natural-language-processing-11

Document Ranking

3260 papers • 126 benchmarks • 313 datasets

Sort documents according to some criterion so that the "best" results appear early in the result list displayed to the user (Source: Wikipedia).

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in document-ranking-22

Trend

Dataset

Best Model

Actions

DaReCzech

ClueWeb09-B

Libraries

i

Use these libraries to find document-ranking-22 models and implementations

oaqa/knn4qa

3 papers 214

Datasets

Subtasks

Session Search

Most implemented papers

XLNet: Generalized Autoregressive Pretraining for Language Understanding

Quoc V. Le, Yiming Yang, R. Salakhutdinov, Zhilin Yang, Zihang Dai, J. Carbonell•Tue Jun 18 2019

XLNet is proposed, a generalized autoregressive pretraining method that enables learning bidirectional contexts by maximizing the expected likelihood over all permutations of the factorization order and overcomes the limitations of BERT thanks to its autore progressive formulation.

9150

Content

oaqa/FlexNeuART

3 papers 214

0

Paper Graph

ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT

M. Zaharia, O. Khattab•Sun Apr 26 2020

ColBERT is presented, a novel ranking model that adapts deep LMs (in particular, BERT) for efficient retrieval that is competitive with existing BERT-based models (and outperforms every non-BERT baseline) and enables leveraging vector-similarity indexes for end-to-end retrieval directly from millions of documents.

1827 0

Paper Graph

CEDR: Contextualized Embeddings for Document Ranking

Sean MacAvaney, Andrew Yates, Arman Cohan, Nazli Goharian•Sun Apr 14 2019

This work investigates how two pretrained contextualized language models (ELMo and BERT) can be utilized for ad-hoc document ranking and proposes a joint approach that incorporates BERT's classification vector into existing neural models and shows that it outperforms state-of-the-art ad-Hoc ranking baselines.

357 0

Paper Graph

Learning deep structured semantic models for web search using clickthrough data

Po-Sen Huang, L. Deng, Jianfeng Gao, Xiaodong He, A. Acero, Larry Heck•Sat Oct 26 2013

A series of new latent semantic models with a deep structure that project queries and documents into a common low-dimensional space where the relevance of a document given a query is readily computed as the distance between them are developed.

2169 0

Paper Graph

Context Attentive Document Ranking and Query Suggestion

Kai-Wei Chang, Wasi Uddin Ahmad, Hongning Wang•Tue Jun 04 2019

A two-level hierarchical recurrent neural network is introduced to learn search context representation of individual queries, search tasks, and corresponding dependency structure by jointly optimizing two companion retrieval tasks: document ranking and query suggestion.

117 0

Paper Graph

Neural vector spaces for unsupervised information retrieval

Van Gysel, de Rijke•Sun Dec 31 2017

This dissertation aims to provide a history of web exceptionalism from 1989 to 2002, a period chosen in order to explore its roots as well as specific cases up to and including the year in which descriptions of “Web 2.0” began to circulate.

77 0

Paper Graph

Simplified TinyBERT: Knowledge Distillation for Document Retrieval

Le Sun, Xuanang Chen, Kai Hui, Ben He, Yingfei Sun•Tue Sep 15 2020

Evaluation on MS MARCO document re-ranking task confirms the effectiveness of the proposed simplifications of TinyBERT, and investigates the applications of knowledge distillation models on document ranking task.

31 0

Paper Graph

The Expando-Mono-Duo Design Pattern for Text Ranking with Pretrained Sequence-to-Sequence Models

Jimmy J. Lin, Ronak Pradeep, Rodrigo Nogueira•Wed Jan 13 2021

A design pattern for tackling text ranking problems, dubbed "Expando-Mono-Duo", that has been empirically validated for a number of ad hoc retrieval tasks in different domains, and implementations of the design are open-sourced in the Pyserini IR toolkit and PyGaggle neural reranking library.

194 0

Paper Graph

Multi-Stage Document Ranking with BERT

Kyunghyun Cho, Jimmy J. Lin, Rodrigo Nogueira, Wei Yang•Wed Oct 30 2019

This work proposes two variants of BERT, called monoBERT and duoBERT, that formulate the ranking problem as pointwise and pairwise classification, respectively, arranged in a multi-stage ranking architecture to form an end-to-end search system.

464 0

Paper Graph

IRGAN: A Minimax Game for Unifying Generative and Discriminative Information Retrieval Models

Benyou Wang, Weinan Zhang, Jun Wang, P. Zhang, Yinghui Xu, Lantao Yu, Yu Gong, Dell Zhang•Mon May 29 2017

A unified framework takes advantage of both schools of thinking in information retrieval modelling and shows that the generative model learns to fit the relevance distribution over documents via the signals from the discriminative model to achieve a better estimation for document ranking.

649 0

Paper Graph

Adding a benchmark result helps the community track progress.