Robustness of Learning from Task Instructions. (arXiv:2212.03813v3 [cs.CL] UPDATED)
Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning. (arXiv:2212.03760v4 [cs.IR] UPDATED)
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations. (arXiv:2211.08794v2 [cs.CL] UPDATED)
Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and Linguistic Features. (arXiv:2211.00342v2 [cs.SD] UPDATED)
A Close Look into the Calibration of Pre-trained Language Models. (arXiv:2211.00151v3 [cs.CL] UPDATED)
Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning. (arXiv:2210.07565v3 [cs.CL] UPDATED)
Machine Generated Text: A Comprehensive Survey of Threat Models and Detection Methods. (arXiv:2210.07321v4 [cs.CL] UPDATED)
Are Synonym Substitution Attacks Really Synonym Substitution Attacks?. (arXiv:2210.02844v3 [cs.CL] UPDATED)
Music-to-Text Synaesthesia: Generating Descriptive Text from Music Recordings. (arXiv:2210.00434v2 [eess.AS] UPDATED)
Vega-MT: The JD Explore Academy Translation System for WMT22. (arXiv:2209.09444v4 [cs.CL] UPDATED)
Shortcut Learning of Large Language Models in Natural Language Understanding. (arXiv:2208.11857v2 [cs.CL] UPDATED)
Persuasion Strategies in Advertisements. (arXiv:2208.09626v2 [cs.CL] UPDATED)
General-to-Specific Transfer Labeling for Domain Adaptable Keyphrase Generation. (arXiv:2208.09606v2 [cs.CL] UPDATED)
Characterizing narrative time in books through fluctuations in power and danger arcs. (arXiv:2208.09496v3 [cs.CL] UPDATED)
Delving into the Openness of CLIP. (arXiv:2206.01986v3 [cs.CV] UPDATED)
Helpfulness and Fairness of Task-Oriented Dialogue Systems. (arXiv:2205.12554v3 [cs.CL] UPDATED)
A Large and Diverse Arabic Corpus for Language Modeling. (arXiv:2201.09227v3 [cs.CL] UPDATED)
Cross-Modal Retrieval for Motion and Text via MildTriple Loss. (arXiv:2305.04195v1 [cs.CV])
OpenViVQA: Task, Dataset, and Multimodal Fusion Models for Visual Question Answering in Vietnamese. (arXiv:2305.04183v1 [cs.CL])
Shall We Trust All Relational Tuples by Open Information Extraction? A Study on Speculation Detection. (arXiv:2305.04181v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl