research
∙
05/26/2023
DataFinder: Scientific Dataset Recommendation from Natural Language Descriptions
Modern machine learning relies on datasets to develop and validate resea...
share
research
∙
05/11/2023
Active Retrieval Augmented Generation
Despite the remarkable ability of large language models (LMs) to compreh...
research
∙
03/30/2023
Self-Refine: Iterative Refinement with Self-Feedback
Like people, LLMs do not always generate the best text for a given gener...
research
∙
12/20/2022
Precise Zero-Shot Dense Retrieval without Relevance Labels
While dense retrieval has been shown effective and efficient across task...
research
∙
12/05/2022
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer
Systems for knowledge-intensive tasks such as open-domain question answe...
research
∙
11/18/2022
PAL: Program-aided Language Models
Large language models (LLMs) have recently demonstrated an impressive ab...
research
∙
10/17/2022
RARR: Researching and Revising What Language Models Say, Using Language Models
Language models (LMs) now excel at many tasks such as few-shot learning,...
research
∙
05/09/2022
Long Document Re-ranking with Modular Re-ranker
Long document re-ranking has been a challenging problem for neural re-ra...
research
∙
03/11/2022
Tevatron: An Efficient and Flexible Toolkit for Dense Retrieval
Recent rapid advancements in deep pre-trained language models and the in...
research
∙
08/12/2021
Unsupervised Corpus Aware Language Model Pre-training for Dense Passage Retrieval
Recent research demonstrates the effectiveness of using fine-tuned langu...
research
∙
04/16/2021
Is Your Language Model Ready for Dense Representation Fine-tuning?
Pre-trained language models (LM) have become go-to text representation e...
research
∙
04/15/2021
COIL: Revisit Exact Lexical Match in Information Retrieval with Contextualized Inverted List
Classical information retrieval systems such as BM25 rely on exact lexic...
research
∙
01/21/2021
Rethink Training of BERT Rerankers in Multi-Stage Retrieval Pipeline
Pre-trained deep language models (LM) have advanced the state-of-the-art...
research
∙
01/18/2021
Scaling Deep Contrastive Learning Batch Size with Almost Constant Peak Memory Usage
Contrastive learning has been applied successfully to learn numerical ve...
research
∙
10/04/2020
Improving Target-side Lexical Transfer in Multilingual Neural Machine Translation
To improve the performance of Neural Machine Translation (NMT) for low-r...
research
∙
07/21/2020
Understanding BERT Rankers Under Distillation
Deep language models such as BERT pre-trained on large corpus have given...
research
∙
04/29/2020
Complementing Lexical Retrieval with Semantic Residual Embedding
Information retrieval traditionally has relied on lexical matching signa...
research
∙
04/28/2020