Text Representation

When classifying grammatical role, BERT doesn’t care about word order... except when it matters ACL 2022 Where Does Linguistic Information Emerge in Neural Language Models? Measuring Gains and Contributions across Layers COLING 2022 Whose Language Counts as High Quality? Measuring Language Ideologies in Text Data Selection EMNLP 2022 WikiHan: A New Comparative Dataset for Chinese Languages COLING 2022 WikiOmnia: filtration and evaluation of the generated QA corpus on the whole Russian Wikipedia EMNLP 2022 Word Representation Models for Arabic Dialect Identification EMNLP 2022 WordTies: Measuring Word Associations in Language Models via Constrained Sampling EMNLP 2022 Word Tour: One-dimensional Word Embeddings via the Traveling Salesman Problem NAACL 2022 You Are My Type! Type Embeddings for Pre-trained Language Models EMNLP 2022 A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space ACL 2021 A Computational Model for Interactive Transcription NAACL 2021 Adapting Entities across Languages and Cultures EMNLP 2021 A Fine-Grained Annotated Corpus for Target-Based Opinion Analysis of Economic and Financial Narratives EMNLP 2021 Aligning Estonian and Russian news industry keywords with the help of subtitle translations and an environmental thesaurus EACL 2021 A Massively Multilingual Analysis of Cross-linguality in Shared Embedding Space EMNLP 2021 A Mixed-Methods Analysis of Western and Hong Kong–based Reporting on the 2019–2020 Protests EMNLP 2021 Analyzing the Surprising Variability in Word Embedding Stability Across Languages EMNLP 2021 Anchor-based Bilingual Word Embeddings for Low-Resource Languages ACL 2021 Anchor & Transform: Learning Sparse Embeddings for Large Vocabularies ICLR 2021 AND does not mean OR: Using Formal Languages to Study Language Models’ Representations ACL 2021 ANDI at SemEval-2021 Task 1: Predicting complexity in context using distributional models, behavioural norms, and lexical resources SemEval 2021 An Immersive Computational Text Analysis Course for Non-Computer Science Students at Barnard College NAACL 2021 A (Non)-Perfect Match: Mapping plWordNet onto PrincetonWordNet EACL 2021 Are we human, or are we users? The role of natural language processing in human-centric news recommenders that nudge users to diverse content ACL 2021 A Simple and Effective Positional Encoding for Transformers EMNLP 2021