https://github.com/amazon-science/synthesizrr
공식 코드SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
Information retrieval is the task of ranking a list of documents or search results in response to a query
<span style="color:grey; opacity: 0.6">( Image credit: sudhanshumittal )</span>
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
SynthesizRR: Generating Diverse Datasets with Retrieval Augmentation
EMPRA: Embedding Perturbation Rank Attack against Neural Ranking Models
RouterRetriever: Routing over a Mixture of Expert Embedding Models
Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging
LLM2KB: Constructing Knowledge Bases using instruction tuned context aware Large Language Models
Topological Information Retrieval with Dilation-Invariant Bottleneck Comparative Measures
Symbolic Music Representations for Classification Tasks: A Systematic Evaluation
Open-Domain Question Answering Goes Conversational via Question Rewriting
MILL: Mutual Verification with Large Language Models for Zero-Shot Query Expansion
Evaluating Token-Level and Passage-Level Dense Retrieval Models for Math Information Retrieval
A Comparison of Supervised Learning to Match Methods for Product Search
Towards Trustworthy Reranking: A Simple yet Effective Abstention Mechanism
Rational Retrieval Acts: Leveraging Pragmatic Reasoning to Improve Sparse Retrieval
Coreference Resolution in Research Papers from Multiple Domains
DebateSum: A large-scale argument mining and summarization dataset
An Empirical Comparison of LM-based Question and Answer Generation Methods
HybridCite: A Hybrid Model for Context-Aware Citation Recommendation
HybridCite: A Hybrid Model for Context-Aware Citation Recommendation
Improved IR-based Bug Localization with Intelligent Relevance Feedback
Rank over Class: The Untapped Potential of Ranking in Natural Language Processing
Why These Documents? Explainable Generative Retrieval with Hierarchical Category Paths
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.