#Computational Linguistics

Articles (14)

• 🇺🇸 Between Century and Poet: Graph-Based Lexical Semantic Change in Persian Poetry — 09/04/2026 [USA]

  arXiv:2604.06674v1 Announce Type: cross Abstract: Meaning in Persian poetry is both historical and relational. Words persist through literary tradition while shifting their force through changing con...

  Related: #Digital Humanities, #Literary Analysis
• 🇺🇸 URMF: Uncertainty-aware Robust Multimodal Fusion for Multimodal Sarcasm Detection — 09/04/2026 [USA]

  arXiv:2604.06728v1 Announce Type: cross Abstract: Multimodal sarcasm detection (MSD) aims to identify sarcastic intent from semantic incongruity between text and image. Although recent methods have i...

  Related: #Artificial Intelligence, #Social Media Analysis
• 🇺🇸 Environmental, Social and Governance Sentiment Analysis on Slovene News: A Novel Dataset and Models — 09/04/2026 [USA]

  arXiv:2604.06826v1 Announce Type: cross Abstract: Environmental, Social, and Governance (ESG) considerations are increasingly integral to assessing corporate performance, reputation, and long-term su...

  Related: #Artificial Intelligence, #Sustainable Finance
• 🇺🇸 FrameNet Semantic Role Classification by Analogy — 23/03/2026 [USA]

  arXiv:2603.19825v1 Announce Type: cross Abstract: In this paper, we adopt a relational view of analogies applied to Semantic Role Classification in FrameNet. We define analogies as formal relations o...

  Related: #Natural Language Processing
• 🇺🇸 Breeze Taigi: Benchmarks and Models for Taiwanese Hokkien Speech Recognition and Synthesis — 23/03/2026 [USA]

  arXiv:2603.19259v1 Announce Type: cross Abstract: Taiwanese Hokkien (Taigi) presents unique opportunities for advancing speech technology methodologies that can generalize to diverse linguistic conte...

  Related: #Language Technology
• 🇺🇸 Morphemes Without Borders: Evaluating Root-Pattern Morphology in Arabic Tokenizers and LLMs — 18/03/2026 [USA]

  arXiv:2603.15773v1 Announce Type: cross Abstract: This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphol...

  Related: #Arabic Morphology
• 🇺🇸 COGNAC at SemEval-2026 Task 5: LLM Ensembles for Human-Level Word Sense Plausibility Rating in Challenging Narratives — 18/03/2026 [USA]

  arXiv:2603.15897v1 Announce Type: cross Abstract: We describe our system for SemEval-2026 Task 5, which requires rating the plausibility of given word senses of homonyms in short stories on a 5-point...

  Related: #AI Evaluation
• 🇺🇸 Computational lexical analysis of Flamenco genres — 16/03/2026 [USA]

  arXiv:2405.05723v2 Announce Type: replace-cross Abstract: Flamenco, recognized by UNESCO as part of the Intangible Cultural Heritage of Humanity, is a profound expression of cultural identity rooted ...

  Related: #Music Analysis
• 🇺🇸 What Makes an Ideal Quote? Recommending "Unexpected yet Rational" Quotations via Novelty — 27/02/2026 [USA]

  arXiv:2602.22220v1 Announce Type: cross Abstract: Quotation recommendation aims to enrich writing by suggesting quotes that complement a given context, yet existing systems mostly optimize surface-le...

  Related: #Information Retrieval, #Artificial Intelligence
• 🇺🇸 Efficient Dialect-Aware Modeling and Conditioning for Low-Resource Taiwanese Hakka Speech Processing — 27/02/2026 [USA]

  arXiv:2602.22522v1 Announce Type: cross Abstract: Taiwanese Hakka is a low-resource, endangered language that poses significant challenges for automatic speech recognition (ASR), including high diale...

  Related: #Language Technology, #Endangered Languages Preservation
• 🇺🇸 RooseBERT: A New Deal For Political Language Modelling — 25/02/2026 [USA]

  arXiv:2508.03250v3 Announce Type: replace-cross Abstract: The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automa...

  Related: #Political Language Analysis, #Artificial Intelligence
• 🇺🇸 Semantic Chunking and the Entropy of Natural Language — 16/02/2026 [USA]

  arXiv:2602.13194v1 Announce Type: cross Abstract: The entropy rate of printed English is famously estimated to be about one bit per character, a benchmark that modern large language models (LLMs) hav...

  Related: #Information Theory, #Natural Language Processing
• 🇺🇸 Debate is efficient with your time — 10/02/2026 [USA]

  arXiv:2602.08630v1 Announce Type: new Abstract: AI safety via debate uses two competing models to help a human judge verify complex computational tasks. Previous work has established what problems de...

  Related: #AI Safety, #Human Oversight
• 🇺🇸 Hyperbolic Fine-Tuning for Large Language Models — 09/02/2026 [USA]

  arXiv:2410.04010v2 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated remarkable performance across various tasks. However, it remains an open question whether the ...

  Related: #Artificial Intelligence, #Mathematics