Deep Relevance Ranking Using Enhanced Document-Query Interactions

By Ryan T. McDonald, George Brokos, Ion Androutsopoulos. 2018

128 citations recorded by the source corpus.

We explore several new models for document relevance ranking, building upon the Deep Relevance Matching Model (DRMM) of Guo et al. (2016). Unlike DRMM, which uses context-insensitive encodings of terms and query-document term interactions, we inject rich context-sensitive encodings throughout our models, inspired by PACRR’s (Hui et al., 2017) convolutional n-gram matching features, but extended in several ways including multiple views of query and document inputs. We test our models on datasets from the BIOASQ question answering challenge (Tsatsaronis et al., 2015) and TREC ROBUST 2004 (Voorhees, 2005), showing they outperform BM25-based baselines, DRMM, and PACRR.

Subfields: Artificial Intelligence, 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 Artificial Intelligence

In Information Retrieval & Search

Citations in the corpus

Pretrained Transformers for Text Ranking: BERT and Beyond (2020, methodology): “For example, POSIT-DRMM [McDonald et al., 2018] uses an LSTM to contextualize static embeddings before comparing them.”
AUEB at BioASQ 7: Document and Snippet Retrieval (2019, methodology): “We experimented with two neural models for document reranking, one based on pacrr [17] and one based on bert [5].”
An anatomy for neural search engines (2019, methodology): “Therefore, the authors opted for implementing what they judged to be the most consolidated, accessible and easily reproducible neural models in the literature, which are also a reference for several recent works [McDonald et al., 2018; Hui et al., 2017; Pang et al., 2017b].”
CORD-19: The Covid-19 Open Research Dataset (2020, methodology): “Similarly, the AUEB system 29 employs question answering by training the model presented in McDonald et al. (2018).”
Promptagator: Few-shot Dense Retrieval From 8 Examples (2022, methodology): “Interaction based models on the other hand explicitly model the interaction between query and document terms (Guo et al., 2016; Hui et al., 2017; Xiong et al., 2017; Dai et al., 2018; McDonald et al., 2018; Nogueira & Cho, 2019), and therefore make more informed decisions.”
Cross-Domain Modeling of Sentence-Level Evidence for Document Retrieval (2019, methodology): “To provide two recent examples, McDonald et al. (2018) report a best AP score of 0.272 and Li et al. (2018) 0.290, compared to a simple bag-of-words query expansion baseline that achieves 0.299 (Lin, 2018).”
CEDR: Contextualized Embeddings for Document Ranking (2019, background): “In a similar vein, McDonald et al. [12] proposes an approach that learns a recurrent neural network for term representations, thus being able to capture context from the entire text [12].”
Capreolus: A Toolkit for End-to-End Neural Ad Hoc Retrieval (2020, methodology): “We implemented the multi-view POSITDRMM variant.”