MétaCan
← all works

Document Ranking with a Pretrained Sequence-to-Sequence Model

2020· article· en· 414 citations· W3100107515 on OpenAlex· 10.18653/v1/2020.findings-emnlp.63

Why is this work in the frame?

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

Canadian funderA Canadian agency funded it. The work may carry no Canadian affiliation at all.

No Canadian affiliation. An affiliation-only frame — the usual design — would never have seen this work. It is one of the works that make the case for inverting the frame.

Machine scores (provisional)

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Opus teacher head0.070
GPT teacher head0.276
Teacher spread
0.206 · how far apart the two teachers sit on this one work
Validation status
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Abstract

This work proposes the use of a pretrained sequence-to-sequence model for document ranking. Our approach is fundamentally different from a commonly adopted classificationbased formulation based on encoder-only pretrained transformer architectures such as BERT. We show how a sequence-to-sequence model can be trained to generate relevance labels as "target tokens", and how the underlying logits of these target tokens can be interpreted as relevance probabilities for ranking. Experimental results on the MS MARCO passage ranking task show that our ranking approach is superior to strong encoderonly models. On three other document retrieval test collections, we demonstrate a zeroshot transfer-based approach that outperforms previous state-of-the-art models requiring indomain cross-validation. Furthermore, we find that our approach significantly outperforms an encoder-only architecture in a data-poor setting. We investigate this observation in more detail by varying target tokens to probe the model's use of latent knowledge. Surprisingly, we find that the choice of target tokens impacts effectiveness, even for words that are closely related semantically. This finding sheds some light on why our sequence-to-sequence formulation for document ranking is effective. Code and models are available at pygaggle.ai.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

The record

Venue
Topic
Topic Modeling
Field
Computer Science
Canadian institutions
Funders
Natural Sciences and Engineering Research Council of CanadaCanada First Research Excellence Fund
Keywords
Computer scienceRanking (information retrieval)Sequence (biology)EncoderRelevance (law)Artificial intelligenceTransformerTask (project management)Information retrievalMachine learningNatural language processingData miningEngineering
Has abstract in OpenAlex
yes