arXiv Computation and Language August 28, 2026 By Jungyeul Park, KyungTae Lim, Zihao Huang, Eunkyul Leah Jo, Yige Chen, Chulwoo Park

Representing and Parsing Korean Constituency Structure at Different Levels of Granularity

Read the original on arXiv Computation and Language →

The paper investigates how different representations of Korean constituency structure affect parsing performance. It compares three formats—Morpheme+XPOS, Eojeol+XPOS, and Eojeol+UPOS—derived from the Penn Korean Treebank, using gold segmentation and labels to evaluate transition-based parsers. Results show that fine-grained morphological and XPOS information yields the best parsing accuracy, while eojeol-based representations offer shorter transition sequences but lower performance when only UPOS is used.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

computer-vision

arXiv Computation and Language

Aug 31

Lexically conditioned realization ambiguity in Korean predicate morphology

The article investigates Korean predicate morphology, showing that a sequence of canonical morphemes and grammatical labels does not uniquely determine the surface form for certain predicates. It demonstrates that identical or nearly identical stem-ending configurations can produce different outputs depending on lexical identity and realization class membership. The study frames this as homonymy with inflectional divergence, highlighting that lexical meaning, subcategorization, and semantic role structure are essential for determining the correct surface realization.

By Wonjun Oh, KyungTae Lim, Jungyeul Park

arXiv Machine Learning

Aug 4

Automatic Annotation of Ancient Greek Vowel Length

arXiv:2608. 01935v1 Announce Type: cross Abstract: Prior work in Ancient Greek NLP relies on corpora that do not disambiguate the phonemic vowel length of alpha, iota, and ypsilon, together known as the dichrona.

By Albin Th\"orn Cleland, Eric Cullhed

llms nlp benchmarks

arXiv Machine Learning

Aug 12

The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding

arXiv:2608. 10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step.

By I\c{s}{\i}l \"Ozg\"u, Yaoxuan Wu, Guy Van den Broeck, Miryung Kim

llms efficiency safety

arXiv AI

Sep 18

KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms

KoNeoBench is a curated dataset designed to evaluate large language models’ understanding of Korean neologisms. It contains 1,785 recently attested Korean words from online news since 2020, each accompanied by usage examples, word‑formation analyses, and dictionary‑style definitions. The authors define four evaluation tasks, report results from recent models and a human baseline, and find that current LLMs struggle with recovering source components, distinguishing semantic categories, and generating accurate definitions.

By Soha Lee, Soojin Lee, Heesung Yang, Hyunju Song, Hyunji Lee, Jinsan An, Jeongwan Shin, Jin Hyun Park, Jun Lee, Hyeyoung Park, Kilim Nam

llms benchmarks

arXiv Machine Learning

Jul 10

Holographic Neural PCFG for Unsupervised Parsing

arXiv:2607. 08063v1 Announce Type: cross Abstract: Unsupervised constituency parsing aims to accurately induce latent tree structures from raw text alone.

By Ryosuke Yamaki, Daichi Mochihashi, Nobutaka Shimada, Tadahiro Taniguchi

rag computer-vision benchmarks

arXiv Computation and Language

Aug 28

Non-binary bottom-up constituency parsing without arity actions

arXiv:2607. 10591v2 Announce Type: replace Abstract: Non-binary bottom-up constituency parsing commonly uses arity-specific reductions such as \(\textsc{Reduce-}X\#k\), which jointly specify the mother label and number of children.

By Jungyeul Park, Eunkyul Leah Jo, Zihao Huang

One email a morning, machine-written

Related stories

Lexically conditioned realization ambiguity in Korean predicate morphology

Automatic Annotation of Ancient Greek Vowel Length

The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding

KoNeoBench: A Curated Evaluation Dataset for LLM Understanding of Korean Neologisms

Holographic Neural PCFG for Unsupervised Parsing

Non-binary bottom-up constituency parsing without arity actions