从字段感知的混合匹配视角定制表格检索
Tailoring Table Retrieval from a Field-aware Hybrid Matching Perspective
AI总结:
针对表格不同字段具有不同匹配偏好的挑战,提出表格定制混合匹配检索器THYME,从字段感知的混合匹配视角处理表格检索,在NQ-TABLES和OTT-QA基准上显著优于最先进基线。
摘要:
表格检索对于通过表格数据访问信息至关重要,但与文本检索相比探索较少。表格的行/列结构和不同字段(包括标题、表头和单元格)带来了独特挑战。例如,不同的表格字段有不同的匹配偏好:由于单元格具有碎片化和详细的特点,与标题不同,它们可能更倾向于细粒度(词/短语级别)匹配,而非更广泛的(句子/段落级别)匹配。这需要一个针对表格定制的检索器来适应每个表格字段的各种匹配需求。因此,我们引入了Table-tailored HYbrid Matching rEtriever (THYME)(表格定制混合匹配检索器),它从字段感知的混合匹配视角来处理表格检索。在两个表格检索基准NQ-TABLES和OTT-QA上的实证结果表明,THYME显著优于最先进的基线。综合分析证实了表格字段之间不同的匹配偏好,并验证了THYME的设计。
英文摘要:
Table retrieval, essential for accessing information through tabular data, is less explored compared to text retrieval. The row/column structure and distinct fields of tables (including titles, headers, and cells) present unique challenges. For example, different table fields have varying matching preferences: cells may favor finer-grained (word/phrase level) matching over broader (sentence/passage level) matching due to their fragmented and detailed nature, unlike titles. This necessitates a table-specific retriever to accommodate the various matching needs of each table field. Therefore, we introduce a Table-tailored HYbrid Matching rEtriever (THYME), which approaches table retrieval from a field-aware hybrid matching perspective. Empirical results on two table retrieval benchmarks, NQ-TABLES and OTT-QA, show that THYME significantly outperforms state-of-the-art baselines. Comprehensive analyses confirm the differing matching preferences across table fields and validate the design of THYME.
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。