引导式测验 · 中等 等级
密集段落检索测验
测试 DPR 查询和段落编码器、点积评分、批量和 BM25 负数,以及嵌入更改时刷新索引的需要。
问题 1 的 8
How does Dense Passage Retrieval decide which passages match a query?
预览每个问题8 问题
当您参加测验时,就会出现答案和解释。
- How does Dense Passage Retrieval decide which passages match a query?
- 通过相似性比较查询和段落的密集向量表示
- 统计每个文档中出现的查询词数量
- 在搜索之前将查询翻译成 SQL
- 纯粹按照文档的发布时间对文档进行排名
- DPR 使用“双编码器”架构。这意味着什么?
- 它对文本进行两次编码并对结果进行平均
- 它仅适用于双语文档
- 它同时对字符和单词进行编码
- 它使用两个独立的编码器,一个用于查询,一个用于段落
- 为什么DPR中可以提前计算通道向量?
- 因为一旦写下的段落就永远不会改变
- 因为查询编码器在搜索时被禁用
- 因为每个段落的编码独立于任何查询
- 因为段落仅存储为原始文本
- 什么训练技巧可以让 DPR 廉价地生成许多反例?
- 随机标签翻转
- 批次内阴性,使用同一批次中的其他通道
- 丢弃一半的神经元
- 手动标记每个错误的段落
- For what vocabulary mismatch can learned DPR representations be useful compared with lexical matching alone?
- The passage is unrelated but repeats the query's terms
- Every query contains only an exact serial number
- The encoder is guaranteed to retrieve the right answer for all inputs
- A relevant passage expresses a query's idea using different words
- 通常使用什么工具来使 DPR 的最近邻搜索快速大规模进行?
- 近似最近邻索引,例如 FAISS
- 电子表格排序
- 正则表达式引擎
- 关系数据库连接
- Why can BM25-retrieved nonanswer passages be useful hard negatives when training DPR?
- They guarantee that every retrieved passage is irrelevant
- Their lexical overlap can make them challenging distractors that the retriever must distinguish from the answer passage
- They remove the need for a positive answer passage
- They force the passage encoder to count words without learning
- After changing DPR's passage encoder, what should happen to a stored passage-vector index?
- Keep the old embeddings because encoder weights cannot affect vectors
- Rename the index without recalculating any representation
- Recompute the passage embeddings with the intended compatible encoder and update the index
- Disable the query encoder and search raw filenames instead