{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T20:30:34Z","timestamp":1773520234888,"version":"3.50.1"},"reference-count":18,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGIR Forum"],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"<jats:p>Artificial intelligence (AI), specifically, Natural Language Processing (NLP) is being hailed as a new breeding ground for immense innovation potential. Researchers believe that NLP-based technologies could help to solve societal issues such as equality and inclusion, education, health, and hunger, climate action etc., and many more. Tackling these questions requires a concerted, collaborative effort across all sectors of society. The 3rd Symposium on NLP for Social Good (NSG) was a novel effort that aimed to enable NLP researchers and scholars from inter-disciplinary field who want to think about the societal implications of their work for solving humanitarian and environmental challenges. The objective of the symposium was to support fundamental research and engineering efforts and empower the social sector with tools and resources, while collaborating with partners from all sectors to maximise effect in solving problems within public health, nature &amp; society, accessibility, crisis response etc. In its 3rd year, we invited speakers from academia and industry to provide an overview of some areas from NLP applications such as healthcare, climate and legal domains in order to provide a platform to stimulate discussion regarding the current state of NLP in these varied fields.<\/jats:p>\n                  <jats:p>\n                    <jats:bold>Date:<\/jats:bold>\n                    25\u201326 June, 2025.\n                  <\/jats:p>\n                  <jats:p>\n                    <jats:bold>Website:<\/jats:bold>\n                    https:\/\/nlp4social.github.io\/NSG\/.\n                  <\/jats:p>","DOI":"10.1145\/3799914.3799925","type":"journal-article","created":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T18:19:03Z","timestamp":1772648343000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Report on the 3rd Symposium on NLP for Social Good (NSG 2025)"],"prefix":"10.1145","volume":"59","author":[{"given":"Procheta","family":"Sen","sequence":"first","affiliation":[{"name":"University of Liverpool, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tulika","family":"Saha","sequence":"additional","affiliation":[{"name":"International Institute of Information Technology Bangalore, India"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danushka","family":"Bollegala","sequence":"additional","affiliation":[{"name":"University of Liverpool, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,4]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-032-04627-7_28"},{"key":"e_1_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN55064.2022.9892890"},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.208"},{"key":"e_1_2_1_4_1","volume-title":"T-vaks: A tutoring-based multimodal dialog system via knowledge selection","author":"Jain Raghav","year":"2023","unstructured":"Raghav Jain, Tulika Saha, and Sriparna Saha. T-vaks: A tutoring-based multimodal dialog system via knowledge selection. 2023b."},{"key":"e_1_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i11.21453"},{"key":"e_1_2_1_6_1","volume-title":"Debiasing isn't enough!-on the effectiveness of debiasing mlms and their social biases in downstream tasks. arXiv preprint arXiv:2210.02938","author":"Kaneko Masahiro","year":"2022","unstructured":"Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. Debiasing isn't enough!-on the effectiveness of debiasing mlms and their social biases in downstream tasks. arXiv preprint arXiv:2210.02938, 2022a."},{"key":"e_1_2_1_7_1","volume-title":"Gender bias in meta-embeddings. arXiv preprint arXiv:2205.09867","author":"Kaneko Masahiro","year":"2022","unstructured":"Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. Gender bias in meta-embeddings. arXiv preprint arXiv:2205.09867, 2022b."},{"key":"e_1_2_1_8_1","volume-title":"The impact of debiasing on the performance of language models in downstream tasks is underestimated. arXiv preprint arXiv:2309.09092","author":"Kaneko Masahiro","year":"2023","unstructured":"Masahiro Kaneko, Danushka Bollegala, and Naoaki Okazaki. The impact of debiasing on the performance of language models in downstream tasks is underestimated. arXiv preprint arXiv:2309.09092, 2023."},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3704740"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531912"},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.174"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615311"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-28241-6_36"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5654"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12859-022-05032-y"},{"key":"e_1_2_1_16_1","volume-title":"Automated argument generation from legal facts","author":"Tuvey Oscar","year":"2023","unstructured":"Oscar Tuvey and Procheta Sen. Automated argument generation from legal facts, 2023."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680082"},{"key":"e_1_2_1_18_1","volume-title":"Sense embeddings are also biased-evaluating social biases in static and contextualised sense embeddings. arXiv preprint arXiv:2203.07523","author":"Zhou Yi","year":"2022","unstructured":"Yi Zhou, Masahiro Kaneko, and Danushka Bollegala. Sense embeddings are also biased-evaluating social biases in static and contextualised sense embeddings. arXiv preprint arXiv:2203.07523, 2022."}],"container-title":["ACM SIGIR Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3799914.3799925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T17:19:52Z","timestamp":1773508792000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3799914.3799925"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":18,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,1]]}},"alternative-id":["10.1145\/3799914.3799925"],"URL":"https:\/\/doi.org\/10.1145\/3799914.3799925","relation":{},"ISSN":["0163-5840"],"issn-type":[{"value":"0163-5840","type":"print"}],"subject":[],"published":{"date-parts":[[2025,12,1]]},"assertion":[{"value":"2026-03-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}