Show newer

From Zero to Hero: Harnessing Transformers for Biomedical Named Entity Recognition in Zero- and Few-shot Contexts. (arXiv:2305.04928v3 [cs.CL] UPDATED) 

A Dual Semantic-Aware Recurrent Global-Adaptive Network For Vision-and-Language Navigation. (arXiv:2305.03602v2 [cs.CV] UPDATED) 

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs. (arXiv:2305.03111v2 [cs.CL] UPDATED) 

Towards Weakly-Supervised Hate Speech Classification Across Datasets. (arXiv:2305.02637v2 [cs.CL] UPDATED) 

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model. (arXiv:2305.00586v3 [cs.CL] UPDATED) 

Still no evidence for an effect of the proportion of non-native speakers on language complexity -- A response to Kauhanen, Einhaus & Walkden (2023). (arXiv:2305.00217v6 [cs.CL] UPDATED) 

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers. (arXiv:2304.09116v3 [eess.AS] UPDATED) 

Efficient Sequence Transduction by Jointly Predicting Tokens and Durations. (arXiv:2304.06795v2 [eess.AS] UPDATED) 

BenCoref: A Multi-Domain Dataset of Nominal Phrases and Pronominal Reference Annotations. (arXiv:2304.03682v2 [cs.CL] UPDATED) 

ContraSim -- A Similarity Measure Based on Contrastive Learning. (arXiv:2303.16992v2 [cs.CL] UPDATED) 

Analyzing the Performance of GPT-3.5 and GPT-4 in Grammatical Error Correction. (arXiv:2303.14342v2 [cs.CL] UPDATED) 

CB2: Collaborative Natural Language Interaction Research Platform. (arXiv:2303.08127v3 [cs.LG] UPDATED) 

Unsupervised Layer-wise Score Aggregation for Textual OOD Detection. (arXiv:2302.09852v2 [cs.CL] UPDATED) 

Pre-training for Speech Translation: CTC Meets Optimal Transport. (arXiv:2301.11716v2 [cs.CL] UPDATED) 

Parameter-Efficient Low-Resource Dialogue State Tracking by Prompt Tuning. (arXiv:2301.10915v2 [cs.CL] UPDATED) 

Continual Contrastive Finetuning Improves Low-Resource Relation Extraction. (arXiv:2212.10823v2 [cs.CL] UPDATED) 

4D ASR: Joint modeling of CTC, Attention, Transducer, and Mask-Predict decoders. (arXiv:2212.10818v2 [cs.SD] UPDATED) 

ORCA: A Challenging Benchmark for Arabic Language Understanding. (arXiv:2212.10758v2 [cs.CL] UPDATED) 

Semantically-informed Hierarchical Event Modeling. (arXiv:2212.10547v2 [cs.CL] UPDATED) 

When Not to Trust Language Models: Investigating Effectiveness of Parametric and Non-Parametric Memories. (arXiv:2212.10511v3 [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.