{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T08:44:31Z","timestamp":1780389871063,"version":"3.54.1"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031560590","type":"print"},{"value":"9783031560606","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-56060-6_21","type":"book-chapter","created":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T15:02:17Z","timestamp":1710514937000},"page":"318-332","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["An\u00a0EcoSage Assistant: Towards Building A Multimodal Plant Care Dialogue Assistant"],"prefix":"10.1007","author":[{"given":"Mohit","family":"Tomar","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abhisek","family":"Tiwari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tulika","family":"Saha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prince","family":"Jha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sriparna","family":"Saha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,16]]},"reference":[{"key":"21_CR1","first-page":"23716","volume":"35","author":"JB Alayrac","year":"2022","unstructured":"Alayrac, J.B., et al.: Flamingo: a visual language model for few-shot learning. Adv. Neural. Inf. Process. Syst. 35, 23716\u201323736 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR2","doi-asserted-by":"publisher","unstructured":"Awadalla, A., et al.: Openflamingo (2023). https:\/\/doi.org\/10.5281\/zenodo.7733589","DOI":"10.5281\/zenodo.7733589"},{"key":"21_CR3","unstructured":"Baevski, A., Hsu, W.N., Xu, Q., Babu, A., Gu, J., Auli, M.: Data2vec: a general framework for self-supervised learning in speech, vision and language. In: International Conference on Machine Learning, pp. 1298\u20131312. PMLR (2022)"},{"key":"21_CR4","unstructured":"Bai, Y., et al.: Training a helpful and harmless assistant with reinforcement learning from human feedback. arXiv preprint arXiv:2204.05862 (2022)"},{"key":"21_CR5","doi-asserted-by":"publisher","unstructured":"Black, S., Leo, G., Wang, P., Leahy, C., Biderman, S.: GPT-Neo: Large Scale Autoregressive Language Modeling with Mesh-Tensorflow (2021). https:\/\/doi.org\/10.5281\/zenodo.5297715. If you use this software, please cite it using these metadata","DOI":"10.5281\/zenodo.5297715"},{"key":"21_CR6","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR7","unstructured":"Chiang, W.L., et al.: Vicuna: an open-source chatbot impressing GPT-4 with 90%* ChatGPT quality (2023). https:\/\/lmsys.org\/blog\/2023-03-30-vicuna\/"},{"key":"21_CR8","unstructured":"Chowdhery, A., et al.: PaLM: scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"21_CR9","unstructured":"Chung, H.W., et al.: Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)"},{"key":"21_CR10","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"11","key":"21_CR12","doi-asserted-by":"publisher","first-page":"2107","DOI":"10.3390\/agronomy11112107","volume":"11","author":"G Fenu","year":"2021","unstructured":"Fenu, G., Malloci, F.M.: Diamos plant: a dataset for diagnosis and monitoring plant disease. Agronomy 11(11), 2107 (2021)","journal-title":"Agronomy"},{"issue":"5","key":"21_CR13","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"JL Fleiss","year":"1971","unstructured":"Fleiss, J.L.: Measuring nominal scale agreement among many raters. Psychol. Bull. 76(5), 378 (1971)","journal-title":"Psychol. Bull."},{"key":"21_CR14","unstructured":"Gao, L., et al.: The pile: an 800GB dataset of diverse text for language modeling. arXiv preprint arXiv:2101.00027 (2020)"},{"key":"21_CR15","unstructured":"Glaese, A., et al.: Improving alignment of dialogue agents via targeted human judgements. arXiv preprint arXiv:2209.14375 (2022)"},{"key":"21_CR16","doi-asserted-by":"crossref","unstructured":"Jain, R., Saha, T., Chakraborty, S., Saha, S.: Domain infused conversational response generation for tutoring based virtual agent. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892890"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Jain, R., Saha, T., Lalwani, J., Saha, S.: Can you summarize my learnings? Towards perspective-based educational dialogue summarization. In: Findings of the Association for Computational Linguistics: EMNLP 2023, pp. 3158\u20133173 (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.208"},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Jain, R., Saha, T., Saha, S.: T-vaks: a tutoring-based multimodal dialog system via knowledge selection. In: ECAI 2023, pp. 1132\u20131139. IOS Press (2023)","DOI":"10.3233\/FAIA230388"},{"key":"21_CR19","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"21_CR20","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"21_CR21","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"21_CR22","doi-asserted-by":"publisher","first-page":"2003","DOI":"10.1109\/TIP.2021.3049334","volume":"30","author":"X Liu","year":"2021","unstructured":"Liu, X., Min, W., Mei, S., Wang, L., Jiang, S.: Plant disease recognition: a large-scale benchmark dataset and a visual region and loss reweighting approach. IEEE Trans. Image Process. 30, 2003\u20132015 (2021)","journal-title":"IEEE Trans. Image Process."