Improving Visual Grounding by Encouraging Consistent Gradient-based Explanations. (arXiv:2206.15462v3 [cs.CV] UPDATED)
Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models. (arXiv:2206.04615v3 [cs.CL] UPDATED)
DiMS: Distilling Multiple Steps of Iterative Non-Autoregressive Transformers for Machine Translation. (arXiv:2206.02999v2 [cs.CL] UPDATED)
Cross-View Language Modeling: Towards Unified Cross-Lingual Cross-Modal Pre-training. (arXiv:2206.00621v2 [cs.CL] UPDATED)
ClaimDiff: Comparing and Contrasting Claims on Contentious Issues. (arXiv:2205.12221v2 [cs.CL] UPDATED)
Recent Advances in Neural Text Generation: A Task-Agnostic Survey. (arXiv:2203.03047v3 [cs.CL] UPDATED)
Measuring the Impact of Individual Domain Factors in Self-Supervised Pre-Training. (arXiv:2203.00648v3 [cs.CL] UPDATED)
Multi-Row, Multi-Span Distant Supervision For Table+Text Question. (arXiv:2112.07337v3 [cs.CL] UPDATED)
A Comprehensive Review of State-of-The-Art Methods for Java Code Generation from Natural Language Text. (arXiv:2306.06371v1 [cs.CL])
Improving Non-autoregressive Translation Quality with Pretrained Language Model, Embedding Distillation and Upsampling Strategy for CTC. (arXiv:2306.06345v1 [cs.CL])
Investigating the Effectiveness of ChatGPT in Mathematical Reasoning and Problem Solving: Evidence from the Vietnamese National High School Graduation Examination. (arXiv:2306.06331v1 [cs.CL])
Towards Arabic Multimodal Dataset for Sentiment Analysis. (arXiv:2306.06322v1 [cs.CL])
Protect Your Prompts: Protocols for IP Protection in LLM Applications. (arXiv:2306.06297v1 [cs.CL])
Measuring and Modifying Factual Knowledge in Large Language Models. (arXiv:2306.06264v1 [cs.CL])
Record Deduplication for Entity Distribution Modeling in ASR Transcripts. (arXiv:2306.06246v1 [cs.CL])
Using Foundation Models to Detect Policy Violations with Minimal Supervision. (arXiv:2306.06234v1 [cs.CL])
Probing self-supervised speech models for phonetic and phonemic information: a case study in aspiration. (arXiv:2306.06232v1 [cs.CL])
Conformalizing Machine Translation Evaluation. (arXiv:2306.06221v1 [cs.CL])
Morphosyntactic probing of multilingual BERT models. (arXiv:2306.06205v1 [cs.CL])
Reliability Check: An Analysis of GPT-3's Response to Sensitive Topics and Prompt Wording. (arXiv:2306.06199v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl