Co-PACRR: A Context-Aware Neural IR Model for Ad-hoc Retrieval

By Kai Hui, Andrew Yates, Klaus Berberich, Gerard de Melo. 2017

125 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Information Systems, Information Retrieval & Search

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Information Systems

In Information Retrieval & Search

Citations in the corpus

Passage Re-ranking with BERT (2019, methodology): “The information retrieval (IR) community has also experienced a ﬂourishing development of neural ranking models, such as DRMM (Guo et al., 2016), KNRM (Xiong et al., 2017), Co-PACRR (Hui et al., 2018), and DUET (Mitra et al., 2017).”
Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “Following Humeau et al. [2019], several roughly contemporaneous works closely followed.”
Document Ranking with a Pretrained Sequence-to-Sequence Model (2020, background): “, 2017), and CoPACRR (Hui et al., 2018); the literature is too vast for an exhaustive review here, and thus we refer readers to past overviews (Onal et al.”
Multi-Stage Document Ranking with BERT (2019, methodology): “Well-known neural ranking models include DRMM (Guo et al., 2016), DUET (Mitra et al., 2017), KNRM (Xiong et al., 2017), and Co-PACRR (Hui et al., 2018); the literature is too vast for an exhaustive review here, and thus we refer readers to recent overviews (Onal et al., 2018; Mitra and Craswell,…”
CEDR: Contextualized Embeddings for Document Ranking (2019, methodology): “We show the runtime and ranking performance of PACRR when only processing a certain number of layers in Figure 2(b).”
NPRF: A Neural Pseudo Relevance Feedback Framework for Ad-hoc Information Retrieval (2018, methodology): “These changes lead to a small but competitive K-NRM variant, as demonstrated in (Hui et al., 2018).”
TU Wien @ TREC Deep Learning '19 - Simple Contextualization for Re-ranking (2019, methodology): “This makes TK more powerful than previous local-only contextualization methods used in CONV-KNRM [2] and CO-PACRR [7].”
Local Self-Attention over Long Text for Efficient Document Retrieval (2020, unknown): “286 22 d CO-PACRR [13] 200 e0.”
AUEB at BioASQ 7: Document and Snippet Retrieval (2019, background): “Neural document ranking models [7, 9, 10, 17, 18] have only recently managed to improve upon the rankings of traditional ir systems (e.”
Interpretable & Time-Budget-Constrained Contextualization for Re-Ranking (2020, methodology): “This makes TK more powerful than previous local-only contextualization methods used in CONV-KNRM [5] and CO-PACRR [16].”
Rethinking Search: Making Experts out of Dilettantes (2021, methodology): “Some examples of such models include Deep Relevance Matching Model (DRMM) [32], DUET [60], Kernel-based Neural Ranking Model (KNRM) [101], Position-Aware Convolutional-Recurrent Relevance (PACRR) [34], and Context-Aware PACRR (co-PACRR) [35].”
Training Curricula for Open Domain Answer Re-Ranking (2020, methodology): “We also compare our results to the performance reported by [28] and [24], which use BERT and the PACRR neural ranking architecture augmented with entity embeddings for classification, respectively.”
BERT-QE: Contextualized Query Expansion for Document Re-ranking (2020, methodology): “alized models like BERT on NLP tasks, Nogueira and Cho (2019) examine the performance of BERT on the passage re-ranking tasks using MS MARCO and TREC-CAR datasets, and demonstrate superior performances compared with the existing shallow ranking models like Co-PACRR (Hui et al., 2018)”
Deep Relevance Ranking Using Enhanced Document-Query Interactions (2018, methodology): “Following Hui et al. (2018), we concatenate the rows of the resulting matrix into a single vector, which is passed to an MLP (Fig.”
Early Exiting BERT for Efficient Document Ranking (2020, background): “Throughout this paper, we refer to candidates to be retrieved as documents , although they may actually be passages, answers to a question, etc. Representative neural ranking models include DRMM (Guo et al., 2016), DUET (Mitra et al., 2017), KNRM (Xiong et al., 2017), Co-PACRR (Hui et al., 2018) — j”
Long Document Ranking with Query-Directed Sparse Transformer (2020, methodology): “• CO-PACRR (Hui et al., 2018) utilizes CNNs to model query-document similarity matrices and provide a score using a max-pooling layer.”
MarkedBERT: Integrating Traditional IR Cues in Pre-trained Language Models for Passage Retrieval (2020, methodology): “With the advent of deep learning, the IR community witnessed a flourishing development of neural ranking models, such as DRMM [3], DUET [7], KNRM [15] and Co-PACRR [4].”