Show newer

G-MAP: General Memory-Augmented Pre-trained Language Model for Domain Tasks. (arXiv:2212.03613v1 [cs.CL]) 

Tag Embedding and Well-defined Intermediate Representation improve Auto-Formulation of Problem Description. (arXiv:2212.03575v1 [cs.CL]) 

Low-Resource End-to-end Sanskrit TTS using Tacotron2, WaveGlow and Transfer Learning. (arXiv:2212.03558v1 [cs.CL]) 

Talking About Large Language Models. (arXiv:2212.03551v1 [cs.CL]) 

Text Embeddings by Weakly-Supervised Contrastive Pre-training. (arXiv:2212.03533v1 [cs.CL]) 

WIDER & CLOSER: Mixture of Short-channel Distillers for Zero-shot Cross-lingual Named Entity Recognition. (arXiv:2212.03506v1 [cs.CL]) 

A Generative Approach for Script Event Prediction via Contrastive Fine-tuning. (arXiv:2212.03496v1 [cs.CL]) 

Improved Self-Supervised Multilingual Speech Representation Learning Combined with Auxiliary Language Information. (arXiv:2212.03476v1 [eess.AS]) 

Improve Bilingual TTS Using Dynamic Language and Phonology Embedding. (arXiv:2212.03435v1 [cs.SD]) 

JamPatoisNLI: A Jamaican Patois Natural Language Inference Dataset. (arXiv:2212.03419v1 [cs.CL]) 

Towards using Few-Shot Prompt Learning for Automating Model Completion. (arXiv:2212.03404v1 [cs.SE]) 

Analysis and Utilization of Entrainment on Acoustic and Emotion Features in User-agent Dialogue. (arXiv:2212.03398v1 [eess.AS]) 

KATSum: Knowledge-aware Abstractive Text Summarization. (arXiv:2212.03371v1 [cs.CL]) 

Fine-Grained Emotional Paraphrasing along Emotion Gradients. (arXiv:2212.03297v1 [cs.CL]) 

Cheater's Bowl: Human vs. Computer Search Strategies for Open-Domain Question Answering. (arXiv:2212.03296v1 [cs.CL]) 

From Knowledge Augmentation to Multi-tasking: Towards Human-like Dialogue Systems. (arXiv:2212.03279v1 [cs.AI]) 

Counterfactual reasoning: Do language models need world knowledge for causal understanding?. (arXiv:2212.03278v1 [cs.CL]) 

Analysis of Utterance Embeddings and Clustering Methods Related to Intent Induction for Task-Oriented Dialogue. (arXiv:2212.02021v2 [cs.CL] UPDATED) 

Orders Are Unwanted: Dynamic Deep Graph Convolutional Network for Personality Detection. (arXiv:2212.01515v2 [cs.CL] UPDATED) 

Transformers are Short Text Classifiers: A Study of Inductive Short Text Classifiers on Benchmarks and Real-world Datasets. (arXiv:2211.16878v2 [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.