A General-Purpose Multilingual Document Encoder. (arXiv:2305.07016v1 [cs.CL])
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers. (arXiv:2305.07011v1 [cs.CV])
Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation. (arXiv:2305.07005v1 [cs.CL])
Not All Languages Are Created Equal in LLMs: Improving Multilingual Capability by Cross-Lingual-Thought Prompting. (arXiv:2305.07004v1 [cs.CL])
Recommendation as Instruction Following: A Large Language Model Empowered Recommendation Approach. (arXiv:2305.07001v1 [cs.IR])
SMATCH++: Standardized and Extended Evaluation of Semantic Graphs. (arXiv:2305.06993v1 [cs.CL])
Self-Chained Image-Language Model for Video Localization and Question Answering. (arXiv:2305.06988v1 [cs.CV])
Evaluating Open-Domain Question Answering in the Era of Large Language Models. (arXiv:2305.06984v1 [cs.CL])
Active Retrieval Augmented Generation. (arXiv:2305.06983v1 [cs.CL])
Humans are Still Better than ChatGPT: Case of the IEEEXtreme Competition. (arXiv:2305.06934v1 [cs.SE])
CoMoSpeech: One-Step Speech and Singing Voice Synthesis via Consistency Model. (arXiv:2305.06908v1 [cs.SD])
AfriQA: Cross-lingual Open-Retrieval Question Answering for African Languages. (arXiv:2305.06897v1 [cs.CL])
IUST_NLP at SemEval-2023 Task 10: Explainable Detecting Sexism with Transformers and Task-adaptive Pretraining. (arXiv:2305.06892v1 [cs.CL])
WebCPM: Interactive Web Search for Chinese Long-form Question Answering. (arXiv:2305.06849v1 [cs.CL])
Think Twice: Measuring the Efficiency of Eliminating Prediction Shortcuts of Question Answering Models. (arXiv:2305.06841v1 [cs.CL])
Towards a Computational Analysis of Suspense: Detecting Dangerous Situations. (arXiv:2305.06818v1 [cs.CL])
THUIR@COLIEE 2023: More Parameters and Legal Knowledge for Legal Case Entailment. (arXiv:2305.06817v1 [cs.CL])
THUIR@COLIEE 2023: Incorporating Structural Knowledge into Pre-trained Language Models for Legal Case Retrieval. (arXiv:2305.06812v1 [cs.IR])
Detecting Idiomatic Multiword Expressions in Clinical Terminology using Definition-Based Representation Learning. (arXiv:2305.06801v1 [cs.CL])
COCKATIEL: COntinuous Concept ranKed ATtribution with Interpretable ELements for explaining neural net classifiers on NLP tasks. (arXiv:2305.06754v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl