Text Representation

Sentence-Alignment in Semi-parallel Datasets NAACL 2025 Sinhala Encoder-only Language Models and Evaluation ACL 2025 Social Norms in Cinema: A Cross-Cultural Analysis of Shame, Pride and Prejudice NAACL 2025 Soft Syntactic Reinforcement for Neural Event Extraction NAACL 2025 Splintering Nonconcatenative Languages for Better Tokenization ACL 2025 Standardizing Heterogeneous Corpora with DUUR: A Dual Data- and Process-Oriented Approach to Enhancing NLP Pipeline Integration IJCNLP 2025 Sticking to the Mean: Detecting Sticky Tokens in Text Embedding Models ACL 2025 Stories that (are) Move(d by) Markets: A Causal Exploration of Market Shocks and Semantic Shifts across Different Partisan Groups ACL 2025 Studying the Effect of Hindi Tokenizer Performance on Downstream Tasks COLING 2025 Survey on Lexical Resources Focused on Multiword Expressions for the Purposes of NLP NAACL 2025 SWEb: A Large Web Dataset for the Scandinavian Languages ICLR 2025 TeCoFeS: Text Column Featurization using Semantic Analysis NAACL 2025 Tell, Don’t Show: Leveraging Language Models’ Abstractive Retellings to Model Literary Themes ACL 2025 Tethering Broken Themes: Aligning Neural Topic Models with Labels and Authors NAACL 2025 Textagon: Boosting Language Models with Theory-guided Parallel Representations ACL 2025 TEXT-CAKE: Challenging Language Models on Local Text Coherence COLING 2025 The Elephant in the Coreference Room: Resolving Coreference in Full-Length French Fiction Works EMNLP 2025 The Foundations of Tokenization: Statistical and Computational Concerns ICLR 2025 The Gemma Sutras: Fine-Tuning Gemma 3 for Sanskrit Sandhi Splitting EMNLP 2025 The iRead4Skills Intelligent Complexity Analyzer EMNLP 2025 The Learning Dynamics of Subword Segmentation for Morphologically Diverse Languages IJCNLP 2025 The revision of linguistic annotation in the Universal Dependencies framework: a look at the annotators’ behavior ACL 2025 The Russian-focused embedders’ exploration: ruMTEB benchmark and Russian embedding model design NAACL 2025 Thread: A Logic-Based Data Organization Paradigm for How-To Question Answering with Retrieval Augmented Generation EMNLP 2025 TNCSE: Tensor Norm Constraints for Unsupervised Contrastive Learning of Sentence Embeddings AAAI 2025