Show newer

Toward Efficient Language Model Pretraining and Downstream Adaptation via Self-Evolution: A Case Study on SuperGLUE. (arXiv:2212.01853v1 [cs.CL]) 

Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction. (arXiv:2212.01844v1 [cs.CL]) 

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation. (arXiv:2212.01810v1 [cs.CL]) 

An LSTM model for Twitter Sentiment Analysis. (arXiv:2212.01791v1 [cs.CL]) 

MiLMo:Minority Multilingual Pre-trained Language Model. (arXiv:2212.01779v1 [cs.CL]) 

Improving End-to-end Speech Translation by Leveraging Auxiliary Speech and Text Data. (arXiv:2212.01778v1 [eess.AS]) 

Languages You Know Influence Those You Learn: Impact of Language Characteristics on Multi-Lingual Text-to-Text Transfer. (arXiv:2212.01757v1 [cs.CL]) 

KPT: Keyword-guided Pre-training for Grounded Dialog Generation. (arXiv:2212.01739v1 [cs.CL]) 

Linguistic Constructs as the Representation of the Domain Model in an Intelligent Language Tutoring System. (arXiv:2212.01711v1 [cs.CL]) 

Towards Robust NLG Bias Evaluation with Syntactically-diverse Prompts. (arXiv:2212.01700v1 [cs.CL]) 

What is Not in the Context? Evaluation of Few-shot Learners with Informative Demonstrations. (arXiv:2212.01692v1 [cs.CL]) 

Language Models as Agent Models. (arXiv:2212.01681v1 [cs.CL]) 

A Survey on Medical Document Summarization. (arXiv:2212.01669v1 [cs.CL]) 

T-STAR: Truthful Style Transfer using AMR Graph as Intermediate Representation. (arXiv:2212.01667v1 [cs.CL]) 

Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models. (arXiv:2212.01661v1 [eess.AS]) 

Global memory transformer for processing long documents. (arXiv:2212.01650v1 [cs.CL]) 

Intermediate Entity-based Sparse Interpretable Representation Learning. (arXiv:2212.01641v1 [cs.CL]) 

Named Entity and Relation Extraction with Multi-Modal Retrieval. (arXiv:2212.01612v1 [cs.CL]) 

CoP: Factual Inconsistency Detection by Controlling the Preference. (arXiv:2212.01611v1 [cs.CL]) 

RHO ($\rho$): Reducing Hallucination in Open-domain Dialogues with Knowledge Grounding. (arXiv:2212.01588v1 [cs.CL]) 

Show older
Qoto Mastodon

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