Acc)":"78.60"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1709.00893","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}