Skip to content
conftrace_

Text Representation

2,156 papers

2
5
230
293
'10
'15
'20
'25

Papers

Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI NAACL 2024 Universal Feature-based Morphological Trees COLING 2024 Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization EMNLP 2024 Unpacking Tokenization: Evaluating Text Compression and its Correlation with Model Performance ACL 2024 Unsupervised Authorship Attribution for Medieval Latin Using Transformer-Based Embeddings COLING 2024 Unveiling Semantic Information in Sentence Embeddings COLING 2024 Using Machine Learning to Predict Item Difficulty and Response Time in Medical Tests NAACL 2024 Variationist: Exploring Multifaceted Variation and Bias in Written Language Data ACL 2024 Varying Sentence Representations via Condition-Specified Routers EMNLP 2024 ViLexNorm: A Lexical Normalization Corpus for Vietnamese Social Media Text EACL 2024 VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval ACL 2024 Watermarking for Large Language Models ACL 2024 Where are we Still Split on Tokenization? EACL 2024 Where is the signal in tokenization space? EMNLP 2024 Whitening Not Recommended for Classification Tasks in LLMs ACL 2024 Who Wrote When? Author Diarization in Social Media Discussions EMNLP 2024 Wikiformer: Pre-training with Structured Information of Wikipedia for Ad-Hoc Retrieval AAAI 2024 Willkommens-Merkel, Chaos-Johnson, and Tore-Klose: Modeling the Evaluative Meaning of German Personal Name Compounds COLING 2024 Word Embeddings Are Steers for Language Models ACL 2024 WordNet under Scrutiny: Dictionary Examples in the Era of Large Language Models COLING 2024 Zero-Shot Tokenizer Transfer NeurIPS 2024 Zipfian Whitening NeurIPS 2024 A Comparative Study on Textual Saliency of Styles from Eye Tracking, Annotations, and Language Models CoNLL 2023 Acoustic Word Embeddings for Untranscribed Target Languages with Continued Pretraining and Learned Pooling Interspeech 2023 Aggregating Crowdsourced and Automatic Judgments to Scale Up a Corpus of Anaphoric Reference for Fiction and Wikipedia Texts EACL 2023