HL Dataset: Grounding High-Level Linguistic Concepts in Vision. (arXiv:2302.12189v1 [cs.CL])
Simple and Scalable Nearest Neighbor Machine Translation. (arXiv:2302.12188v1 [cs.CL])
More than you've asked for: A Comprehensive Analysis of Novel Prompt Injection Threats to Application-Integrated Large Language Models. (arXiv:2302.12173v1 [cs.CR])
Prosodic features improve sentence segmentation and parsing. (arXiv:2302.12165v1 [cs.CL])
On the Generalization Ability of Retrieval-Enhanced Transformers. (arXiv:2302.12128v1 [cs.CL])
KHAN: Knowledge-Aware Hierarchical Attention Networks for Political Stance Prediction. (arXiv:2302.12126v1 [cs.CL])
On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspective. (arXiv:2302.12095v1 [cs.AI])
Deep learning model for Mongolian Citizens Feedback Analysis using Word Vector Embeddings. (arXiv:2302.12069v1 [cs.CL])
ProsAudit, a prosodic benchmark for self-supervised speech models. (arXiv:2302.12057v1 [cs.CL])
SPINDLE: Spinning Raw Text into Lambda Terms with Graph Attention. (arXiv:2302.12050v1 [cs.CL])
Evaluating Automatic Speech Recognition in an Incremental Setting. (arXiv:2302.12049v1 [cs.CL])
Generative Sentiment Transfer via Adaptive Masking. (arXiv:2302.12045v1 [cs.CL])
Exploring Social Media for Early Detection of Depression in COVID-19 Patients. (arXiv:2302.12044v1 [cs.CL])
Conversational Agents and Children: Let Children Learn. (arXiv:2302.12043v1 [cs.CL])
Natural Language Processing in the Legal Domain. (arXiv:2302.12039v1 [cs.CL])
Metric-oriented Speech Enhancement using Diffusion Probabilistic Model. (arXiv:2302.11989v1 [cs.SD])
Does Deep Learning Learn to Abstract? A Systematic Probing Framework. (arXiv:2302.11978v1 [cs.LG])
Sentence Simplification via Large Language Models. (arXiv:2302.11957v1 [cs.CL])
Improved Training of Mixture-of-Experts Language GANs. (arXiv:2302.11875v1 [cs.CL])
Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs. (arXiv:2302.11849v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl