qq_52852138的博客

语言模型何时需要检索增强

Reliable, Adaptable, and Attributable Language Models with Retrieval

小白也能懂的AUROC介绍

【SIGIR-AP 2023】AComparative Study of Training Objectives for Clarification Facet Generation

检索增强相关文章总结：`Knn-LM`->`REALM`->`DPR`->`RAG`->`FID`->`COG`->`GenRead`->`REPLUG`->`Adaptive retrieval`

【论文阅读】REPLUG: Retrieval-Augmented Black-Box Language Models

【论文阅读】MIMICS: A Large-Scale Data Collection for Search Clarification

【论文阅读 SIGIR'19】Asking Clarifying Questions in Open-Domain Information-Seeking Conversations

【论文阅读】Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Information

【论文阅读 WWW'23】Zero-shot Clarifying Question Generation for Conversational Search

BPE简介

常见的分词方法：word-based，character-based，subword-based tokenization

【论文阅读 T5】Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

【论文阅读 CIKM2011】Finding Dimensions for Queries

【论文阅读 CIKM2014】Extending Faceted Search to the General Web

【论文阅读 CIKM 2022】Stochastic Optimization of Text Set Generation for Learning Multiple Query Intent Representations

Clarifying Question 领域最常用的数据集

【论文阅读 CIKM'2021】Learning Multiple Intent Representations for Search Queries

【论文阅读 ICTIR'2022】Revisiting Open Domain Query Facet Extraction and Generation

【WSDM'2022】Evaluating Mixed-initiative Conversational Search Systems via User Simulation

关于Dialog和Clarifying question的文献整理

【论文阅读 WSDM'21】PROP: Pre-training with Representative Words Prediction for Ad-hoc Retrieval

【论文阅读】A Large Scale Search Dataset for Unbiased Learning to Rank

【论文阅读 FnTIR2022】Pre-training Methods in Information Retrieval

信息检索相关任务及数据集介绍

【论文阅读】GPT系列论文详解

【论文阅读 ICLR2022】Multitask Prompted Training Enables Zero-shot Task Generalization

【论文阅读 ICLR2022】Finetuned Language Models Are Zero-Shot Learners

信息检索第二阶段【排序阶段】的综述

信息检索第一阶段【retrieval】综述

MAP , MRR , NDCG第一步，读取数据并处理读取 qrels.txt中的数据，并对格式进行处理，转成字典形式存储在列表中queryAns = []with open("qrels.txt", "r") as f: file = f.readlines() for line in file: query_dict = {} line = line.strip("\n") line = line.split(" ")