From 1375c99dc210e075b5a92be273dc326c40be42f5 Mon Sep 17 00:00:00 2001 From: verenablaschke Date: Wed, 3 Apr 2024 18:12:39 +0200 Subject: [PATCH] Hyewon's talk --- _events/2024-04-08-hyewon-jang.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/_events/2024-04-08-hyewon-jang.md b/_events/2024-04-08-hyewon-jang.md index 2bca5a4..1717564 100644 --- a/_events/2024-04-08-hyewon-jang.md +++ b/_events/2024-04-08-hyewon-jang.md @@ -3,7 +3,7 @@ title: "Towards well-rounded sarcasm handling by language models" abstract: "We investigate the ways of reaching well-rounded handling of sarcasm by language models (LMs), exemplified by the ability to generalize well, to understand the reasoning behind the use of sarcasm, or to generate sarcasm at an appropriate time. As the first attempt, we tested the robustness of sarcasm detection models by examining their behavior when fine-tuned on four sarcasm datasets containing varying characteristics of sarcasm: label source (authors vs. third-party), domain (social media/online vs. offline conversations/dialogues), style (aggressive vs. humorous mocking). We found that most LMs failed to generalize well to the other datasets, implying that one type of dataset cannot represent all sorts of sarcasm with different styles and domains. Compared to the existing datasets, LMs fine-tuned on the new dataset we newly released showed the highest generalizability to other datasets. From analyzing these results, we show that sarcasm encompasses a broad spectrum of characteristics, intricately intertwined with factors requiring inference and pragmatics, and argue that future research of sarcasm should take these factors into account. We conclude by discussing future work in this direction." speaker: Hyewon Jang
PhD candidate, University of Konstanz (Germany) -bio: Hyewon Jang is a PhD candidate in computational psycholinguistics at the University of Konstanz supervised by Diego Frassinelli and Bettina Braun. Hyewon uses experimental and computational linguistics methods to investigate the pragmatic dimensions of language that make human language complex and fun, with sarcasm being the current topic of interest. +bio: Hyewon Jang is a PhD candidate in computational psycholinguistics at the University of Konstanz supervised by Diego Frassinelli and Bettina Braun. Hyewon uses experimental and computational linguistics methods to investigate the pragmatic dimensions of language that make human language complex and fun, with sarcasm being the current topic of interest. website: https://hyewon-jang-kn.github.io/ time: April 8, 2024; 9:00–10:00 location: Akademiestr. 7, room 218A (meeting room)