1 code implementation • Findings (EMNLP) 2021 • Hwiyeol Jo, Jaeseo Lim, Byoung-Tak Zhang
We present a new form of ensemble method–Devil’s Advocate, which uses a deliberately dissenting model to force other submodels within the ensemble to better collaborate.
no code implementations • Findings (EMNLP) 2021 • Hwiyeol Jo, Dongyeop Kang, Andrew Head, Marti A. Hearst
Natural language models often fall short when understanding and generating mathematical notation.
no code implementations • 5 Apr 2024 • Hwiyeol Jo, Taiwoo Park, Nayoung Choi, Changbong Kim, Ohjoon Kwon, Donghyeon Jeon, Hyunwoo Lee, Eui-Hyeon Lee, Kyoungho Shin, Sun Suk Lim, Kyungmi Kim, Jihye Lee, Sun Kim
Although there has been a growing interest among industries to integrate generative LLMs into their services, limited experiences and scarcity of resources acts as a barrier in launching and servicing large-scale LLM-based conversational services.
no code implementations • 25 May 2022 • Kang Min Yoo, Junyeob Kim, Hyuhng Joon Kim, Hyunsoo Cho, Hwiyeol Jo, Sang-Woo Lee, Sang-goo Lee, Taeuk Kim
Despite recent explosion of interests in in-context learning, the underlying mechanism and the precise impact of the quality of demonstrations remain elusive.
no code implementations • 1 Jan 2021 • Hwiyeol Jo, Byoung-Tak Zhang
Through the re-training process, some of noises can be compensated and other noises can be utilized to learn better representations.
no code implementations • 7 Nov 2020 • Jaeseo Lim, Hwiyeol Jo, Byoung-Tak Zhang, Jooyong Park
In the end, we showed not only that we can make build better machine training framework through the human experiment result, but also empirically confirm the result of human experiment through imitated machine experiments; human-like active learning have crucial effect on learning performance.
no code implementations • 8 Nov 2019 • Hwiyeol Jo, Byoung-Tak Zhang
Next, we gradually add random noises to the word representations and repeat the training process from scratch, but initialize with the noised word representations.
1 code implementation • IJCNLP 2019 • Hwiyeol Jo, Ceyda Cinarel
We propose a novel and simple method for semi-supervised text classification.
General Classification Semi-Supervised Text Classification +1
no code implementations • 22 Aug 2018 • Hwiyeol Jo
Retrofitting techniques, which inject external resources into word representations, have compensated the weakness of distributed representations in semantic and relational knowledge between words.
no code implementations • 3 Jun 2018 • Hwiyeol Jo, Jeong Ryu
Starting with the idea that sentiment analysis models should be able to predict not only positive or negative but also other psychological states of a person, we implement a sentiment analysis model to investigate the relationship between the model and emotional state.
2 code implementations • WS 2018 • Hwiyeol Jo, Stanley Jungkyu Choi
The method consists of 3 steps as follows: (i) Expanding 1 or more dimension(s) on all the word vectors, filling with their representative value.
no code implementations • 11 Apr 2017 • Hwiyeol Jo, Soo-Min Kim, Jeong Ryu
As the first step to model emotional state of a person, we build sentiment analysis models with existing deep neural network algorithms and compare the models with psychological measurements to enlighten the relationship.
no code implementations • 13 Jul 2016 • Hwiyeol Jo, Yohan Moon, Jong In Kim, Jeong Ryu
The results of CES-D and PANAS show the relationship between emotion and memory retrieval as follows: depressed people have shown a tendency of representing a story more negatively, and they seemed less expressive.