Coreference
View article: The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma
The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma Open
The mathematical intelligibility of the physical universe, famously described as "unreasonably effective" by Eugene Wigner, is not a miraculous property of the cosmos but an emergent feature of our interaction with it. This article argues …
View article: The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma
The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma Open
The mathematical intelligibility of the physical universe, famously described as "unreasonably effective" by Eugene Wigner, is not a miraculous property of the cosmos but an emergent feature of our interaction with it. This article argues …
View article: The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma
The Ontological Status of Mathematical Laws: A Structural-Operative Resolution to Wigner's Enigma Open
The mathematical intelligibility of the physical universe, famously described as "unreasonably effective" by Eugene Wigner, is not a miraculous property of the cosmos but an emergent feature of our interaction with it. This article argues …
View article: Syntactic and rhetorical transformation in Vietnamese EFL students’ academic writing
Syntactic and rhetorical transformation in Vietnamese EFL students’ academic writing Open
This study examines how AI-assisted writing tools reshape the linguistic and rhetorical profile of Vietnamese EFL students’ academic texts. Using a convergent mixed-methods design, we analyzed paired drafts (pre-AI and post-AI revision) fr…
View article: Long-Text Summarisation
Long-Text Summarisation Open
This study enhances text summarization techniques using advanced transformer models to handle complex documents like those in the BIGPATENT dataset, which includes 1.3 million U.S. patent documents. We focused on integrating self-attention…
View article: Long-Text Summarisation
Long-Text Summarisation Open
This study enhances text summarization techniques using advanced transformer models to handle complex documents like those in the BIGPATENT dataset, which includes 1.3 million U.S. patent documents. We focused on integrating self-attention…
View article: Data associated with manuscript "Multi-scale classification decodes the complexity of the human E3 ligome"
Data associated with manuscript "Multi-scale classification decodes the complexity of the human E3 ligome" Open
This repository contains: Additional supplementary data files, Source data, Final figures, and Scripts associated with the manuscript "Multi-scale classification decodes the complexity of the human E3 ligome".
View article: Data associated with manuscript "Multi-scale classification decodes the complexity of the human E3 ligome"
Data associated with manuscript "Multi-scale classification decodes the complexity of the human E3 ligome" Open
This repository contains: Additional supplementary data files, Source data, Final figures, and Scripts associated with the manuscript "Multi-scale classification decodes the complexity of the human E3 ligome".
View article: Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs
Chatty-KG: A Multi-Agent AI System for On-Demand Conversational Question Answering over Knowledge Graphs Open
Conversational Question Answering over Knowledge Graphs (KGs) combines the factual grounding of KG-based QA with the interactive nature of dialogue systems. KGs are widely used in enterprise and domain applications to provide structured, e…
View article: DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble Approach
DPATransLLM: Detection of Pronominal Anaphora in Turkish Sentences Using Transformer-Based, Large Language Models and Hybrid Ensemble Approach Open
In the current information age, with the exponential growth of data volume and language-based applications, the accurate resolution of intra-contextual relationships in texts has become indispensable for both academic research and industri…
View article: Orações adverbiais em Línguas Tupi
Orações adverbiais em Línguas Tupi Open
Tupian languages typically do not exhibit tense morphology in subordinate clauses, although they show aspectual morphology in these environments. We examine adverbial clauses in these languages, particularly the syntactic strategies used t…
View article: M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark Open
We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning, cro…
View article: M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark
M^3-Bench: Multi-Modal, Multi-Hop, Multi-Threaded Tool-Using MLLM Agent Benchmark Open
We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning, cro…
View article: Principle B is an early, predictive filter on active cataphor resolution: Eye-tracking evidence
Principle B is an early, predictive filter on active cataphor resolution: Eye-tracking evidence Open
Pronouns that precede their antecedents are called cataphors. Upon encountering a cataphor, comprehenders engage in an active, eager search for its antecedent later in the sentence. The processing of cataphoric dependencies has been used t…
View article: Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces Open
Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation …
View article: Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces
Beyond Fact Retrieval: Episodic Memory for RAG with Generative Semantic Workspaces Open
Large Language Models (LLMs) face fundamental challenges in long-context reasoning: many documents exceed their finite context windows, while performance on texts that do fit degrades with sequence length, necessitating their augmentation …
View article: Few-Shot Coreference Resolution with Semantic Difficulty Metrics and In-Context Learning
Few-Shot Coreference Resolution with Semantic Difficulty Metrics and In-Context Learning Open
This paper presents our submission to the CRAC 2025 Shared Task on Multilingual Coreference Resolution in the LLM track. We propose a prompt-based few-shot coreference resolution system where the final inference is performed by Grok-3 usin…
View article: Exploring Coreference Resolution in Glosses of German Sign Language
Exploring Coreference Resolution in Glosses of German Sign Language Open
In recent years, research on sign languages has attracted increasing attention in the NLP community and requires more effort from a linguistic perspective. In this paper, we explore coreference resolution in German Sign Language (GSL) prim…
View article: Few-Shot Multilingual Coreference Resolution Using Long-Context Large Language Models
Few-Shot Multilingual Coreference Resolution Using Long-Context Large Language Models Open
In this work, we present our system, which ranked second in the CRAC 2025 Shared Task on Multilingual Coreference Resolution (LLM Track). For multilingual coreference resolution, our system mainly uses long-context large language models (L…
View article: GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task?
