Text Representation

One Word, Two Sides: Traces of Stance in Contextualized Word Representations COLING 2022 On Isotropy Calibration of Transformer Models ACL 2022 On Masked Language Models for Contextual Link Prediction ACL 2022 On the Curious Case of l2 norm of Sense Embeddings EMNLP 2022 Optimizing text representations to capture (dis)similarity between political parties CoNLL 2022 Paraphrastic Representations at Scale EMNLP 2022 Perturbations and Subpopulations for Testing Robustness in Token-Based Argument Unit Recognition COLING 2022 Pretraining with Artificial Language: Studying Transferable Knowledge in Language Models ACL 2022 Probing for Labeled Dependency Trees ACL 2022 Probing with Noise: Unpicking the Warp and Weft of Embeddings EMNLP 2022 Problems with Cosine as a Measure of Embedding Similarity for High Frequency Words ACL 2022 PromptBERT: Improving BERT Sentence Embeddings with Prompts EMNLP 2022 Proposition-Level Clustering for Multi-Document Summarization NAACL 2022 Proxy Learning of Visual Concepts of Fine Art Paintings from Styles through Language Models AAAI 2022 QASem Parsing: Text-to-text Modeling of QA-based Semantics EMNLP 2022 RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction EMNLP 2022 Reference-free Summarization Evaluation via Semantic Correlation and Compression Ratio NAACL 2022 Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation EMNLP 2022 Reweighting Strategy Based on Synthetic Data Identification for Sentence Similarity COLING 2022 Roadblocks in Gender Bias Measurement for Diachronic Corpora ACL 2022 SBERT studies Meaning Representations: Decomposing Sentence Embeddings into Explainable Semantic Features AACL 2022 Scene Graph Parsing via Abstract Meaning Representation in Pre-trained Language Models NAACL 2022 Seeing the advantage: visually grounding word embeddings to better capture human semantic knowledge ACL 2022 SEHY: A Simple yet Effective Hybrid Model for Summarization of Long Scientific Documents AACL 2022 Semantic Shift Stability: Efficient Way to Detect Performance Degradation of Word Embeddings and Pre-trained Language Models AACL 2022