arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2103.16669cs.IR
收藏

面向上下文文档排序的段落级标签迁移深度分析

An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking

Koustav Rudra, Zeon Trevor Fernando, Avishek Anand

AI总结:

本文分析文档切分与段落级标签迁移对检索效果和效率的影响,提出弱监督段落标注方案,在四个数据集上以可控复杂度取得3%–14%的nDCG提升。

摘要:

诸如 BERT、GPT 和 XLnet 等预训练上下文语言模型在文档检索任务上表现相当出色。此类模型基于查询-文档或查询-段落级相关性标签进行微调,以捕获排序信号。然而,文档比段落更长,这类文档排序模型受到 BERT 的 512 个 token 限制。研究人员提出了若干排序策略,要么截断超出 token 限制的文档,要么将文档切分为能够输入 BERT 的单元。在后一种情况下,相关性标签要么从原始查询-文档对直接迁移,要么通过某个外部模型学习。本文详细研究了切分与标签迁移方面的设计决策对检索效果和效率的影响。我们发现,将相关性标签从文档直接迁移到段落会引入标签噪声,并在大规模训练数据集上严重影响检索效果。我们还发现,查询处理时间会受到细粒度切分方案的不利影响。作为补救措施,我们提出一种采用弱监督的谨慎段落级标注方案;在四个多样化的文档检索数据集上,该方案相对于大多数近期提出的 ad-hoc retrieval 模型实现了 3%–14% 的 nDCG 分数提升,同时保持可控的计算复杂度。

英文摘要:

Pre-trained contextual language models such as BERT, GPT, and XLnet work quite well for document retrieval tasks. Such models are fine-tuned based on the query-document/query-passage level relevance labels to capture the ranking signals. However, the documents are longer than the passages and such document ranking models suffer from the token limitation (512) of BERT. Researchers proposed ranking strategies that either truncate the documents beyond the token limit or chunk the documents into units that can fit into the BERT. In the later case, the relevance labels are either directly transferred from the original query-document pair or learned through some external model. In this paper, we conduct a detailed study of the design decisions about splitting and label transfer on retrieval effectiveness and efficiency. We find that direct transfer of relevance labels from documents to passages introduces label noise that strongly affects retrieval effectiveness for large training datasets. We also find that query processing times are adversely affected by fine-grained splitting schemes. As a remedy, we propose a careful passage level labelling scheme using weak supervision that delivers improved performance (3-14% in terms of nDCG score) over most of the recently proposed models for ad-hoc retrieval while maintaining manageable computational complexity on four diverse document retrieval datasets.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