Source author record

Jong-Hyeok Lee

Jong-Hyeok Lee appears in the imported research catalog. Authorship, coauthor and topic links are available while profile ownership is still unclaimed.

ResearcherUnclaimed source record

Computation and Language cmp-lg Machine Learning Artificial Intelligence Information Retrieval physics.soc-ph

Catalog footprint

What is connected

6works

6topics

4close collaborators

Actions

Connect this record

Open graph Browse works

Inspect adjacent papers, topics, institutions and collaborators without losing the researcher page.

Building this map preview

BZPEER is loading the nearby papers, people, topics and institutions for this page.

preprint2026arXiv

Merging Methods for Multilingual Knowledge Editing for Large Language Models: An Empirical Odyssey

Multilingual knowledge editing (MKE) remains challenging because language-specific edits interfere with one another, even when locate-then-edit methods work well in monolingual settings. This paper focuses on three issues: the effectiveness of vector merging methods for MKE, the extent to which Task Singular Vectors for Merging (TSVM) can reduce multilingual interference, and the influence of the weight scaling factor and rank compression ratio on performance. We evaluate six merging variants with two popular backbone large language models, two base knowledge editing methods, and 12 languages on the MzsRE benchmark under a large-scale batch-editing setting. Our results show that vector summation with shared covariance is the most reliable overall strategy, whereas simple summation without shared covariance performs poorly. TSVM improves performance in some settings, but its ability to mitigate multilingual interference is limited. We also find that performance is sensitive to both weight scale and rank ratio, with larger-than-default scaling and relatively low rank often yielding better results. These findings clarify the practical strengths and limits of current vector merging methods for MKE and provide guidance for future multilingual knowledge editing research.

preprint2022arXiv

mcBERT: Momentum Contrastive Learning with BERT for Zero-Shot Slot Filling

Zero-shot slot filling has received considerable attention to cope with the problem of limited available data for the target domain. One of the important factors in zero-shot learning is to make the model learn generalized and reliable representations. For this purpose, we present mcBERT, which stands for momentum contrastive learning with BERT, to develop a robust zero-shot slot filling model. mcBERT uses BERT to initialize the two encoders, the query encoder and key encoder, and is trained by applying momentum contrastive learning. Our experimental results on the SNIPS benchmark show that mcBERT substantially outperforms the previous models, recording a new state-of-the-art. Besides, we also show that each component composing mcBERT contributes to the performance improvement.

preprint2020arXiv

Identifying time dependence in network growth

Identifying power-law scaling in real networks - indicative of preferential attachment - has proved controversial. Critics argue that measuring the temporal evolution of a network directly is better than measuring the degree distribution when looking for preferential attachment. However, many of the established methods do not account for any potential time-dependence in the attachment kernels of growing networks, or methods assume that node degree is the key observable determining network evolution. In this paper, we argue that these assumptions may lead to misleading conclusions about the evolution of growing networks. We illustrate this by introducing a simple adaptation of the Barab{á}si-Albert model, the "k2 model", where new nodes attach to nodes in the existing network in proportion to the number of nodes one or two steps from the target node. The k2 model results in time dependent degree distributions and attachment kernels, despite initially appearing to grow as linear preferential attachment, and without the need to include explicit time dependence in key network parameters (such as the average out-degree). We show that similar effects are seen in several real world networks where constant network growth rules do not describe their evolution. This implies that measurements of specific degree distributions in real networks are also likely to change over time.

preprint2015arXiv

Improving Term Frequency Normalization for Multi-topical Documents, and Application to Language Modeling Approaches

Term frequency normalization is a serious issue since lengths of documents are various. Generally, documents become long due to two different reasons - verbosity and multi-topicality. First, verbosity means that the same topic is repeatedly mentioned by terms related to the topic, so that term frequency is more increased than the well-summarized one. Second, multi-topicality indicates that a document has a broad discussion of multi-topics, rather than single topic. Although these document characteristics should be differently handled, all previous methods of term frequency normalization have ignored these differences and have used a simplified length-driven approach which decreases the term frequency by only the length of a document, causing an unreasonable penalization. To attack this problem, we propose a novel TF normalization method which is a type of partially-axiomatic approach. We first formulate two formal constraints that the retrieval model should satisfy for documents having verbose and multi-topicality characteristic, respectively. Then, we modify language modeling approaches to better satisfy these two constraints, and derive novel smoothing methods. Experimental results show that the proposed method increases significantly the precision for keyword queries, and substantially improves MAP (Mean Average Precision) for verbose queries.

preprint1996arXiv

Integrating HMM-Based Speech Recognition With Direct Manipulation In A Multimodal Korean Natural Language Interface

This paper presents a HMM-based speech recognition engine and its integration into direct manipulation interfaces for Korean document editor. Speech recognition can reduce typical tedious and repetitive actions which are inevitable in standard GUIs (graphic user interfaces). Our system consists of general speech recognition engine called ABrain {Auditory Brain} and speech commandable document editor called SHE {Simple Hearing Editor}. ABrain is a phoneme-based speech recognition engine which shows up to 97% of discrete command recognition rate. SHE is a EuroBridge widget-based document editor that supports speech commands as well as direct manipulation interfaces.

preprint1995arXiv

Bi-directional memory-based dialog translation: The KEMDT approach

A bi-directional Korean/English dialog translation system is designed and implemented using the memory-based translation technique. The system KEMDT (Korean/English Memory-based Dialog Translation system) can perform Korean to English, and English to Korean translation using unified memory network and extended marker passing algorithm. We resolve the word order variation and frequent word omission problems in Korean by classifying the concept sequence element in four different types and extending the marker- passing-based-translation algorithm. Unlike the previous memory-based translation systems, the KEMDT system develops the bilingual memory network and the unified bi-directional marker passing translation algorithm. For efficient language specific processing, we separate the morphological processors from the memory-based translator. The KEMDT technology provides a hierarchical memory network and an efficient marker-based control for the recent example-based MT paradigm.