{"id":210,"date":"2019-12-19T15:49:15","date_gmt":"2019-12-19T14:49:15","guid":{"rendered":"https:\/\/multi3generation.eu\/?page_id=210"},"modified":"2019-12-19T15:49:15","modified_gmt":"2019-12-19T14:49:15","slug":"wg3","status":"publish","type":"page","link":"https:\/\/multi3generation.inesc-id.pt\/?page_id=210","title":{"rendered":"WG 3 &#8211; Dialogue, interaction and conversational language generation applications"},"content":{"rendered":"\n<div class=\"wp-block-group\"><div class=\"wp-block-group__inner-container is-layout-flow wp-block-group-is-layout-flow\">\n<p>WG3 focuses on on Human Computer Interaction (HCI) tasks in multilingual and multimodal scenarios applying LG models to distinct use cases, such as conversational agents, with 3 main directions:<\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>New answer generation techniques where the (human) agent will receive suggestions<\/li><li>New techniques for conversational quality estimation and sentiment analysis<\/li><li>Creation of multilingual datasets for low resourced languages<\/li><\/ul>\n\n\n\n<p><strong>Main challenges for WG3:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Scarcity of multimodal and multilingual datasets for chat in general<\/li><li>Scarcity of multilingual datasets for low resourced languages<\/li><li>Benchmarking the models applied<\/li><li>New metrics for multilingual conversational dialogues<\/li><\/ul>\n\n\n\n<h4 class=\"wp-block-heading\"><strong>This working group will be working on:<\/strong><\/h4>\n\n\n\n<ul class=\"wp-block-list\"><li>a survey on affective agents and answer generation adaptations to chat data<\/li><li>a survey on metrics for dialogue systems<\/li><li>report on available multilingual datasets for conversational data<\/li><li>creation of multilingual datasets for low resourced languages<\/li><li>contribution to the cross-task roadmap of the project<\/li><li>contribution to responsible AI initiatives, since we are working with modalities with severe ethic aspects&nbsp;<\/li><\/ul>\n\n\n\n<p>If you would like to join this working group, please contact the WG Leader and co leader:&nbsp; Helena Moniz (helena.moniz@campus.ul.pt) and Inguna Skadina (<a href=\"mailto:inguna.skadina@lu.lv\">inguna.skadina@lu.lv<\/a>)<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Low resourced languages datasets<\/strong><\/h2>\n\n\n\n<p>Available datasets:<\/p>\n\n\n\n<ol class=\"wp-block-list\" type=\"1\"><li>Latvian corpus: <a href=\"http:\/\/hdl.handle.net\/20.500.12574\/47\">http:\/\/hdl.handle.net\/20.500.12574\/47<\/a><\/li><\/ol>\n\n\n\n<p>This multi-targeted dataset contains several datasets that allow to train goal-oriented dialogue systems for student service domain in Latvian. The dataset contains a manually annotated dataset of domain-specific dialog intents, a manually created and annotated dataset of generalised and formalised dialog scenarios based on corpus evidence, dataset for FAQ module training.<\/p>\n\n\n\n<h2 class=\"wp-block-heading\"><strong>Publications and preprints<\/strong><\/h2>\n\n\n\n<ul class=\"wp-block-list\"><li>Ramos, R., Pereira, P., Moniz, H., Carvalho, J., and Martins, B. <strong>\u201cRetrieval Augmentation for Deep Neural Networks\u201d<\/strong>, <em>Proceedings of\u00a0 IJCNN 2021<\/em>. <a href=\"https:\/\/ieeexplore.ieee.org\/document\/9533978\">Link to paper<\/a><\/li><li><a href=\"http:\/\/ailab.lv\/publications\/d.+gosko\/\">D. Gosko<\/a>,\u00a0<a href=\"http:\/\/ailab.lv\/publications\/a.+znotins\/\">A. Znotins<\/a>,\u00a0<a href=\"http:\/\/ailab.lv\/publications\/i.+skadina\/\">I. Skadina<\/a>,\u00a0<a href=\"http:\/\/ailab.lv\/publications\/n.+gruzitis\/\">N. Gruzitis<\/a>,\u00a0<a href=\"http:\/\/ailab.lv\/publications\/g.+nespore-berzkalne\/\">G. Nespore-Berzkalne<\/a>, <strong>\u201c<a href=\"http:\/\/ailab.lv\/publications\/451\/\">Domain Expert Platform for Goal-Oriented Dialog Collection<\/a>\u201d<\/strong>, <em>Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL): System Demonstrations, 2021<\/em>. <a href=\"https:\/\/aclanthology.org\/2021.eacl-demos.35\/\">Link to paper<\/a><\/li><\/ul>\n<\/div><\/div>\n","protected":false},"excerpt":{"rendered":"<p>WG3 focuses on on Human Computer Interaction (HCI) tasks in multilingual and multimodal scenarios applying LG models to distinct use cases, such as conversational agents, &hellip;<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":175,"menu_order":3,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-210","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/pages\/210","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=210"}],"version-history":[{"count":0,"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/pages\/210\/revisions"}],"up":[{"embeddable":true,"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=\/wp\/v2\/pages\/175"}],"wp:attachment":[{"href":"https:\/\/multi3generation.inesc-id.pt\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=210"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}