每日阅读论文记录
9 月
| 日期 |
标题 |
备注 |
| 09/15 |
A Short Review: Deep Retrieval-Based Dialogue Systems |
|
| 09/16 |
Improved Deep Learning Baselines for Ubuntu Corpus Dialogs |
UDC |
| 09/16 |
Sequential Attention-based Network for Noetic End-to-End Response Selection |
ESIM |
| 09/23 |
Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks |
SBERT |
| 09/24 |
Augmented SBERT: Data Augmentation Method for Improving Bi-Encoders for Pairwise Sentence Scoring Tasks |
|
| 09/25 |
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data |
InferSent |
| 09/26 |
Learning Semantic Textual Similarity from Conversations |
USE |
| 09/27 |
A SIMPLE BUT TOUGH-TO-BEAT BASELINE FOR SENTENCE EMBEDDINGS (undone) |
|
| 09/27 |
An Effective Domain Adaptive Post-Training Method for BERT in Response Selection |
BERT-VFT |
| 09/28 |
Sequential Matching Network: A New Architecture for Multi-turn Response Selection in Retrieval-Based Chatbots |
SMN |
| 09/29 |
APPLYING DEEP LEARNING TO ANSWER SELECTION: A STUDY AND AN OPEN TASK |
Siam-CNN |
10 月
| 日期 |
标题 |
备注 |
| 10/06 |
Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues |
BERT-SL |
| 10/07 |
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing |
|
| 10/08 |
Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference |
PET |
| 10/09 |
GPT Understands, Too |
P-Tuning |
| 10/09 |
SimCSE: Simple Contrastive Learning of Sentence Embeddings |
SimCSE |
| 10/10 |
Structural Pre-training for Dialogue Comprehension |
SPIDER |
| 10/11 |
What Makes for Good Views for Contrastive Learning? |
|
| 10/21 |
ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer |
ConSERT |
| 10/23 |
Fine-grained Post-training for Improving Retrieval-based Dialogue Systems |
BERT-FP |
| 10/26 |
SEMANTIC RE-TUNING WITH CONTRASTIVE TENSION |
CT |
| 10/27 |
PRE-TRAINING TASKS FOR EMBEDDING-BASED LARGE-SCALE RETRIEVAL |
|
11 月
| 日期 |
标题 |
备注 |
| 11/3 |
Building an Efficient and Effective Retrieval-based Dialogue System |
BE/CE |
12 月
才发现自己已经摆烂一个多月了。接下来重点放在代码实现上，读完论文一定要看代码。
| 日期 |
标题 |
备注 |
| 12/6 |
Prompt Tuning Can Be Comparable to Fine-tuning Universally Across Scales and Tasks |
P-Tuning v2 |