{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T22:22:01Z","timestamp":1783203721927,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,24]],"date-time":"2024-10-24T00:00:00Z","timestamp":1729728000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,24]]},"DOI":"10.1145\/3674805.3686695","type":"proceedings-article","created":{"date-parts":[[2024,10,15]],"date-time":"2024-10-15T18:39:24Z","timestamp":1729017564000},"page":"359-370","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["A Transformer-based Approach for Augmenting Software Engineering Chatbots Datasets"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1863-9147","authenticated-orcid":false,"given":"Ahmad","family":"Abdellatif","sequence":"first","affiliation":[{"name":"University of Calgary, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2293-3656","authenticated-orcid":false,"given":"Khaled","family":"Badran","sequence":"additional","affiliation":[{"name":"Concordia University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7084-2594","authenticated-orcid":false,"given":"Diego Elias","family":"Costa","sequence":"additional","affiliation":[{"name":"Concordia University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1285-9878","authenticated-orcid":false,"given":"Emad","family":"Shihab","sequence":"additional","affiliation":[{"name":"Concordia University, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,24]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3078384"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10664-019-09788-5"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3379597.3387472"},{"key":"e_1_3_2_1_4_1","unstructured":"Diego Costa Emad\u00a0Shihab Ahmad\u00a0Abdellatif Khaled\u00a0Badran. 2024. A Transformer-based Approach for Augmenting Software Engineering Chatbots Datasets. https:\/\/zenodo.org\/records\/11121853. (Accessed on 05\/06\/2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association","author":"Amin-Nejad Ali","year":"2020","unstructured":"Ali Amin-Nejad, Julia Ive, and Sumithra Velupillai. 2020. Exploring Transformer Text Generation for Medical Dataset Augmentation. In Proceedings of the 12th Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 4699\u20134708."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487672"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3338906.3340442"},{"key":"e_1_3_2_1_8_1","unstructured":"Pradipta Bora. [n. d.]. geekpradd\/PyDictionary: PyDictionary is a Dictionary Module for Python 2\/3 to get meanings translations synonyms and antonyms of words. https:\/\/github.com\/geekpradd\/PyDictionary. (Accessed on 07\/01\/2024)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3180155.3180238"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-5522"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TSE.2021.3128234"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3524842.3528440"},{"key":"e_1_3_2_1_13_1","unstructured":"Microsoft Docs. 2022. Good example utterances. https:\/\/docs.microsoft.com\/en-us\/azure\/cognitive-services\/luis\/luis-concept-utterance. (Accessed on 03\/30\/2024)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387940.3391534"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387940.3391534"},{"key":"e_1_3_2_1_16_1","volume-title":"The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Vol.\u00a0abs\/2105","author":"Dopierre Thomas","year":"2021","unstructured":"Thomas Dopierre, C. Gravier, and Wilfried Logerais. 2021. ProtAugment: Unsupervised diverse short-texts paraphrasing for intent detection meta-learning. In The 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Vol.\u00a0abs\/2105.12995."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196448"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3660812"},{"key":"e_1_3_2_1_19_1","volume-title":"WordNet: An Electronic Lexical Database","author":"Fellbaum Christiane","unstructured":"Christiane Fellbaum. 1998. WordNet: An Electronic Lexical Database. Bradford Books. https:\/\/mitpress.mit.edu\/9780262561167\/"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.deelio-1.4"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/IALP.2018.8629181"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3556925"},{"key":"e_1_3_2_1_23_1","unstructured":"jsphdnl. 2023. nlp Conversational Data for building a chat bot. https:\/\/stackoverflow.com\/questions\/45821517\/conversational-data-for-building-a-chat-bot. (Accessed on 01\/19\/2024)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1131"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2017.4541027"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/MS.2017.4541027"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/BotSE.2019.00008"},{"key":"e_1_3_2_1_28_1","volume-title":"Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady 10 (February","author":"Levenshtein I","year":"1966","unstructured":"Vladimir\u00a0I Levenshtein. 