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 2409.09795cs.IR
收藏

CROSS-JEM:面向短文本排序任务的精准高效交叉编码器

CROSS-JEM: Accurate and Efficient Cross-encoders for Short-text Ranking Tasks

Bhawna Paliwal, Deepak Saini, Mudit Dhawan, Siddarth Asokan, Nagarajan Natarajan, Surbhi Aggarwal, Pankaj Malhotra, Jian Jiao, Manik Varma

AI总结:

针对现有交叉编码器独立打分忽略联合上下文、精度不足且成本高的问题,提出CROSS-JEM方法,通过联合打分与新型训练目标,实现了短文本排序任务的SOTA精度与4倍以上延迟降低。

摘要:

根据一组条目与给定查询的相关性对其进行排序,是搜索与推荐领域的核心问题。基于Transformer的排序模型是此类任务的当前最优方法,但它们会独立为每个查询-条目对打分,忽略了其他相关条目的联合上下文。这会导致排序精度未达最优,且计算成本高昂。针对这一问题,我们提出了联合高效建模交叉编码器(Cross-encoders with Joint Efficient Modeling,CROSS-JEM),这是一种新型排序方法,可让基于Transformer的模型为同一查询的多个条目联合打分,最大化参数利用率。CROSS-JEM利用两大核心设计:(a)借助条目间的冗余性与词元重叠,为多个条目联合打分——这些条目通常是搜索与推荐场景中出现的短文本短语;(b)采用一种新型训练目标,对排序概率进行建模。CROSS-JEM实现了当前最优的精度,且排序延迟比标准交叉编码器低4倍以上。我们的贡献有三方面:(i)我们指出了排序应用中“每个查询需为数千个条目打分”的需求,与当前交叉编码器有限能力之间的差距;(ii)我们提出了CROSS-JEM,用于为每个查询的多个条目进行联合高效打分;(iii)我们在标准公开数据集和一个专有数据集上验证了该方法达到当前最优精度。CROSS-JEM为设计适配生产环境严格约束(如条目多样性、延迟要求)的、基于早期注意力的定制化排序模型开辟了新方向。

英文摘要:

Ranking a set of items based on their relevance to a given query is a core problem in search and recommendation. Transformer-based ranking models are the state-of-the-art approaches for such tasks, but they score each query-item independently, ignoring the joint context of other relevant items. This leads to sub-optimal ranking accuracy and high computational costs. In response, we propose Cross-encoders with Joint Efficient Modeling (CROSS-JEM), a novel ranking approach that enables transformer-based models to jointly score multiple items for a query, maximizing parameter utilization. CROSS-JEM leverages (a) redundancies and token overlaps to jointly score multiple items, that are typically short-text phrases arising in search and recommendations, and (b) a novel training objective that models ranking probabilities. CROSS-JEM achieves state-of-the-art accuracy and over 4x lower ranking latency over standard cross-encoders. Our contributions are threefold: (i) we highlight the gap between the ranking application's need for scoring thousands of items per query and the limited capabilities of current cross-encoders; (ii) we introduce CROSS-JEM for joint efficient scoring of multiple items per query; and (iii) we demonstrate state-of-the-art accuracy on standard public datasets and a proprietary dataset. CROSS-JEM opens up new directions for designing tailored early-attention-based ranking models that incorporate strict production constraints such as item multiplicity and latency.

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。

↑