Picture for Tianda Li

Tianda Li

SPDF: Sparse Pre-training and Dense Fine-tuning for Large Language Models

Add code
Mar 18, 2023
Viaarxiv icon

Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models

Add code
May 25, 2022
Figure 1 for Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models
Figure 2 for Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models
Figure 3 for Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models
Figure 4 for Towards Understanding Label Regularization for Fine-tuning Pre-trained Language Models
Viaarxiv icon

A Short Study on Compressing Decoder-Based Language Models

Add code
Oct 16, 2021
Figure 1 for A Short Study on Compressing Decoder-Based Language Models
Figure 2 for A Short Study on Compressing Decoder-Based Language Models
Figure 3 for A Short Study on Compressing Decoder-Based Language Models
Figure 4 for A Short Study on Compressing Decoder-Based Language Models
Viaarxiv icon

How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding

Add code
Sep 20, 2021
Figure 1 for How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
Figure 2 for How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
Figure 3 for How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
Figure 4 for How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding
Viaarxiv icon

Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference

Add code
Sep 08, 2021
Figure 1 for Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
Figure 2 for Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
Figure 3 for Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
Figure 4 for Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference
Viaarxiv icon

Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems

Add code
Dec 22, 2020
Figure 1 for Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Figure 2 for Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Figure 3 for Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Figure 4 for Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems
Viaarxiv icon

DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement

Add code
Apr 08, 2020
Figure 1 for DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
Figure 2 for DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
Figure 3 for DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
Figure 4 for DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement
Viaarxiv icon

Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots

Add code
Apr 07, 2020
Figure 1 for Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Figure 2 for Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Figure 3 for Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Figure 4 for Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
Viaarxiv icon

Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems

Add code
Apr 04, 2020
Figure 1 for Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
Figure 2 for Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
Figure 3 for Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
Figure 4 for Pre-Trained and Attention-Based Neural Networks for Building Noetic Task-Oriented Dialogue Systems
Viaarxiv icon

Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference

Add code
Apr 27, 2019
Figure 1 for Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Figure 2 for Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Figure 3 for Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Figure 4 for Several Experiments on Investigating Pretraining and Knowledge-Enhanced Models for Natural Language Inference
Viaarxiv icon