{"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/data-augmentation-for-intent-classification-1","title":"Data Augmentation for Intent Classification with Off-the-shelf Large Language Models","arxiv_id":"2204.01959","date":"2022-04-05","proceeding":"NLP4ConvAI (ACL) 2022 5","authors":["Gaurav Sahu","Pau Rodriguez","Issam H. Laradji","Parmida Atighehchian","David Vazquez","Dzmitry Bahdanau"],"abstract":"Data augmentation is a widely employed technique to alleviate the problem of data scarcity. In this work, we propose a prompting-based approach to generate labelled training data for intent classification with off-the-shelf language models (LMs) such as GPT-3. An advantage of this method is that no task-specific LM-fine-tuning for data generation is required; hence the method requires no hyper-parameter tuning and is applicable even when the available training data is very scarce. We evaluate the proposed method in a few-shot setting on four diverse intent classification tasks. We find that GPT-generated data significantly boosts the performance of intent classifiers when intents in consideration are sufficiently distinct from each other. In tasks with semantically close intents, we observe that the generated data is less helpful. Our analysis shows that this is because GPT often generates utterances that belong to a closely-related intent instead of the desired one. We present preliminary evidence that a prompting-based GPT classifier could be helpful in filtering the generated data to enhance its quality.","url_abs":"https://arxiv.org/abs/2204.01959v1","url_pdf":"https://arxiv.org/pdf/2204.01959v1.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":"data-augmentation-for-intent-classification-1","repo_url":"https://github.com/elementai/data-augmentation-with-llms","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"intent-classification","task_name":"Intent Classification"},{"task_slug":"intent-classification-1","task_name":"intent-classification"}],"methods":[{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"attention-dropout","method_name":"Attention Dropout"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"cosine-annealing","method_name":"Cosine Annealing"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"discriminative-fine-tuning","method_name":"Discriminative Fine-Tuning"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt","method_name":"GPT"},{"method_slug":"gpt-3","method_name":"GPT-3"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"linear-warmup-with-cosine-annealing","method_name":"Linear Warmup With Cosine Annealing"},{"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"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2204.01959","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.01959"}},"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/elementai/data-augmentation-with-llms","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"ran":1,"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":"f15117422b72cf43","entry":"get_only_chars","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/eda_utils.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/eda_utils.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f15117422b72cf43"}},{"code_sha256_prefix":"a71ad2709e49eaa1","entry":"compile_results","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"runners/compile_results.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/runners/compile_results.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a71ad2709e49eaa1"}},{"code_sha256_prefix":"47b1f7854f607d9f","entry":"fmt","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"runners/compile_results.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/runners/compile_results.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"47b1f7854f607d9f"}},{"code_sha256_prefix":"e21dc00b769aac77","entry":"get_data_dict","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/hwu64_utils.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/hwu64_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e21dc00b769aac77"}},{"code_sha256_prefix":"461078e5a822e755","entry":"get_synonyms","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/eda_utils.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/eda_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"461078e5a822e755"}},{"code_sha256_prefix":"c516938250ca27b0","entry":"gptj_complete","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/augment_slices.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/augment_slices.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"c516938250ca27b0"}},{"code_sha256_prefix":"6644e45fa8204287","entry":"load_dataset_slices","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/augment_slices.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/augment_slices.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6644e45fa8204287"}},{"code_sha256_prefix":"56c4355e2e469224","entry":"openai_complete","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/augment_slices.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/augment_slices.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56c4355e2e469224"}},{"code_sha256_prefix":"7fa8a4756763ccbc","entry":"segregate_sub_folders","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"runners/compile_results.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/runners/compile_results.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7fa8a4756763ccbc"}},{"code_sha256_prefix":"56366bd6ff30a29a","entry":"synonym_replacement","repo":"elementai/data-augmentation-with-llms","repo_kind":"official","path":"utils/data_utils/eda_utils.py","file_url":"https://github.com/elementai/data-augmentation-with-llms/blob/HEAD/utils/data_utils/eda_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"56366bd6ff30a29a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}