BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Cross domain similarities and intra-person changes - Maria Liakata
  (University of Warwick)
DTSTART:20210430T110000Z
DTEND:20210430T120000Z
UID:TALK159940@talks.cam.ac.uk
CONTACT:Huiyuan Xie
DESCRIPTION:Join Zoom Meeting\nhttps://cl-cam-ac-uk.zoom.us/j/97474773044?
 pwd=ZzZsQTZPVFdRWnFUNElxS3RlQzRXdz09\n\nMeeting ID: 974 7477 3044\nPasscod
 e: 322272\n\nI will talk about two conceptually interconnected lines of wo
 rk in NLP within my group\; on the one hand identifying semantic similarit
 ies between instances (sentences or longer texts but also entities) across
  domains\, and on the other hand detecting changes within the same person 
 or domain over time. \nEven though semantic similarity is a fundamental ta
 sk within NLP it can be very challenging when comparisons are made across 
 domains as the vocabulary and context can be very different from one domai
 n setting to another. I will talk about recent work of ours where we addre
 ss semantic similarity between two texts in a variety of datasets\, includ
 ing community question answering\, by injecting domain-specific topic mode
 l information to pre-trained language models [1]. I will also be discussin
 g how in the case of cross domain entity similarity (and co-reference more
  specifically) current models struggle\, some of the reasons behind this a
 nd a new resource to help with addressing this problem [2]. The second par
 t of my talk can be seen as the flip side of semantic similarity\, where t
 he goal is to look for differences in the representation of the same indiv
 idual (word or person) that signal a change. I will be discussing work of 
 ours on sequential modelling of the evolution of a word for semantic chang
 e detection [3] and how we are developing methods to detect changes in ind
 ividuals as part of my UKRI Turing AI fellowship.\n \n[1] Peinelt\, N.\, N
 guyen\, D.\, & Liakata\, M. (2020\, July). tBERT: Topic models and BERT jo
 ining forces for semantic similarity detection. In Proceedings of the 58th
  Annual Meeting of the Association for Computational Linguistics (pp. 7047
 -7055). https://www.aclweb.org/anthology/2020.acl-main.630/\n[2] Ravenscro
 ft\, J.\, Clare\, A.\, Cattan\, A.\, Dagan\, I.\, & Liakata\, M. (2021\, A
 pril). CDˆ2CR: Co-reference resolution across documents and domains. In P
 roceedings of the 16th Conference of the European Chapter of the Associati
 on for Computational Linguistics: Main Volume (pp. 270-280). https://www.a
 clweb.org/anthology/2021.eacl-main.21/\n[3] Tsakalidis\, A.\, & Liakata\, 
 M. (2020\, November). Sequential Modelling of the Evolution of Word Repres
 entations for Semantic Change Detection. In Proceedings of the 2020 Confer
 ence on Empirical Methods in Natural Language Processing (EMNLP) (pp. 8485
 -8497). https://www.aclweb.org/anthology/2020.emnlp-main.682.pdf
LOCATION:Virtual (Zoom)
END:VEVENT
END:VCALENDAR