Chaehun Park

Also published as: ChaeHun Park


2021

pdf bib
Park. Optimizing Domain Specificity of Transformer-based Language Models for Extractive Summarization of Financial News Articles in Korean
Huije Lee | Wonsuk Yang | Chaehun Park | Hoyun Song | Eugene Jang | Jong C. Park
Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation

pdf bib
Park. Optimizing Domain Specificity of Transformer-based Language Models for Extractive Summarization of Financial News Articles in Korean
Huije Lee | Wonsuk Yang | Chaehun Park | Hoyun Song | Eugene Jang | Jong C. Park
Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation

pdf bib
Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model
ChaeHun Park | Eugene Jang | Wonsuk Yang | Jong Park
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Evaluating the quality of responses generated by open-domain conversation systems is a challenging task. This is partly because there can be multiple appropriate responses to a given dialogue history. Reference-based metrics that rely on comparisons to a set of known correct responses often fail to account for this variety, and consequently correlate poorly with human judgment. To address this problem, researchers have investigated the possibility of assessing response quality without using a set of known correct responses. RUBER demonstrated that an automatic response evaluation model could be made using unsupervised learning for the next-utterance prediction (NUP) task. For the unsupervised learning of such model, we propose a method of manipulating a golden response to create a new negative response that is designed to be inappropriate within the context while maintaining high similarity with the original golden response. We find, from our experiments on English datasets, that using the negative samples generated by our method alongside random negative samples can increase the model’s correlation with human evaluations. The process of generating such negative samples is automated and does not rely on human annotation.

pdf bib
Unsupervised Document Expansion for Information Retrieval with Stochastic Text Generation
Soyeong Jeong | Jinheon Baek | ChaeHun Park | Jong Park
Proceedings of the Second Workshop on Scholarly Document Processing

One of the challenges in information retrieval (IR) is the vocabulary mismatch problem, which happens when the terms between queries and documents are lexically different but semantically similar. While recent work has proposed to expand the queries or documents by enriching their representations with additional relevant terms to address this challenge, they usually require a large volume of query-document pairs to train an expansion model. In this paper, we propose an Unsupervised Document Expansion with Generation (UDEG) framework with a pre-trained language model, which generates diverse supplementary sentences for the original document without using labels on query-document pairs for training. For generating sentences, we further stochastically perturb their embeddings to generate more diverse sentences for document expansion. We validate our framework on two standard IR benchmark datasets. The results show that our framework significantly outperforms relevant expansion baselines for IR.

2019

pdf bib
Generating Sentential Arguments from Diverse Perspectives on Controversial Topic
ChaeHun Park | Wonsuk Yang | Jong Park
Proceedings of the Second Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda

Considering diverse aspects of an argumentative issue is an essential step for mitigating a biased opinion and making reasonable decisions. A related generation model can produce flexible results that cover a wide range of topics, compared to the retrieval-based method that may show unstable performance for unseen data. In this paper, we study the problem of generating sentential arguments from multiple perspectives, and propose a neural method to address this problem. Our model, ArgDiver (Argument generation model from diverse perspectives), in a way a conversational system, successfully generates high-quality sentential arguments. At the same time, the automatically generated arguments by our model show a higher diversity than those generated by any other baseline models. We believe that our work provides evidence for the potential of a good generation model in providing diverse perspectives on a controversial topic.