DailyBestPaper
记录每日精选的论文,当然也不是每日啦,就当作一个记录的地方吧~~~
- 每周至少3天刷arxiv订阅邮件!
- 将感兴趣或不错的论文记录下来!
- 精读过的文章标记"⭐"!
- 督促自己每天都有进步!go!go!加油!
2022-05-10
NAACL2022 Prompt相关论文
Template-free Prompt Tuning for Few-shot NER
IDPG: An Instance-Dependent Prompt Generation Method
Automatic Multi-Label Prompting: Simple and Interpretable Few-Shot Classification
ProQA: Structural Prompt-based Pre-training for Unified Question Answering
On Transferability of Prompt Tuning for Natural Language Processing
PROMPT WAYWARDNESS: The Curious Case of Discretized Interpretation of Continuous Prompts
Learning to Transfer Prompts for Text Generation
Learning To Retrieve Prompts for In-Context Learning
Do Prompt-Based Models Really Understand the Meaning of Their Prompts?
Go Back in Time: Generating Flashbacks in Stories with Event Plots and Temporal Prompts
Probing via Prompting and Pruning
Contrastive Learning for Prompt-based Few-shot Language Learners
Using Natural Sentence Prompts for Understanding Biases in Language Models
Zero-Shot Event Detection Based on Ordered Contrastive Learning and Prompt-Based Prediction
LiST: Lite Prompted Self-training Makes Efficient Few-shot Learners
Exploring the Universal Vulnerability of Prompt-based Learning Paradigm
Prompt Augmented Generative Replay via Supervised Contrastive Learning for Lifelong Intent Detection
RGL: A Simple yet Effective Relation Graph Augmented Prompt-based Tuning Approach for Few-Shot Learning
On Measuring Social Biases in Prompt-Based Learning
Few-Shot Self-Rationalization with Natural Language Prompts
SEQZERO: Few-shot Compositional Semantic Parsing with Sequential Prompts and Zero-shot Models
PromptGen: Automatically Generate Prompts using Generative Models
2022-04-27
sigir2022论文
检索排序相关
RankFlow: Joint Optimization of Multi-Stage Cascade Ranking Systems as Flows
Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking
IR Evaluation and Learning in the Presence of Forbidden Documents
Incorporating Retrieval Information into the Truncation of Ranking Lists in the Legal Domain
Webformer: Pre-training with Web Pages for Information Retrieval
Automatic Expert Selection for Multi-Scenario and Multi-Task Search
CharacterBERT and Self-Teaching for Improving the Robustness of Dense Retrievers on Queries with Typos
H-ERNIE: A Hierarchical Multi-Granularity Pre-Trained Language Model for Chinese Search Engine
Interpreting Patient Descriptions using Distantly Supervised Similar Case Retrieval
Axiomatically Regularized Pre-training for Ad hoc Search
Entity-aware Transformers for Entity Search
Pre-train a Discriminative Text Encoder for Dense Retrieval via Contrastive Span Prediction
Faster Learned Sparse Retrieval with Guided Traversal
P^3 Ranker: Mitigating the Gaps between Pre-training and Ranking Fine-tuning with Prompt-based Learning and Pre-finetuning
Curriculum Learning for Dense Retrieval Distillation
Analysing the Robustness of Dual Encoders for Dense Retrieval Against Misspellings
From Cluster Ranking to Document Ranking
How does Feedback Signal Quality Impact Effectiveness of Pseudo Relevance Feedback for Passage Retrieval
Improving Contrastive Learning of Sentence Embeddings with Case-Augmented Positives and Retrieved Negatives
GERE: Generative Evidence Retrieval for Fact Verification
Learning to Rank Knowledge Sub-Graph Nodes for Entity Retrieval
BERT-based Dense Intra-ranking and Contextualized Late Interaction via Multi-task Learning for Long Document Retrieval
From Distillation to Hard Negative Sampling: Making Sparse Neural IR Models More Effective
Long Document Re-ranking with Modular Re-ranker
Unsupervised Dataset Generation for Information Retrieval
On Optimizing Top-K Metrics for Neural Ranking Models
Alignment Rationale for Query-Document
To interpolate or not to interpolate: PRF, Dense Retrievers and BM25
C3: Continued Pretraining with Contrastive Weak Supervision for Cross Language Ad-Hoc Retrieval
小样本
Curriculum Contrastive Context Denoising for Few-shot Conversational Dense Retrieval
Recognizing Medical Search Query Intent by Few-shot Learning
Zero-shot Query Contextualization for Conversational Search
Relation-Guided Few-Shot Relational Triple Extraction
Multi-labels Masked Language Modeling on Zero-shot Code-switched Sentiment Analysis
多模态相关
Hybrid Transformer with Multi-level Fusion for Multimodal Knowledge Graph Completion
Learn from Unlabeled Videos for Near-duplicate Video Retrieval
Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation
V2P: Vision-to-Prompt based Multi-Modal Product Summary Generation
CenterCLIP: Token Clustering for Efficient Text-Video Retrieval
Multimodal Entity Linking with Gated Hierarchical Fusion and Contrastive Training
Bit-aware Semantic Transformer Hashing for Multi-modal Retrieval
Multimodal Disentanglement Variational AutoEncoders for Zero-Shot Cross-Modal Retrieval
Animating Images to transfer CLIP for Video-Text Retrieval
Image-Text Retrieval via Contrastive Learning with Auxiliary Generative Features and Support-set Regularization
Cross-Probe BERT for Fast Cross-Modal Search
生成
