paper-with-me

Papers

Set-Encoder: Permutation-Invariant Inter-Passage Attention for Listwise Passage Re-Ranking with Cross-Encoders

2024-04-10 · Ferdinand Schlatt, Maik Fröbe, Harrisen Scells, Shengyao Zhuang, Bevan Koopman, Guido Zuccon, Benno Stein, Martin Potthast, Matthias Hagen

Existing cross-encoder models can be categorized as pointwise, pairwise, or listwise. Pairwise and listwise models allow passage interactions, which typically makes them more effective than pointwise models but less efficient and less robust to input passage order permutations. To enable efficient permutation-invariant passage interactions during re-ranking, we propose a new cross-encoder architecture with inter-passage attention: the Set-Encoder. In experiments on TREC Deep Learning and TIREx, the Set-Encoder is as effective as state-of-the-art listwise models while being more efficient and invariant to input passage order permutations. Compared to pointwise models, the Set-Encoder is particularly more effective when considering inter-passage information, such as novelty, and retains its advantageous properties compared to other listwise models. Our code is publicly available at https://github.com/webis-de/ECIR-25.

📄 PDF Abstract BibTeX arXiv:2404.06912

Code (2)

webis-de/ecir-25 공식 구현
webis-de/set-encoder 공식 구현 pytorch

Tasks

Passage Re-RankingRe-Ranking

Similar Papers 제목 키워드 기반

Set Transformer: A Framework for Attention-based Permutation-Invariant Neural Networks

2018-10-01 · Juho Lee, Yoonho Lee, Jungtaek Kim, Adam R. Kosiorek 외

Many machine learning tasks such as multiple instance learning, 3D shape recognition, and few-shot image classification are defined on sets of instances. Since solutions to such problems do not depend on the order of ele…

3D Shape RecognitionDecoderFew-Shot Image Classificationimage-classification+2

Few-shot Action Recognition with Permutation-invariant Attention

2020-01-12 · ECCV 2020 8 · Hongguang Zhang, Li Zhang, Xiaojuan Qi, Hongdong Li 외

Many few-shot learning models focus on recognising images. In contrast, we tackle a challenging task of few-shot action recognition from videos. We build on a C3D encoder for spatio-temporal video blocks to capture short…

Action RecognitionFew-Shot action recognitionFew Shot Action RecognitionFew-Shot Learning+2

Incorporating Explicit Knowledge in Pre-trained Language Models for Passage Re-ranking

2022-04-25 · Qian Dong, Yiding Liu, Suqi Cheng, Shuaiqiang Wang 외

Passage re-ranking is to obtain a permutation over the candidate passage set from retrieval stage. Re-rankers have been boomed by Pre-trained Language Models (PLMs) due to their overwhelming advantages in natural languag…

Graph Neural NetworkNatural Language UnderstandingPassage Re-RankingRe-Ranking+1

Equivariant vs. Invariant Layers: A Comparison of Backbone and Pooling for Point Cloud Classification

2023-06-08 · Abihith Kothapalli, Ashkan Shahbazi, Xinran Liu, Robert Sheng 외

Learning from set-structured data, such as point clouds, has gained significant attention from the machine learning community. Geometric deep learning provides a blueprint for designing effective set neural networks that…

Point Cloud Classification

Learning Permutation-invariant Macroscopic Dynamics

2026-05-29 · Zhichao Han, Mengyi Chen, Qianxiao Li arxiv

Accurately modeling the macroscopic dynamics of high-dimensional microscopic systems is of broad interest across the sciences. Many data-driven approaches learn a low-dimensional latent state through an autoencoder train…