Kyungjae Lee


2022

pdf bib
Plug-and-Play Adaptation for Continuously-updated QA
Kyungjae Lee | Wookje Han | Seung-won Hwang | Hwaran Lee | Joonsuk Park | Sang-Woo Lee
Findings of the Association for Computational Linguistics: ACL 2022

Language models (LMs) have shown great potential as implicit knowledge bases (KBs). And for their practical use, knowledge in LMs need to be updated periodically. However, existing tasks to assess LMs’ efficacy as KBs do not adequately consider multiple large-scale updates. To this end, we first propose a novel task—Continuously-updated QA (CuQA)—in which multiple large-scale updates are made to LMs, and the performance is measured with respect to the success in adding and updating knowledge while retaining existing knowledge. We then present LMs with plug-in modules that effectively handle the updates. Experiments conducted on zsRE QA and NQ datasets show that our method outperforms existing approaches. We find that our method is 4x more effective in terms of updates/forgets ratio, compared to a fine-tuning baseline.

2021

pdf bib
Query Generation for Multimodal Documents
Kyungho Kim | Kyungjae Lee | Seung-won Hwang | Young-In Song | Seungwook Lee
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume

This paper studies the problem of generatinglikely queries for multimodal documents withimages. Our application scenario is enablingefficient “first-stage retrieval” of relevant doc-uments, by attaching generated queries to doc-uments before indexing. We can then indexthis expanded text to efficiently narrow downto candidate matches using inverted index, sothat expensive reranking can follow. Our eval-uation results show that our proposed multi-modal representation meaningfully improvesrelevance ranking.More importantly, ourframework can achieve the state of the art inthe first stage retrieval scenarios

pdf bib
Robustifying Multi-hop QA through Pseudo-Evidentiality Training
Kyungjae Lee | Seung-won Hwang | Sang-eun Han | Dohyeon Lee
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

This paper studies the bias problem of multi-hop question answering models, of answering correctly without correct reasoning. One way to robustify these models is by supervising to not only answer right, but also with right reasoning chains. An existing direction is to annotate reasoning chains to train models, requiring expensive additional annotations. In contrast, we propose a new approach to learn evidentiality, deciding whether the answer prediction is supported by correct evidences, without such annotations. Instead, we compare counterfactual changes in answer confidence with and without evidence sentences, to generate “pseudo-evidentiality” annotations. We validate our proposed model on an original set and challenge set in HotpotQA, showing that our method is accurate and robust in multi-hop reasoning.

2019

pdf bib
Learning with Limited Data for Multilingual Reading Comprehension
Kyungjae Lee | Sunghyun Park | Hojae Han | Jinyoung Yeo | Seung-won Hwang | Juho Lee
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

This paper studies the problem of supporting question answering in a new language with limited training resources. As an extreme scenario, when no such resource exists, one can (1) transfer labels from another language, and (2) generate labels from unlabeled data, using translator and automatic labeling function respectively. However, these approaches inevitably introduce noises to the training data, due to translation or generation errors, which require a judicious use of data with varying confidence. To address this challenge, we propose a weakly-supervised framework that quantifies such noises from automatically generated labels, to deemphasize or fix noisy data in training. On reading comprehension task, we demonstrate the effectiveness of our model on low-resource languages with varying similarity to English, namely, Korean and French.

pdf bib
Categorical Metadata Representation for Customized Text Classification
Jihyeok Kim | Reinald Kim Amplayo | Kyungjae Lee | Sua Sung | Minji Seo | Seung-won Hwang
Transactions of the Association for Computational Linguistics, Volume 7

The performance of text classification has improved tremendously using intelligently engineered neural-based models, especially those injecting categorical metadata as additional information, e.g., using user/product information for sentiment classification. This information has been used to modify parts of the model (e.g., word embeddings, attention mechanisms) such that results can be customized according to the metadata. We observe that current representation methods for categorical metadata, which are devised for human consumption, are not as effective as claimed in popular classification methods, outperformed even by simple concatenation of categorical features in the final layer of the sentence encoder. We conjecture that categorical features are harder to represent for machine use, as available context only indirectly describes the category, and even such context is often scarce (for tail category). To this end, we propose using basis vectors to effectively incorporate categorical metadata on various parts of a neural-based model. This additionally decreases the number of parameters dramatically, especially when the number of categorical features is large. Extensive experiments on various data sets with different properties are performed and show that through our method, we can represent categorical metadata more effectively to customize parts of the model, including unexplored ones, and increase the performance of the model greatly.

2018

pdf bib
Semi-supervised Training Data Generation for Multilingual Question Answering
Kyungjae Lee | Kyoungho Yoon | Sunghyun Park | Seung-won Hwang
Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)