},{"key":"21_CR23","unstructured":"Mangrulkar, S., Gugger, S., Debut, L., Belkada, Y., Paul, S.: PEFT: state-of-the-art parameter-efficient fine-tuning methods (2022). https:\/\/github.com\/huggingface\/peft"},{"key":"21_CR24","unstructured":"OpenAI: GPT-4 technical report. arXiv abs\/2303.08774 (2023). https:\/\/api.semanticscholar.org\/CorpusID:257532815"},{"key":"21_CR25","first-page":"27730","volume":"35","author":"L Ouyang","year":"2022","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. Adv. Neural. Inf. Process. Syst. 35, 27730\u201327744 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"21_CR27","unstructured":"Paszke, A., et al.: Pytorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"21_CR28","unstructured":"Peng, B., et al.: Godel: large-scale pre-training for goal-directed dialog. arXiv preprint arXiv:2206.11309 (2022)"},{"key":"21_CR29","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)"},{"issue":"8","key":"21_CR30","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI Blog 1(8), 9 (2019)","journal-title":"OpenAI Blog"},{"key":"21_CR31","unstructured":"Rae, J.W., et al.: Scaling language models: methods, analysis & insights from training gopher. arXiv preprint arXiv:2112.11446 (2021)"},{"issue":"1","key":"21_CR32","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR33","doi-asserted-by":"crossref","unstructured":"Saha, T., Chopra, S., Saha, S., Bhattacharyya, P., Kumar, P.: A large-scale dataset for motivational dialogue system: an application of natural language generation to mental health. In: 2021 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138. IEEE (2021)","DOI":"10.1109\/IJCNN52387.2021.9533924"},{"key":"21_CR34","doi-asserted-by":"crossref","unstructured":"Saha, T., Gakhreja, V., Das, A.S., Chakraborty, S., Saha, S.: Towards motivational and empathetic response generation in online mental health support. In: Proceedings of the 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 2650\u20132656 (2022)","DOI":"10.1145\/3477495.3531912"},{"key":"21_CR35","doi-asserted-by":"crossref","unstructured":"Saha, T., Reddy, S., Das, A., Saha, S., Bhattacharyya, P.: A shoulder to cry on: towards a motivational virtual assistant for assuaging mental agony. In: Proceedings of the 2022 Conference of the North American chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 2436\u20132449 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.174"},{"key":"21_CR36","doi-asserted-by":"crossref","unstructured":"Saha, T., Reddy, S.M., Saha, S., Bhattacharyya, P.: Mental health disorder identification from motivational conversations. IEEE Trans. Comput. Soc. Syst. (2022)","DOI":"10.1109\/TCSS.2022.3143763"},{"key":"21_CR37","unstructured":"Schulman, J., et al.: ChatGPT: optimizing language models for dialogue. OpenAI blog (2022)"},{"key":"21_CR38","doi-asserted-by":"crossref","unstructured":"Singh, D., Jain, N., Jain, P., Kayal, P., Kumawat, S., Batra, N.: Plantdoc: a dataset for visual plant disease detection. In: Proceedings of the 7th ACM IKDD CoDS and 25th COMAD, pp. 249\u2013253 (2020)","DOI":"10.1145\/3371158.3371196"},{"key":"21_CR39","unstructured":"Smith, S., et al.: Using deepspeed and megatron to train megatron-turing NLG 530B, a large-scale generative language model. arXiv preprint arXiv:2201.11990 (2022)"},{"key":"21_CR40","doi-asserted-by":"publisher","unstructured":"Tiwari, A., et al.: Symptoms are known by their companies: towards association guided disease diagnosis assistant. BMC Bioinform. 23(1), 556 (2022). https:\/\/doi.org\/10.1186\/S12859-022-05032-Y","DOI":"10.1186\/S12859-022-05032-Y"},{"key":"21_CR41","unstructured":"Touvron, H., et al.: Llama: open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)"},{"key":"21_CR42","unstructured":"Touvron, H., et al.: Llama 2: open foundation and fine-tuned chat models. arXiv abs\/2307.09288 (2023). https:\/\/api.semanticscholar.org\/CorpusID:259950998"},{"key":"21_CR43","unstructured":"Wolf, T., et al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345. Association for Computational Linguistics, Online (2020). https:\/\/www.aclweb.org\/anthology\/2020.emnlp-demos.6"},{"key":"21_CR44","unstructured":"Zhang, S., et al.: OPT: open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)"},{"key":"21_CR45","unstructured":"Zhang, T., Kishore, V., Wu, F., Weinberger, K.Q., Artzi, Y.: Bertscore: evaluating text generation with bert. arXiv preprint arXiv:1904.09675 (2019)"},{"key":"21_CR46","doi-asserted-by":"crossref","unstructured":"Zhang, Y., et al.: Dialogpt: large-scale generative pre-training for conversational response generation. arXiv preprint arXiv:1911.00536 (2019)","DOI":"10.18653\/v1\/2020.acl-demos.30"},{"key":"21_CR47","unstructured":"Zhu, D., Chen, J., Shen, X., Li, X., Elhoseiny, M.: Minigpt-4: enhancing vision-language understanding with advanced large language models. arXiv preprint arXiv:2304.10592 (2023)"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56060-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,15]],"date-time":"2024-03-15T15:05:37Z","timestamp":1710515137000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56060-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031560590","9783031560606"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56060-6_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"16 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECIR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Information Retrieval","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 March 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 March 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecir2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.ecir2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"578","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"110","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"69","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"19% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31 (Tracks: Workshop, Tutorial, Industry, Doctoral Consortium)","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}