Show newer

FactKB: Generalizable Factuality Evaluation using Language Models Enhanced with Factual Knowledge. (arXiv:2305.08281v2 [cs.CL] UPDATED) 

Automatic Prompt Optimization with "Gradient Descent" and Beam Search. (arXiv:2305.03495v2 [cs.CL] UPDATED) 

PEFT-Ref: A Modular Reference Architecture and Typology for Parameter-Efficient Finetuning Techniques. (arXiv:2304.12410v2 [cs.CL] UPDATED) 

Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study. (arXiv:2304.06762v2 [cs.CL] UPDATED) 

MWE as WSD: Solving Multiword Expression Identification with Word Sense Disambiguation. (arXiv:2303.06623v2 [cs.CL] UPDATED) 

Test-Time Distribution Normalization for Contrastively Learned Vision-language Models. (arXiv:2302.11084v2 [cs.LG] UPDATED) 

PK-ICR: Persona-Knowledge Interactive Context Retrieval for Grounded Dialogue. (arXiv:2302.06674v3 [cs.CL] UPDATED) 

NNKGC: Improving Knowledge Graph Completion with Node Neighborhoods. (arXiv:2302.06132v3 [cs.CL] UPDATED) 

IC3: Image Captioning by Committee Consensus. (arXiv:2302.01328v3 [cs.CV] UPDATED) 

Can NLI Provide Proper Indirect Supervision for Low-resource Biomedical Relation Extraction?. (arXiv:2212.10784v3 [cs.CL] UPDATED) 

Speaking Style Conversion in the Waveform Domain Using Discrete Self-Supervised Units. (arXiv:2212.09730v2 [cs.SD] UPDATED) 

A Retrieve-and-Read Framework for Knowledge Graph Link Prediction. (arXiv:2212.09724v2 [cs.CL] UPDATED) 

Large Language Models are Better Reasoners with Self-Verification. (arXiv:2212.09561v5 [cs.AI] UPDATED) 

Exploiting Contrastive Learning and Numerical Evidence for Improving Confusing Legal Judgment Prediction. (arXiv:2211.08238v2 [cs.CL] UPDATED) 

Reinforcement Learning and Bandits for Speech and Language Processing: Tutorial, Review and Outlook. (arXiv:2210.13623v3 [cs.AI] UPDATED) 

Can Brain Signals Reveal Inner Alignment with Human Languages?. (arXiv:2208.06348v4 [q-bio.NC] UPDATED) 

Learning to translate by learning to communicate. (arXiv:2207.07025v2 [cs.CL] UPDATED) 

Dict-TTS: Learning to Pronounce with Prior Dictionary Knowledge for Text-to-Speech. (arXiv:2206.02147v3 [eess.AS] UPDATED) 

Towards Automatic Construction of Filipino WordNet: Word Sense Induction and Synset Induction Using Sentence Embeddings. (arXiv:2204.03251v3 [cs.CL] UPDATED) 

Example-based Hypernetworks for Out-of-Distribution Generalization. (arXiv:2203.14276v3 [cs.CL] UPDATED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.