{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:28:24Z","timestamp":1763191704943,"version":"3.45.0"},"reference-count":42,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/ijcnn64981.2025.11227844","type":"proceedings-article","created":{"date-parts":[[2025,11,14]],"date-time":"2025-11-14T18:46:15Z","timestamp":1763145975000},"page":"1-8","source":"Crossref","is-referenced-by-count":0,"title":["Optimized Domain-Specific Text Processing with Keyword Knowledge Distillation (KKD)"],"prefix":"10.1109","author":[{"given":"Momojit","family":"Biswas","sequence":"first","affiliation":[{"name":"TCS Research,Kolkata,India"}]},{"given":"Anmol","family":"Singhal","sequence":"additional","affiliation":[{"name":"TCS Research,New Delhi,India"}]},{"given":"Preethu Rose","family":"Anish","sequence":"additional","affiliation":[{"name":"TCS Research,Pune,India"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.261"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3462757.3466088"},{"journal-title":"Finbert: Financial sentiment analysis with pre-trained language models","year":"2019","author":"Araci","key":"ref6"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","article-title":"Biobert: a pre-trained biomedical language representation model for biomedical text mining","volume":"36","author":"Jinhyuk","year":"2020","journal-title":"Bioinformatics"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-021-00455-y"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.3726\/978-3-0351-0317-5"},{"volume-title":"The language of the law","year":"2004","author":"Mellinkoff","key":"ref10"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx228"},{"key":"ref12","first-page":"39","article-title":"Distributional semantics resources for biomedical text processing","volume-title":"Proceedings of LBM","author":"Moen"},{"journal-title":"Finbert: A pretrained language model for financial communications","year":"2020","author":"Yang","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1580"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1355"},{"journal-title":"Compressing deep convolutional networks using vector quantization","year":"2014","author":"Gong","key":"ref17"},{"key":"ref18","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han","year":"2015","journal-title":"Advances in neural information processing systems"},{"journal-title":"Distilling the knowledge in a neural network","year":"2015","author":"Hinton","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/msp.2017.2765695"},{"article-title":"Keybert: Minimal keyword extraction with bert","year":"2020","author":"Grootendorst","key":"ref21"},{"journal-title":"Distilling task-specific knowledge from bert into simple neural networks","year":"2019","author":"Tang","key":"ref22"},{"journal-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","year":"2019","author":"Sanh","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"journal-title":"Mixkd: Towards efficient distillation of large-scale language models","year":"2020","author":"Liang","key":"ref26"},{"key":"ref27","first-page":"5776","article-title":"Minilm: Deep self-attention distillation for task-agnostic compression of pre-trained transformers","volume":"33","author":"Wang","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.188"},{"journal-title":"Do not blindly imitate the teacher: Using perturbed loss for knowledge distillation","year":"2023","author":"Zhang","key":"ref29"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.471"},{"article-title":"Minillm: Knowledge distillation of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Gu","key":"ref31"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.ecnlp-1.18"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.116"},{"journal-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","year":"2018","author":"Devlin","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.528"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3936759"},{"key":"ref37","first-page":"29 217","article-title":"Pile of law: Learning responsible data filtering from the law and a 256gb open-source legal dataset","volume":"35","author":"Henderson","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.66"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.nllp-1.22"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1002\/asi.23062"},{"volume-title":"WWW\u201918: Companion Proceedings of the The Web Conference 2018","author":"Champin","key":"ref41"},{"journal-title":"Finer: Financial named entity recognition dataset and weak-supervision model","year":"2023","author":"Shah","key":"ref42"}],"event":{"name":"2025 International Joint Conference on Neural Networks (IJCNN)","start":{"date-parts":[[2025,6,30]]},"location":"Rome, Italy","end":{"date-parts":[[2025,7,5]]}},"container-title":["2025 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11227166\/11227148\/11227844.pdf?arnumber=11227844","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T07:25:42Z","timestamp":1763191542000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11227844\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":42,"URL":"https:\/\/doi.org\/10.1109\/ijcnn64981.2025.11227844","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}