论文标题
注射域的适应性，并进行学习，以实现有效而有效的零射击量检索
Injecting Domain Adaptation with Learning-to-hash for Effective and Efficient Zero-shot Dense Retrieval
论文作者
论文摘要
密集的检索克服了词汇差距，并在临时信息检索（IR）方面取得了巨大成功。尽管他们成功了，但密集的猎犬在实际用例中服务还是昂贵的。对于需要从数百万个文档中搜索的用例，致密索引变得笨重，并且需要高度的存储器来存储索引。最近，对于BPR和JPQ而言，学习对手（LTH）技术，产生二进制文档向量，从而减少了有效存储密集索引的内存需求。 LTH技术受到监督，并使用排名损失对猎犬进行了捕获。他们的表现胜过同行，即传统的开箱即用矢量压缩技术，例如PCA或PQ。先前工作中缺少的一部分是仅在单个数据集（例如MASCO）上对现有技术进行了评估。在我们的工作中，我们评估了LTH和矢量压缩技术，以提高TAS-B致密回寻回剂的下游零射击检索准确性，同时在推理时保持效率。我们的研究结果表明，与先前的工作不同，在贝尔基准中，无天然应用的策略平均可以表现不佳，平均零射Tas-b致密猎犬的恢复。为了解决这一局限性，在我们的工作中，我们提出了一种简单而有效的解决方案，以使用现有的监督LTH技术对域进行适应。我们尝试两种众所周知的无监督域适应技术：GENQ和GPL。 Our domain adaptation injection technique can improve the downstream zero-shot retrieval effectiveness for both BPR and JPQ variants of the TAS-B model by on average 11.5% and 8.2% nDCG@10 while both maintaining 32$\times$ memory efficiency and 14$\times$ and 2$\times$ speedup respectively in CPU retrieval latency on BEIR.我们所有的代码，模型和数据均在https://github.com/thakur-nandan/income上公开获取。
Dense retrieval overcome the lexical gap and has shown great success in ad-hoc information retrieval (IR). Despite their success, dense retrievers are expensive to serve across practical use cases. For use cases requiring to search from millions of documents, the dense index becomes bulky and requires high memory usage for storing the index. More recently, learning-to-hash (LTH) techniques, for e.g., BPR and JPQ, produce binary document vectors, thereby reducing the memory requirement to efficiently store the dense index. LTH techniques are supervised and finetune the retriever using a ranking loss. They outperform their counterparts, i.e., traditional out-of-the-box vector compression techniques such as PCA or PQ. A missing piece from prior work is that existing techniques have been evaluated only in-domain, i.e., on a single dataset such as MS MARCO. In our work, we evaluate LTH and vector compression techniques for improving the downstream zero-shot retrieval accuracy of the TAS-B dense retriever while maintaining efficiency at inference. Our results demonstrate that, unlike prior work, LTH strategies when applied naively can underperform the zero-shot TAS-B dense retriever on average by up to 14% nDCG@10 on the BEIR benchmark. To solve this limitation, in our work, we propose an easy yet effective solution of injecting domain adaptation with existing supervised LTH techniques. We experiment with two well-known unsupervised domain adaptation techniques: GenQ and GPL. Our domain adaptation injection technique can improve the downstream zero-shot retrieval effectiveness for both BPR and JPQ variants of the TAS-B model by on average 11.5% and 8.2% nDCG@10 while both maintaining 32$\times$ memory efficiency and 14$\times$ and 2$\times$ speedup respectively in CPU retrieval latency on BEIR. All our code, models, and data are publicly available at https://github.com/thakur-nandan/income.
