PulseAugur
EN
LIVE 10:03:37

LLMs enable cross-lingual discourse parsing for Japanese SDRT corpora

By PulseAugur Editorial · [1 sources] ·

Researchers have developed a method to construct Japanese discourse structure corpora by translating existing English corpora using large language models (LLMs). This approach allows for discourse parsing based on Segmented Discourse Representation Theory (SDRT) in Japanese, a task previously limited by a lack of specific corpora. Comparative evaluations showed that both prompt-based and fine-tuned LLMs achieved performance comparable to English, indicating the cross-lingual applicability of SDRT-based discourse parsing. Further analysis revealed that Japanese discourse markers had minimal impact, with model predictions relying more on contextual discourse relations than specific content, which may explain the similar performance despite linguistic differences. AI

IMPACT Demonstrates LLMs' capability in cross-lingual corpus creation and discourse analysis, potentially advancing NLP research in under-resourced languages.

RANK_REASON Academic paper detailing a new methodology for discourse parsing. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

LLMs enable cross-lingual discourse parsing for Japanese SDRT corpora

How we ranked this

Signal score
13 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
Academic paper detailing a new methodology for discourse parsing. [lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration
Single-source cluster
Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics
paper, other
Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance
High
Clearly on-topic for AI-industry coverage.
Story freshness
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

Full methodology in our editorial standards.

COVERAGE [1]

  1. arXiv cs.CL TIER_1 English(EN) · Satomu Tomisaki, Yosuke Mikami, Amane Watahiki, Hitomi Yanaka ·

    Japanese Discourse Structure Analysis Based on Segmented Discourse Representation Theory Using LLMs

    arXiv:2610.36667v1 Announce Type: new Abstract: Discourse parsing based on Segmented Discourse Representation Theory (SDRT) is crucial for capturing the structural dynamics of dialogues. However, most prior research focuses on English, and its effectiveness for Japanese remains u…

RELATED ENTITIES

RELATED TOPICS