1966. Binary Codes Capable of Correcting Deletions, Insertions and Reversals. Soviet Physics Doklady 10 (February 1966), 707."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387940.3391501"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5609"},{"key":"e_1_3_2_1_32_1","volume-title":"Machine Learning and Knowledge Extraction, Andreas Holzinger, Peter Kieseberg, A\u00a0Min Tjoa","author":"Marivate Vukosi","unstructured":"Vukosi Marivate and Tshephisho Sefara. 2020. Improving Short Text Classification Through Global Augmentation Methods. In Machine Learning and Knowledge Extraction, Andreas Holzinger, Peter Kieseberg, A\u00a0Min Tjoa, and Edgar Weippl (Eds.). Springer International Publishing, Cham, 385\u2013399."},{"key":"e_1_3_2_1_33_1","unstructured":"Microsoft. 2023. Utterances - Azure Cognitive Services | Microsoft Docs. https:\/\/docs.microsoft.com\/en-us\/azure\/cognitive-services\/luis\/concepts\/utterances. (Accessed on 01\/08\/2024)."},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/BotSE.2019.00016"},{"key":"e_1_3_2_1_35_1","unstructured":"Rasa. [n. d.]. Conversational AI Platform | Superior Customer Experiences Start Here. https:\/\/rasa.com\/. (Accessed on 07\/01\/2024)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358040"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5114"},{"key":"e_1_3_2_1_38_1","unstructured":"Sheri. 2022. Python Intent classification for Chatbot. https:\/\/stackoverflow.com\/questions\/62970861\/intent-classification-for-chatbot. (Accessed on 04\/28\/2024)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.4"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/2950290.2983989"},{"key":"e_1_3_2_1_41_1","unstructured":"Tmbo. 2022. multiple entity recognition\u00b7 Issue #427 \u00b7 RasaHQ\/rasa. https:\/\/github.com\/RasaHQ\/rasa\/issues\/427. (Accessed on 03\/23\/2024)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510621"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","unstructured":"Jason Wei and Kai Zou. 2019. EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics Hong Kong China 6382\u20136388. https:\/\/doi.org\/10.18653\/v1\/D19-1670","DOI":"10.18653\/v1\/D19-1670"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","unstructured":"Peter West Ximing Lu Ari Holtzman Chandra Bhagavatula Jena\u00a0D. Hwang and Yejin Choi. 2021. Reflective Decoding: Beyond Unidirectional Generation with Off-the-Shelf Language Models. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). Association for Computational Linguistics Online 1435\u20131450. https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.114","DOI":"10.18653\/v1\/2021.acl-long.114"},{"key":"e_1_3_2_1_45_1","volume-title":"Statistical methods in the atmospheric sciences. Vol.\u00a0100","author":"Wilks S","unstructured":"Daniel\u00a0S Wilks. 2011. Statistical methods in the atmospheric sciences. Vol.\u00a0100. Academic press."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/SANER.2016.10"},{"key":"e_1_3_2_1_47_1","volume-title":"Proc. of NAACL.","author":"Zhang Yuan","year":"2019","unstructured":"Yuan Zhang, Jason Baldridge, and Luheng He. 2019. PAWS: Paraphrase Adversaries from Word Scrambling. In Proc. of NAACL."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"crossref","unstructured":"Jianing Zhou Hongyu Gong and Suma Bhat. 2020. PIE: A Parallel Idiomatic Expression Corpus for Idiomatic Sentence Generation and Paraphrasing. In The Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP 2021) MWE Workshop 2021.","DOI":"10.18653\/v1\/2021.mwe-1.5"}],"event":{"name":"ESEM '24: ACM \/ IEEE International Symposium on Empirical Software Engineering and Measurement","location":"Barcelona Spain","acronym":"ESEM '24","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"]},"container-title":["Proceedings of the 18th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674805.3686695","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3674805.3686695","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T12:58:33Z","timestamp":1755867513000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3674805.3686695"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,24]]},"references-count":48,"alternative-id":["10.1145\/3674805.3686695","10.1145\/3674805"],"URL":"https:\/\/doi.org\/10.1145\/3674805.3686695","relation":{},"subject":[],"published":{"date-parts":[[2024,10,24]]},"assertion":[{"value":"2024-10-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}