← Resources & Methods
Natural Language Processing › Resources & Methods ›

Text Representation

2246 directly classified papers

Papers per year

Papers

Paraphrases do not explain word analogies EACL 2021
Implicit Representations of Meaning in Neural Language Models IJCNLP 2021
Explaining Contextualization in Language Models using Visual Analytics IJCNLP 2021
Dictionary-based Debiasing of Pre-trained Word Embeddings EACL 2021
A Bidirectional Transformer Based Alignment Model for Unsupervised Word Alignment IJCNLP 2021
Evaluating a Joint Training Approach for Learning Cross-lingual Embeddings with Sub-word Information without Parallel Corpora on Lower-resource Languages IJCNLP 2021
Debiasing Pre-trained Contextualised Embeddings EACL 2021
Denoising Word Embeddings by Averaging in a Shared Space IJCNLP 2021
Inducing Language-Agnostic Multilingual Representations IJCNLP 2021
ParaSCI: A Large Scientific Paraphrase Dataset for Longer Paraphrase Generation EACL 2021
TDMSci: A Specialized Corpus for Scientific Literature Entity Tagging of Tasks Datasets and Metrics EACL 2021
Discrete Cosine Transform as Universal Sentence Encoder ACL 2021
Introducing Orthogonal Constraint in Structural Probes ACL 2021
NPVec1: Word Embeddings for Nepali - Construction and Evaluation ACL 2021
Examining Cross-lingual Contextual Embeddings with Orthogonal Structural Probes EMNLP 2021
Pairwise Supervised Contrastive Learning of Sentence Representations EMNLP 2021
A Statistical Extension of Byte-Pair Encoding IJCNLP 2021
SHAPELURN: An Interactive Language Learning Game with Logical Inference IJCNLP 2021
Distilling Relation Embeddings from Pretrained Language Models EMNLP 2021
Modeling Text using the Continuous Space Topic Model with Pre-Trained Word Embeddings IJCNLP 2021
Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence IJCNLP 2021
MuVER: Improving First-Stage Entity Retrieval with Multi-View Entity Representations EMNLP 2021
Discrete Cosine Transform as Universal Sentence Encoder IJCNLP 2021
Relative Importance in Sentence Processing IJCNLP 2021
Chinese WPLC: A Chinese Dataset for Evaluating Pretrained Language Models on Word Prediction Given Long-Range Context EMNLP 2021