KoFREN: Comprehensive Korean Word Frequency Norms Derived from Large Scale Free Speech Corpora (2024.lrec-main)
Copied to clipboard
| Challenge: | Word frequency norms in Korean are based on large-scale spontaneous speech corpora, but are not available in minor languages. |
| Approach: | They employ a machine learning-powered POS tagger to create Korean word frequency norms from large-scale spontaneous speech corpora that include a balanced representation of gender and age. |
| Outcome: | The proposed Korean word frequency norms correlate with external studies’ lexical decision time (LDT) and AoA measures. |
Similar Papers
KoSBI: A Dataset for Mitigating Social Bias Risks Towards Safer Large Language Model Applications (2023.acl-industry)
Copied to clipboard
| Challenge: | Existing research and resources are not readily applicable in South Korea due to the differences in language and culture, both of which significantly affect the biases and targeted demographic groups. |
| Approach: | They propose a social bias dataset of 34k pairs of contexts and sentences in Korean covering 72 demographic groups in 15 categories. |
| Outcome: | The proposed dataset reduces social biases by 16.47%p on average for HyperClova (30B and 82B), and GPT-3. |
Making Sense of Korean Sentences: A Comprehensive Evaluation of LLMs through KoSEnd Dataset (2025.acl-srw)
Copied to clipboard
| Challenge: | Despite advances in LLMs, there are still concerns about their effectiveness with low-resource agglutinative languages compared to English. |
| Approach: | They evaluated 11 LLMs to assess their understanding of Korean sentence endings . they found that explicitly considering linguistic features improved performance . |
| Outcome: | The evaluated LLMs were able to understand Korean sentences better than other languages. |
Don’t Just Scratch the Surface: Enhancing Word Representations for Korean with Hanja (D19-1)
Copied to clipboard
| Challenge: | Existing knowledge of Korean and Chinese is based on cultural and historical reasons. |
| Approach: | They propose a method for improving Korean word representations using additional linguistic annotation by leveraging the fact that Hanja is closely related to Chinese. |
| Outcome: | The proposed approach improves representations on a novel Korean news headline generation task. |
Diversifying language models for lesser-studied languages and language-usage contexts: A case of second language Korean (2023.findings-emnlp)
Copied to clipboard
| Challenge: | Existing morpheme parsers/taggers do not work reliably and optimally for L2 data. |
| Approach: | They train a neural network model on varying L2 datasets and measure its morpheme parsing/POS tagging performance on L2 test sets. |
| Outcome: | The proposed model excels in domain-specific tokenization and POS tagging compared to the baseline model. |
Kosmic: Korean Text Similarity Metric Reflecting Honorific Distinctions (2024.lrec-main)
Copied to clipboard
| Challenge: | Existing methods for text similarity measurement focus on the semantic dimension, neglecting the unique linguistic attributes found in languages like Korean. |
| Approach: | They propose a Korean text-similarity metric that encompasses the semantic and tonal facets of a given text pair. |
| Outcome: | The proposed method outperforms existing methods in Korean and other languages . it identifies which methods preserve semantics and tone while preserving similarity . |
The Undesirable Dependence on Frequency of Gender Bias Metrics Based on Word Embeddings (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Recent studies have found word embeddings can capture semantic similarity but may be affected by word frequency. |
| Approach: | They find that word embeddings can capture semantic similarity but may be affected by word frequency . they compare this effect with an alternative metric based on Pointwise Mutual Information . |
| Outcome: | The proposed method does not depend on word frequency, but it does return female bias in low frequency words. |
Constructing Korean Learners’ L2 Speech Corpus of Seven Languages for Automatic Pronunciation Assessment (2024.lrec-main)
Copied to clipboard
| Challenge: | Multilingual L2 speech corpora for automatic speech assessment are currently available, but lack comprehensive annotations of L2 from non-native speakers of various languages. |
| Approach: | They propose to use Korean learners’ L2 speech corpus of seven languages to develop automatic speech assessment. |
| Outcome: | The proposed corpus contains 1,200 hours of L2 speech data from Korean learners (400 hours for English, 200 hours each for Japanese and Chinese, 100 hours each in French, German, Spanish, and Russian). |
Rich Character-Level Information for Korean Morphological Analysis and Part-of-Speech Tagging (C18-1)
Copied to clipboard
| Challenge: | Korean is a highly agglutinative, character-rich language, requiring dictionary-less morphological analysis . a novel model can perform morphology and part-of-speech tagging without prior knowledge . |
| Approach: | They propose a multi-stage action-based model that performs morphological transformation and part-of-speech tagging using arbitrary units of input. |
| Outcome: | The proposed model achieves state-of-the-art word and sentence-level tagging accuracy with Korean corpus. |
User Guide for KOTE: Korean Online That-gul Emotions Dataset (2024.lrec-main)
Copied to clipboard
| Challenge: | sentiment analysis is used to identify emotional aspects of texts but is limited by its small size and limited range of emotions. |
| Approach: | They propose a Korean sentiment analysis corpus that is limited by its small size and narrow range of emotions . they propose to fine-tune the KOTE dataset and analyze the results for social discrimination . |
| Outcome: | The proposed dataset includes 50,000 Korean online comments, each manually labeled for 43 emotions and NO EMOTION. |
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorial Abstracts (N18-6)
Copied to clipboard
| Challenge: | NAACL-HLT tutorials are an opportunity for conference attendees to participate in a tutorial on a timely topic of importance to the field. |
| Approach: | NAACL-HLT 2018 is a tutorial session for conference attendees to participate in . a total of 51 tutorial submissions were received, of which 6 were selected for presentation . |
| Outcome: | the tutorials committee at the 2018 NAACL-HLT in New Orleans received 51 submissions . the six tutorials demonstrate the increasing relevance of NLP to a wide range of fields . |