Recent work in cross-language information retrieval (CLIR), where queries and
documents are in different languages, has shown the benefit of the
Translate-Distill framework that trains a cross-language neural dual-encoder
model using translation and distillation. However, Translate-Distill only
supports a single document language. Multilingual information retrieval (MLIR),
which ranks a multilingual document collection, is harder to train than CLIR
because the model must assign comparable relevance scores to documents in
different languages. This work extends Translate-Distill and propose
Multilingual Translate-Distill (MTD) for MLIR. We show that ColBERT-X models
trained with MTD outperform their counterparts trained ith Multilingual
Translate-Train, which is the previous state-of-the-art training approach, by
5% to 25% in nDCG@20 and 15% to 45% in MAP. We also show that the model is
robust to the way languages are mixed in training batches. Our implementation
is available on GitHub.

使用 Translate-Distill 框架进行跨语言信息检索 (CLIR) 已经显示出其通过翻译和塑造训练跨语言神经双重编码器模型的好处。然而，Translate-Distill 仅支持单一语言。本研究扩展 Translate-Distill 并提出了用于多语言信息检索 (MLIR) 的多语言 Translate-Distill (MTD) 方法。我们通过 nDCG@20 指标和 MAP 指标在性能上展示了使用 MTD 培训的 ColBERT-X 模型优于以前的最先进训练方法 Multilingual Translate-Train，其在 nDCG@20 上提高了 5% 到 25%，在 MAP 上提高了 15% 到 45%。我们还展示了该模型对于训练批次中语言混合方式的鲁棒性。我们的实现可在 GitHub 上找到。

多语言信息检索的蒸馏

Distillation for Multilingual Information Retrieval

This paper explores a novel technique for improving recall in cross-language
information retrieval (CLIR) systems using iterative query refinement grounded
in the user's lexical-semantic space. The proposed methodology combines
multi-level translation, semantic embedding-based expansion, and user
profile-centered augmentation to address the challenge of matching variance
between user queries and relevant documents. Through an initial BM25 retrieval,
translation into intermediate languages, embedding lookup of similar terms, and
iterative re-ranking, the technique aims to expand the scope of potentially
relevant results personalized to the individual user. Comparative experiments
on news and Twitter datasets demonstrate superior performance over baseline
BM25 ranking for the proposed approach across ROUGE metrics. The translation
methodology also showed maintained semantic accuracy through the multi-step
process. This personalized CLIR framework paves the path for improved
context-aware retrieval attentive to the nuances of user language.

通过多级翻译、语义嵌入扩展和基于用户轮廓的增强技术，该论文探讨了一种在用户的词汇语义空间中改善跨语言信息检索系统召回率的新技术。实验结果表明，该方法在新闻和 Twitter 数据集上相对于基线 BM25 排序在 ROUGE 指标方面表现出优越性，并且该翻译方法在多步骤过程中保持了语义的准确性。此个性化跨语言信息检索框架有望改善对用户语言细微差别的感知性。

利用翻译优化召回率：通过用户配置个性化 LLM

Leveraging Translation For Optimal Recall: Tailoring LLM Personalization  With User Profiles

HC4 is a new suite of test collections for ad hoc Cross-Language Information
Retrieval (CLIR), with Common Crawl News documents in Chinese, Persian, and
Russian, topics in English and in the document languages, and graded relevance
judgments. New test collections are needed because existing CLIR test
collections built using pooling of traditional CLIR runs have systematic gaps
in their relevance judgments when used to evaluate neural CLIR methods. The HC4
collections contain 60 topics and about half a million documents for each of
Chinese and Persian, and 54 topics and five million documents for Russian.
Active learning was used to determine which documents to annotate after being
seeded using interactive search and judgment. Documents were judged on a
three-grade relevance scale. This paper describes the design and construction
of the new test collections and provides baseline results for demonstrating
their utility for evaluating systems.

本文章介绍了一种新的用于跨语言信息检索的测试集合 HC4，并利用交互搜索和判断以及主动学习方法来构建测试集合，以评估神经 CLIR 方法的效用及提供基准结果。

HC4: 用于 Ad Hoc CLIR 的新测试集

HC4: A New Suite of Test Collections for Ad Hoc CLIR

As a crucial role in cross-language information retrieval (CLIR), query
translation has three main challenges: 1) the adequacy of translation; 2) the
lack of in-domain parallel training data; and 3) the requisite of low latency.
To this end, existing CLIR systems mainly exploit statistical-based machine
translation (SMT) rather than the advanced neural machine translation (NMT),
limiting the further improvements on both translation and retrieval quality. In
this paper, we investigate how to exploit neural query translation model into
CLIR system. Specifically, we propose a novel data augmentation method that
extracts query translation pairs according to user clickthrough data, thus to
alleviate the problem of domain-adaptation in NMT. Then, we introduce an
asynchronous strategy which is able to leverage the advantages of the real-time
in SMT and the veracity in NMT. Experimental results reveal that the proposed
approach yields better retrieval quality than strong baselines and can be well
applied into a real-world CLIR system, i.e. Aliexpress e-Commerce search
engine. Readers can examine and test their cases on our website:
this https URL .

利用神经机器翻译及数据增强和异步策略，改善跨语言信息检索中的查询翻译问题，提高信息检索质量。