XATU: A Fine-grained Instruction-based Benchmark for Explainable Text Updates. (arXiv:2309.11063v1 [cs.CL])
Design of Chain-of-Thought in Math Problem Solving. (arXiv:2309.11054v1 [cs.CL])
Fake News BR: A Fake News Detection Platform for Brazilian Portuguese. (arXiv:2309.11052v1 [cs.CL])
Localize, Retrieve and Fuse: A Generalized Framework for Free-Form Question Answering over Tables. (arXiv:2309.11049v1 [cs.CL])
Heterogeneous Entity Matching with Complex Attribute Associations using BERT and Neural Networks. (arXiv:2309.11046v1 [cs.CL])
Making Small Language Models Better Multi-task Learners with Mixture-of-Task-Adapters. (arXiv:2309.11042v1 [cs.CL])
Named Entity Recognition via Machine Reading Comprehension: A Multi-Task Learning Approach. (arXiv:2309.11027v1 [cs.CL])
Towards Joint Modeling of Dialogue Response and Speech Synthesis based on Large Language Model. (arXiv:2309.11000v1 [cs.CL])
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods. (arXiv:2309.10966v1 [cs.CL])
In-Context Learning for Text Classification with Many Labels. (arXiv:2309.10954v1 [cs.CL])
LMDX: Language Model-based Document Information Extraction and Localization. (arXiv:2309.10952v1 [cs.CL])
Benchmarks for Pir\'a 2.0, a Reading Comprehension Dataset about the Ocean, the Brazilian Coast, and Climate Change. (arXiv:2309.10945v1 [cs.CL])
A Family of Pretrained Transformer Language Models for Russian. (arXiv:2309.10931v1 [cs.CL])
Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training. (arXiv:2309.10929v1 [cs.CL])
Semi-Autoregressive Streaming ASR With Label Context. (arXiv:2309.10926v1 [cs.CL])
Semi-automatic staging area for high-quality structured data extraction from scientific literature. (arXiv:2309.10923v1 [cs.CL])
End-to-End Speech Recognition Contextualization with Large Language Models. (arXiv:2309.10917v1 [eess.AS])
What Learned Representations and Influence Functions Can Tell Us About Adversarial Examples. (arXiv:2309.10916v1 [cs.LG])
RedPenNet for Grammatical Error Correction: Outputs to Tokens, Attentions to Spans. (arXiv:2309.10898v1 [cs.CL])
Self-Augmentation Improves Zero-Shot Cross-Lingual Transfer. (arXiv:2309.10891v1 [cs.CL])
All recent Computation and Language articles on arXiv.org for the Fediverse
Inspired by https://twitter.com/arxiv_cscl