paper-with-me

Papers

Graph Fusion Across Languages using Large Language Models

2026-03-22 · Kaung Myat Kyaw, Khush Agarwal, Jonathan Chan arxiv

Combining multiple knowledge graphs (KGs) across linguistic boundaries is a persistent challenge due to semantic heterogeneity and the complexity of graph environments. We propose a framework for cross-lingual graph fusion, leveraging the in-context reasoning and multilingual semantic priors of Large Language Models (LLMs). The framework implements structural linearization by mapping triplets directly into natural language sequences (e.g., [head] [relation] [tail]), enabling the LLM to map relations and reconcile entities between an evolving fused graph ($G_{c}^{(t-1)}$) and a new candidate graph ($G_{t}$). Evaluated on the DBP15K dataset, this exploratory study demonstrates that LLMs can serve as a universal semantic bridge to resolve cross-lingual discrepancies. Results show the successful sequential agglomeration of multiple heterogeneous graphs, offering a scalable, modular solution for continuous knowledge synthesis in multi-source, multilingual environments.

📄 PDF Abstract BibTeX arXiv:2603.21248

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Graphs

Similar Papers 제목 키워드 기반

Syn2Vec: Synset Colexification Graphs for Lexical Semantic Similarity

2022-07-01 · NAACL 2022 7 · John Harvill, Roxana Girju, Mark Hasegawa-Johnson

In this paper we focus on patterns of colexification (co-expressions of form-meaning mapping in the lexicon) as an aspect of lexical-semantic organization, and use them to build large scale synset graphs across BabelNet’…

Semantic SimilaritySemantic Textual Similarity

Why do language models perform worse for morphologically complex languages?

2024-11-21 · Catherine Arnett, Benjamin K. Bergen

Language models perform differently across languages. It has been previously suggested that morphological typology may explain some of this variability (Cotterell et al., 2018). We replicate previous analyses and find ad…

Language ModelingLanguage Modelling

Beyond N-Grams: Rethinking Evaluation Metrics and Strategies for Multilingual Abstractive Summarization

2025-07-11 · Itai Mondshine, Tzuf Paz-Argaman, Reut Tsarfaty arxiv

Automatic n-gram based metrics such as ROUGE are widely used for evaluating generative tasks such as summarization. While these metrics are considered indicative (even if imperfect) of human evaluation for English, their…

Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Grapheme-to-Phoneme (G2P) has many applications in NLP and speech fields. Most existing work focuses heavily on languages with abundant training datasets, which limit the scope of target languages to less than 100 langua…

8kGrapheme-to-Phoneme ConversionZero-Shot Learning

Zero-shot Learning for Grapheme to Phoneme Conversion with Language Ensemble

2022-05-01 · Findings (ACL) 2022 5 · Xinjian Li, Florian Metze, David Mortensen, Shinji Watanabe 외

Grapheme-to-Phoneme (G2P) has many applications in NLP and speech fields. Most existing work focuses heavily on languages with abundant training datasets, which limits the scope of target languages to less than 100 langu…

8kGrapheme-to-Phoneme ConversionZero-Shot Learning