{"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/adapt-or-get-left-behind-domain-adaptation","title":"Adapt or Get Left Behind: Domain Adaptation through BERT Language Model Finetuning for Aspect-Target Sentiment Classification","arxiv_id":"1908.11860","date":"2019-08-30","proceeding":"LREC 2020 5","authors":["Alexander Rietzler","Sebastian Stabinger","Paul Opitz","Stefan Engl"],"abstract":"Aspect-Target Sentiment Classification (ATSC) is a subtask of Aspect-Based Sentiment Analysis (ABSA), which has many applications e.g. in e-commerce, where data and insights from reviews can be leveraged to create value for businesses and customers. Recently, deep transfer-learning methods have been applied successfully to a myriad of Natural Language Processing (NLP) tasks, including ATSC. Building on top of the prominent BERT language model, we approach ATSC using a two-step procedure: self-supervised domain-specific BERT language model finetuning, followed by supervised task-specific finetuning. Our findings on how to best exploit domain-specific language model finetuning enable us to produce new state-of-the-art performance on the SemEval 2014 Task 4 restaurants dataset. In addition, to explore the real-world robustness of our models, we perform cross-domain evaluation. We show that a cross-domain adapted BERT language model performs significantly better than strong baseline models like vanilla BERT-base and XLNet-base. Finally, we conduct a case study to interpret model prediction errors.","url_abs":"https://arxiv.org/abs/1908.11860v2","url_pdf":"https://arxiv.org/pdf/1908.11860v2.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":"adapt-or-get-left-behind-domain-adaptation","repo_url":"https://github.com/deepopinion/domain-adapted-atsc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"adapt-or-get-left-behind-domain-adaptation","repo_url":"https://github.com/ardyh/bert-ada","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"adapt-or-get-left-behind-domain-adaptation","repo_url":"https://github.com/yangheng95/LC-ABSA","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"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":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"sentiment-analysis","task_name":"Sentiment Analysis"},{"task_slug":"sentiment-classification","task_name":"Sentiment Classification"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bert","method_name":"BERT"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-linear-decay","method_name":"Linear Warmup With Linear Decay"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"weight-decay","method_name":"Weight Decay"},{"method_slug":"wordpiece","method_name":"WordPiece"}],"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":"BERT-ADA","rank_in_archive_order":10,"of":48,"metrics":{"Laptop (Acc)":"80.23","Mean Acc (Restaurant + Laptop)":"84.06","Restaurant (Acc)":"87.89"},"uses_additional_data":true}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1908.11860","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.11860"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/deepopinion/domain-adapted-atsc","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ardyh/bert-ada","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yangheng95/LC-ABSA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":7},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1},"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"e442357dd18171c6","entry":"convert_example_to_features","repo":"deepopinion/domain-adapted-atsc","repo_kind":"official","path":"finetuning_and_classification/finetune_on_pregenerated.py","file_url":"https://github.com/deepopinion/domain-adapted-atsc/blob/HEAD/finetuning_and_classification/finetune_on_pregenerated.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"e442357dd18171c6"}},{"code_sha256_prefix":"ed04fa9adc7b8bad","entry":"convert_examples_to_features","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/utils_glue.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/utils_glue.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ed04fa9adc7b8bad"}},{"code_sha256_prefix":"1243fa98fb78271d","entry":"create_instances_from_document","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/pregenerate_training_data.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/pregenerate_training_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1243fa98fb78271d"}},{"code_sha256_prefix":"9f94d1d09b49e09e","entry":"create_masked_lm_predictions","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/pregenerate_training_data.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/pregenerate_training_data.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9f94d1d09b49e09e"}},{"code_sha256_prefix":"c987c7b3fcee5ba4","entry":"generate_qa_sentence_pairs_nosampling","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/utils_glue.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/utils_glue.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c987c7b3fcee5ba4"}},{"code_sha256_prefix":"475bf1a7164076b3","entry":"semeval2014term_to_aspectsentiment_hr","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/utils_glue.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/utils_glue.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"475bf1a7164076b3"}},{"code_sha256_prefix":"72cb221552ac14db","entry":"semeval2014term_to_aspectsentiment_hr","repo":"ardyh/bert-ada","repo_kind":"listed","path":"finetuning_and_classification/utils_glue_ardy.py","file_url":"https://github.com/ardyh/bert-ada/blob/HEAD/finetuning_and_classification/utils_glue_ardy.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"72cb221552ac14db"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}