paper-with-me

Papers

A Sub-Character Architecture for Korean Language Processing

2017-07-20 · EMNLP 2017 9 · Karl Stratos

We introduce a novel sub-character architecture that exploits a unique compositional structure of the Korean language. Our method decomposes each character into a small set of primitive phonetic units called jamo letters from which character- and word-level representations are induced. The jamo letters divulge syntactic and semantic information that is difficult to access with conventional character-level units. They greatly alleviate the data sparsity problem, reducing the observation space to 1.6% of the original while increasing accuracy in our experiments. We apply our architecture to dependency parsing and achieve dramatic improvement over strong lexical baselines.

📄 PDF Abstract BibTeX arXiv:1707.06341

Code (1)

karlstratos/koreannet 공식 구현

Tasks

Dependency Parsing

Similar Papers 제목 키워드 기반

KoSpeech: Open-Source Toolkit for End-to-End Korean Speech Recognition

2020-09-07 · Soohwan Kim, Seyoung Bae, Cheolhwang Won

We present KoSpeech, an open-source software, which is modular and extensible end-to-end Korean automatic speech recognition (ASR) toolkit based on the deep learning library PyTorch. Several automatic speech recognition …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)speech-recognitionSpeech Recognition

HERITAGE: An End-to-End Web Platform for Processing Korean Historical Documents in Hanja

2025-01-21 · Seyoung Song, Haneul Yoo, Jiho Jin, Kyunghyun Cho 외

While Korean historical documents are invaluable cultural heritage, understanding those documents requires in-depth Hanja expertise. Hanja is an ancient language used in Korea before the 20th century, whose characters we…

document understandingMachine Translationnamed-entity-recognitionNamed Entity Recognition+1

KoBigBird-large: Transformation of Transformer for Korean Language Understanding

2023-09-19 · Kisu Yang, Yoonna Jang, Taewoo Lee, Jinwoo Seong 외

This work presents KoBigBird-large, a large size of Korean BigBird that achieves state-of-the-art performance and allows long sequence processing for Korean language understanding. Without further pretraining, we only tr…

Document ClassificationQuestion Answering

Word segmentation granularity in Korean

2023-09-07 · Jungyeul Park, Mija Kim

This paper describes word {segmentation} granularity in Korean language processing. From a word separated by blank space, which is termed an eojeol, to a sequence of morphemes in Korean, there are multiple possible level…

Segmentation

Optimizing Korean-Centric LLMs via Token Pruning

2026-04-17 · Hoyeol Kim, Hyeonwoo Kim arxiv

This paper presents a systematic benchmark of state-of-the-art multilingual large language models (LLMs) adapted via token pruning - a compression technique that eliminates tokens and embedding parameters corresponding t…

Instruction FollowingMachine Translation