From doc2query to docTTTTTquery

By David R. Cheriton. 2019

Subfields: Information Retrieval & Search, Large Language Models

How researchers see this paper

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

In Information Retrieval & Search

In Large Language Models

Citations in the corpus

Autoregressive Search Engines: Generating Substrings as Document Identifiers (2022, background): “For example, one can augment stored documents by generating possible queries that might be answered by them (Nogueira et al., 2019; Nogueira and Lin, 2021).”
Pretrained Transformers for Text Ranking: BERT and Beyond (2020, background): “expansion (Nogueira et al., 2019b; Nogueira and Lin, 2019) and term importance prediction (Dai and Callan, 2019a, 2020).”
Pyserini: An Easy-to-Use Python Toolkit to Support Replicable IR Research with Sparse and Dense Representations (2021, methodology): “Pyserini also provides document expansion baselines using our doc2query method [21]; the latest model uses T5 [24] as described in Nogueira and Lin [19].”
Pyserini: A Python Toolkit for Reproducible Information Retrieval Research with Sparse and Dense Representations (2021, methodology): “Dense retrieval using TCT-ColBERT is shown in row (2); this is a new experimental condition that was not reported in Lin et al. [17].”
RocketQA: An Optimized Training Approach to Dense Passage Retrieval for Open-Domain Question Answering (2020, background): “The sparse retrievers include the traditional retriever BM25 (Yang et al., 2017), and four traditional retrievers enhanced by neural networks, including doc2query (Nogueira et al., 2019c), DeepCT (Dai and Callan, 2019), docTTTT-Tquery (Nogueira et al., 2019a) and GAR (Mao et al., 2020).”
BERT-QE: Contextualized Query Expansion for Document Re-ranking (2020, methodology): “Doc2query is further improved by docTTTTTquery (Nogueira and Lin, 2019) which replaces the seq2seq transformer with T5 (Raffel et al.”
Salient Phrase Aware Dense Retrieval: Can a Dense Retriever Imitate a Sparse One? (2021, background): “, 2021), address vocabulary mismatch (Nogueira and Lin, 2019) and se-”
Expansion via Prediction of Importance with Contextualization (2020, background): “However, these approaches have a substantial computational burden, which can make them impractical [7, 14].”
PAIR: Leveraging Passage-Centric Similarity Relation for Improving Dense Passage Retrieval (2021, background): “, 2019b), DeepCT (Dai and Callan, 2019), docTTTTTquery (Nogueira et al., 2019a) and GAR (Mao et al.”
SparTerm: Learning Term-based Sparse Representation for Fast Text Retrieval (2020, methodology): “• Doc2query-T5 [1] is a document expansion method which utilizes more powerful T5 [13] language model to generate queries for document expansion.”
Dense Text Retrieval Based on Pretrained Language Models: A Survey (2022, background): “For example, docTTTTTquery [171] predicts a set of queries that a document will be relevant to, such that the predicted queries can be used to enrich the document”
SPLADE v2: Sparse Lexical and Expansion Model for Information Retrieval (2021, background): “A first solution to this problem consists in expanding documents using generative approaches such as doc2query [21] and doc2queryT5 [20] to predict expansion words for documents.”
Retrieval as Attention: End-to-end Learning of Retrieval and Reading within a Single Transformer (2022, methodology): “• Supervised adaptation models are trained with downstream task supervision, including RAG trained on BioASQ, Contriever fine-tuned on FiQA, and docT5query, ANCE, ColBERT, and Contriever fine-tuned on MS MARCO (Nogueira and Lin, 2019; Xiong et al., 2021; Khattab and Zaharia, 2020; Izacard et al., 20”
Distilling Dense Representations for Ranking using Tightly-Coupled Teachers (2020, methodology): “We follow two protocols for evaluation aligned with previous work (Nogueira and Lin, 2019; Dai and Callan, 2020; Gao et al., 2020; Luan et al., 2020; Khattab and Zaharia, 2020): (a) MS MARCO Dev: 6980 queries comprise the development set for MS MARCO, with on average one relevant passage per query.”