Zero-shot Text Search
14 papers with code • 18 benchmarks • 16 datasets
Benchmarks
These leaderboards are used to track progress in Zero-shot Text Search
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Zero-shot Text Search models and implementationsDatasets
Natural Questions
DBpedia
FEVER
BEIR
BioASQ
SciFact
SciDocs
Most implemented papers
Approximate Nearest Neighbor Negative Contrastive Learning for Dense Text Retrieval
In this paper, we identify that the main bottleneck is in the training mechanisms, where the negative instances used in training are not representative of the irrelevant documents in testing.
GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval
ukplab/gpl
•
•
NAACL 2022
This limits the usage of dense retrieval approaches to only a few domains with large training datasets.
Efficiently Teaching an Effective Dense Retriever with Balanced Topic Aware Sampling
A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows.
ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction
stanford-futuredata/ColBERT
•
•
NAACL 2022
Neural information retrieval (IR) has greatly advanced search and other knowledge-intensive language tasks.
BM25S: Orders of magnitude faster lexical search via eager sparse scoring
xhluca/bm25s
•
•
We introduce BM25S, an efficient Python-based implementation of BM25 that only depends on Numpy and Scipy.
SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval
naver/splade
•
•
Meanwhile, there has been a growing interest in learning \emph{sparse} representations for documents and queries, that could inherit from the desirable properties of bag-of-words models such as the exact matching of terms and the efficiency of inverted indexes.
Large Dual Encoders Are Generalizable Retrievers
google-research/t5x_retrieval
•
•
With multi-stage training, surprisingly, scaling up the model size brings significant improvement on a variety of retrieval tasks, especially for out-of-domain generalization.
Zero-Shot Question Generation from Knowledge Graphs for Unseen Predicates and Entity Types
We present a neural model for question generation from knowledge base triples in a "Zero-Shot" setup, that is generating questions for triples containing predicates, subject types or object types that were not seen at training time.
MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers
microsoft/unilm
•
•
NeurIPS 2020
The small model (student) is trained by deeply mimicking the self-attention module, which plays a vital role in Transformer networks, of the large model (teacher).
Text and Code Embeddings by Contrastive Pre-Training
Similarly to text embeddings, we train code embedding models on (text, code) pairs, obtaining a 20. 8% relative improvement over prior best work on code search.
