Confidence-Calibrated Ensemble Dense Phrase Retrieval

William Yang, Noah Bergam, Arnav Jain, Nima Sheikhoslami
6/28/2023
cs.CLcs.IR

No confident code implementation found for this paper.

Abstract

In this paper, we consider the extent to which the transformer-based Dense Passage Retrieval (DPR) algorithm, developed by (Karpukhin et. al. 2020), can be optimized without further pre-training. Our method involves two particular insights: we apply the DPR context encoder at various phrase lengths (e.g. one-sentence versus five-sentence segments), and we take a confidence-calibrated ensemble prediction over all of these different segmentations. This somewhat exhaustive approach achieves start-of-the-art results on benchmark datasets such as Google NQ and SQuAD. We also apply our method to domain-specific datasets, and the results suggest how different granularities are optimal for different domains

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Can Transformers Really Do It All? On the Compatibility of Inductive Biases Across Tasks

83% match2026

MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining

83% match1 repo4662023

Adam-Smith at SemEval-2023 Task 4: Discovering Human Values in Arguments with Ensembles of Transformer-based Models

82% match1 repo142023

Increasing The Performance of Cognitively Inspired Data-Efficient Language Models via Implicit Structure Building

81% match2023

Attention over pre-trained Sentence Embeddings for Long Document Classification

81% match2023

Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures

81% match1 repo32025

Cite this paper

@article{yang2023confidencecalibrated,
  title  = {Confidence-Calibrated Ensemble Dense Phrase Retrieval},
  author = {William Yang and Noah Bergam and Arnav Jain and Nima Sheikhoslami},
  year   = {2023},
  eprint = {2306.15917},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2306.15917v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2306.15917.svg)](https://codeofpaper.com/paper/2306.15917)

Discussion