Related papers: Does Incomplete Syntax Influence Korean Language M…
Standard methods in deep learning for natural language processing fail to capture the compositional structure of human language that allows for systematic generalization outside of the training distribution. However, human learners readily…
In-context learning (ICL) greatly improves the performance of large language models (LLMs) on various down-stream tasks, where the improvement highly depends on the quality of demonstrations. In this work, we introduce syntactic knowledge…
We describe a unified and coherent syntactic framework for supporting a semantically-informed syntactic approach to statistical machine translation. Semantically enriched syntactic tags assigned to the target-language training texts…
The Open Ko-LLM Leaderboard has been instrumental in benchmarking Korean Large Language Models (LLMs), yet it has certain limitations. Notably, the disconnect between quantitative improvements on the overly academic leaderboard benchmarks…
Recent advances in large audio language models (LALMs) have enabled multilingual speech understanding. However, benchmarks for evaluating LALMs remain scarce for non-English languages, with Korean being one such underexplored case. In this…
Word order, an essential property of natural languages, is injected in Transformer-based neural language models using position encoding. However, recent experiments have shown that explicit position encoding is not always useful, since some…
Large language models (LLMs) excel at semantic understanding, yet their ability to reconstruct internal structure from scrambled inputs remains underexplored. Sentence-level restoration is ill-posed for automated evaluation because multiple…
Word ordering is a constrained language generation task taking unordered words as input. Existing work uses linear models and neural networks for the task, yet pre-trained language models have not been studied in word ordering, let alone…
With the increasing utilization of multilingual text information, Cross-Lingual Information Retrieval (CLIR) has become a crucial research area. However, the impact of training data composition on both CLIR and Mono-Lingual Information…
This study systematically evaluated the mathematical reasoning capabilities of Large Language Models (LLMs) using the 2026 Korean College Scholastic Ability Test (CSAT) Mathematics section, ensuring a completely contamination-free…
Prosodic modeling is a core problem in speech synthesis. The key challenge is producing desirable prosody from textual input containing only phonetic information. In this preliminary study, we introduce the concept of "style tokens" in…
The syntactic structures of sentences can be readily read-out from the activations of large language models (LLMs). However, the ``structural probes'' that have been developed to reveal this phenomenon are typically evaluated on an…
Critique has surfaced concerning the existing linguistic annotation framework for Korean Universal Dependencies (UDs), particularly in relation to syntactic relationships. In this paper, our primary objective is to refine the definition of…
It is commonly believed that knowledge of syntactic structure should improve language modeling. However, effectively and computationally efficiently incorporating syntactic structure into neural language models has been a challenging topic.…
We introduce GECKO, a bilingual large language model (LLM) optimized for Korean and English, along with programming languages. GECKO is pretrained on the balanced, high-quality corpus of Korean and English employing LLaMA architecture. In…
A new scheme to represent phonological changes during continuous speech recognition is suggested. A phonological tag coupled with its morphological tag is designed to represent the conditions of Korean phonological changes. A pairwise…
Short text classification (STC) remains a challenging task due to the scarcity of contextual information and labeled data. However, existing approaches have pre-dominantly focused on English because most benchmark datasets for the STC are…
We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as a form of self-learning where the semantic parser being…
Particles fullfill several distinct central roles in the Japanese language. They can mark arguments as well as adjuncts, can be functional or have semantic funtions. There is, however, no straightforward matching from particles to…
In this study, we evaluated the performance of the state-of-the-art sequence tagging grammar error detection and correction model (SeqTagger) using Japanese university students' writing samples. With an automatic annotation toolkit, ERRANT,…