Information Retrieval Journal最新文献

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.

Previous work on privacy-aware ranking has addressed the minimization of information leakage when scoring top k documents, and has not studied on how to retrieve these top documents and their features for ranking. This paper proposes a privacy-aware document retrieval scheme with a two-level inverted index structure. In this scheme, posting records are grouped with bucket tags and runtime query processing produces query-specific tags in order to gather encoded features of matched documents with a privacy protection during index traversal. To thwart leakage-abuse attacks, our design minimizes the chance that a server processes unauthorized queries or identifies document sharing across posting lists through index inspection or across-query association. This paper presents the evaluation and analytic results of the proposed scheme to demonstrate the tradeoffs in its design considerations for privacy, efficiency, and relevance.

This paper presents an exploration of the usage of Heterogeneous Graph Attention Networks, or HGATs, for the task of Passage Retrieval. More precisely, we study how these models perform to alleviate the problem of passage contextualization, that is incorporating information about the context of a passage (its containing document, neighbouring passages, etc.) in its relevance estimation. We first propose several configurations to compute contextualized passage representations, including a document graph representation composed of contextualizing signals and judiciously modified HGAT architectures. We then present how we integrate these configurations in a neural passage ranking model. We evaluate our approach on a Passage Retrieval task on patent documents: CLEF-IP2013, as these documents possess several different contextualizing signals fully exploited in our models. Our results show that some HGAT architecture modifications allow for a better context representation leading to improved performances and stability.