GLaRef@CRAC2025: Should we transform coreference resolution into a text generation task? Open
We present the submissions of our team to the Unconstrained and LLM tracks of the Computational Models of Reference, Anaphora and Coreference (CRAC2025) shared task, where we ended respectively in the fifth and the first place, but neverth…
View article: Coreference in simplified German: Linguistic features and challenges of automatic annotation
Coreference in simplified German: Linguistic features and challenges of automatic annotation Open
In this paper, we analyse coreference annotation of the German language, focussing on the phenomenon of simplification, that is, the tendency to use words and constructions that are assumed to be easier perceived, understood, or produced. …
View article: CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution
CorPipe at CRAC 2025: Evaluating Multilingual Encoders for Multilingual Coreference Resolution Open
We present CorPipe 25, the winning entry to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. This fourth iteration of the shared task introduces a new LLM track alongside the original unconstrained track, features reduced …
View article: The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works
The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works Open
While coreference resolution is attracting more interest than ever from computational literature researchers, representative datasets of fully annotated long documents remain surprisingly scarce. In this paper, we introduce a new annotated…
View article: Revisiting the Givenness Hierarchy. A Corpus-Based Evaluation
Revisiting the Givenness Hierarchy. A Corpus-Based Evaluation Open
Gundel et al.'s Givenness Hierarchy remains one of the most influental frameworks of Information Status to this date, and has been employed in different technical contexts to account for context-sensitive and hearer-tailored language in hu…
View article: Impact of ASR Transcriptions on French Spoken Coreference Resolution
Impact of ASR Transcriptions on French Spoken Coreference Resolution Open
This study introduces a new ASR-transcribed coreference corpus for French and explores the transferability of coreference resolution models from human-transcribed to ASR-transcribed data. Given the challenges posed by differences in text c…
View article: Fine-Tuned Llama for Multilingual Text-to-Text Coreference Resolution
Fine-Tuned Llama for Multilingual Text-to-Text Coreference Resolution Open
This paper describes our approach to the CRAC 2025 Shared Task on Multilingual Coreference Resolution. We compete in the LLM track, where the systems are limited to generative text-to-text approaches. Our system is based on Llama 3.1-8B, f…
View article: Timing of referential chain objects construction in syntactic binding and discourse coreference during the filler-gap dependency enabling a binding domain for the embedded clause.
Timing of referential chain objects construction in syntactic binding and discourse coreference during the filler-gap dependency enabling a binding domain for the embedded clause. Open
Timing of referential chain objects construction in syntactic binding and discourse coreference during the filler-gap dependency enabling a binding domain for the embedded clause.
View article: The 64-electrode EGI system.
The 64-electrode EGI system. Open
Hypotheses about top-down structure building propose that gamma (>30Hz) oscillations support the creation of syntax-semantics objects, contrasting with slow-rhythm entrainment of gamma oscillations tracking semantic fitness in bottom-up c…
View article: Distinct paths to false memory revealed in hundreds of narrative recalls
Distinct paths to false memory revealed in hundreds of narrative recalls Open
Memory distortions emerge from a complex interplay between prior knowledge and ongoing experience—dynamics which are not readily provoked in controlled laboratory experiments. Here we investigate naturally occurring memory distortions usin…
View article: A dataset of object agreement in Hewramî
A dataset of object agreement in Hewramî Open
This dataset contains manual tagging for the paper A corpus-based analysis of object indexing in Hewramî (accepted, Corpus Linguistics and Linguistic Theory), written by Masoud Mohammadirad. The data set contains tagging for transitive obj…