Mutual Disentanglement Learning for Joint Fine-Grained Sentiment Classification and Controllable Text Generation
Target-aware Abstractive Related Work Generation with Contrastive Learning
Generating Clarifying Questions with Web Search Results
Task-Oriented Dialogue System as Natural Language Generation
Entity-Conditioned Question Generation for Robust Attention Distribution in Neural Information Retrieval
摘要
ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge Disentanglement
On Extractive Summarization for Profile-centric Neural Expert Search in Academia
QSG Transformer: Transformer with Query-Attentive Semantic Graph for Query-Focused Summarization
MuchSUM: Multi-channel Graph Neural Network for Extractive Summarization
Lightweight Meta-Learning for Low-Resource Abstractive Summarization
Extractive Elementary Discourse Units for Improving Abstractive Summarization
Summarizing Legal Regulatory Documents using Transformers
文本表征
Structure and Semantics Preserving Document Representations
Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders
CRET: Cross-Modal Retrieval Transformer for Efficient Text-Video Retrieval
BERT-ER: Query-Specific BERT Entity Representations for Entity Ranking
Adaptable Text Matching via Meta-Weight Regulator
Re-weighting Negative Samples for Model-Agnostic Matching
Learned Token Pruning in Contextualized Late Interaction over BERT (ColBERT)
问答
PTAU: Prompt Tuning for Attributing Unanswerable Questions
DGQAN: Dual Graph Question-Answer Attention Networks for Answer Selection
Conversational Question Answering on Heterogeneous Sources
QUASER: Question Answering with Scalable Extractive Rationalization
Detecting Frozen Phrases in Open-Domain Question Answering
其他
Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning
LoL: A Comparative Regularization Loss over Query Reformulation Losses for Pseudo-Relevance Feedback
A Dual-Expert Framework for Event Argument Extraction
Aspect Feature Distillation and Enhancement Network for Aspect-based Sentiment Analysis
IAOTP: An Interactive End-to-End Solution for Aspect-Opinion Term Pairs Extraction
Relation Extraction as Open-book Examination: Retrieval-enhanced Prompt Tuning
Training Entire-Space Models for Target-oriented Opinion Words Extraction
A Robust Computerized Adaptive Testing Approach in Educational Question Retrieval
Hierarchical Task-aware Multi-Head Attention Network
Enhancing Event-Level Sentiment Analysis with Structured Arguments
End-to-end Distantly Supervised Information Extraction with Retrieval Augmentation
资源
A Dataset for Sentence Retrieval for Open-Ended Dialogues
ReMeDi: Resources for Multi-domain, Multi-service, Medical Dialogues
Multi-CPR: A Multi Domain Chinese Dataset for Passage Retrieva
2022-02-09
LST: Lexicon-Guided Self-Training for Few-Shot Text Classification
Comparison and Combination of Sentence Embeddings Derived from Different Supervision Signals
To Tune or Not To Tune? Zero-shot Models for Legal Case Entailment
2022-02-08
Zero-Shot Aspect-Based Sentiment Analysis
A Benchmark Corpus for the Detection of Automatically Generated Text in Academic Publications
From Discrimination to Generation: Knowledge Graph Completion with Generative Transformer
2022-02-06
PromptSource: An Integrated Development Environment and Repository for Natural Language Prompts⭐
mSLAM: Massively multilingual joint pre-training for speech and text
2022-02-04
Pre-Trained Language Transformers are Universal Image Classifiers
Improving the fusion of acoustic and text representations in RNN-T
A Survey on Retrieval-Augmented Text Generation⭐
Natural Language to Code Using Transformers
Novelty Controlled Paraphrase Generation with Retrieval Augmented Conditional Prompt Tuning
Improving BERT-based Query-by-Document Retrieval with Multi-Task Optimization
Commonsense Knowledge Reasoning and Generation with Pre-trained Language Models: A Survey
A Simple Information-Based Approach to Unsupervised Domain-Adaptive Aspect-Based Sentiment Analysis
Unsupervised Summarization with Customized Granularities
Clinical-Longformer and Clinical-BigBird
PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddings
Protum: A New Method For Prompt Tuning Based on "[MASK]"⭐
DiscoScore: Evaluating Text Generation with BERT and Discourse Coherence
2022-02-02
Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation
Context-Tuning: Learning Contextualized Prompts for Natural Language Generation
Black-box Prompt Learning for Pre-trained Language Models
SciBERTSUM: Extractive Summarization for Scientific Documents⭐
ZeroPrompt: Scaling Prompt-Based Pretraining to 1,000 Tasks Improves Zero-Shot Generalization⭐
CLIP-TD: CLIP Targeted Distillation for Vision-Language Tasks
Double Retrieval and Ranking for Accurate Question Answering
Improving Biomedical Information Retrieval with Neural Retrievers
PromptBERT: Improving BERT Sentence Embeddings with Prompts⭐
The Dark Side of the Language: Pre-trained Transformers in the DarkNet
AugLy: Data Augmentations for Robustness⭐
Eliciting Knowledge from Pretrained Language Models for Prototypical Prompt Verbalizer