arXiv cs.CL· Keshav Kolluru, Manas Gupta, Maroof Ahmad, Suchitra Sathyanarayana·· 2 天前AI 评分22
混合生成-标注解码：高效提取产品属性值
Hybrid Generative-Tagging Decoding for Efficient Product Attribute-Value Extraction
AI 导读
研究者提出混合生成-标注解码架构，将标注源文本片段与开放式生成结合：可复制的常见属性值由标注头直接从源文本抽取，生成头则专注标注标签空间外的稀有属性和需重格式化或归一化的非可复制值。该解码器集成进 vLLM 推理后，属性覆盖率提升 10%，正确属性值对多提取 63%，精度无损，延迟降低 44%。
正文 · 原文
Abstract:Attribute-value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directly label spans in the source, making them fast and grounded, but they cannot produce values that require reformatting or generate rare attribute names outside their label space. Generative models avoid these drawbacks by generating both attribute names and values token by token, but this auto-regressive nature makes them slow and limits attribute coverage. We introduce hybrid generative-tagging decoding, a novel model architecture that combines tagging source spans and open-ended generation. For frequent attributes whose values are copyable, a tagging head extracts values directly from the source. This lets the generative head focus on the remainder - rare attributes outside the tagger's label space and non-copyable values, including implicit or normalized values. Integrated into vLLM inference, the hybrid decoder raises attribute coverage by 10% and extracts 63% more correct attribute-value pairs at no precision cost, while reducing latency by 44%.
| Comments: | Accepted to EMNLP 2026 (Industry Track) |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.21329 [cs.CL] |
| (or arXiv:2610.21329v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.21329 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Keshav Kolluru [view email]
[v1]
Thu, 15 Oct 2026 06:18:17 UTC (133 KB)
来源：arXiv cs.CL · arxiv.org