In this episode of Neural Search Talks, we discuss Conversational Search with our usual cohosts Andrew Yates and Sergi Castella i Sapé; along with a special guest Antonios Minas Krasakis, PhD candidate at the University of Amsterdam specializing in Conversational Search.
We center our discussion around the ConvDR paper: "Few-Shot Conversational Dense Retrieval" by Shi Yu et al. which was the first work to perform Conversational Search without relying on an explicit conversation-to-query rewriting step.
Listen on other platforms: https://anchor.fm/neural-ir-talks/episodes/Few-Shot-Conversational-Dense-Retrieval-ConvDR-w-special-guest-Antonios-Krasakis-e1ib7l1
Timestamps:
00:00 Introduction
00:50 Conversational AI and Conversational Search
05:40 What makes Conversational Search challenging
10:10 Passage representations
11:30 Conversation representations: query rewriting
19:12 ConvDR novel proposed method: teacher-student setup with ANCE
22:50 Datasets and benchmarks: CAsT, CANARD
25:32 Teacher-student advantages and knowledge distillation vs. ranking loss functions
28:09 TREC CAsT and OR-QuAC
35:50 Metrics: MRR, NDCG, holes@10
44:16 Main Results on CAsT and OR-QuAC (Table 2)
57:35 Ablations on combinations of loss functions (Table 4)
1:00:10 How fast is ConvDR? (Table 3)
1:02:40 Qualitative analysis on ConvDR embeddings (Figure 4)
1:04:50 How has this work aged? More recent works in similar directions: Contextualized Quesy Embeddings for Conversational Search.
1:07:02 Is "end-to-end" the silver-bullet for Conversational Search?
1:10:04 Will conversational search become more mainstream?
1:18:44 Latest initiatives for Conversational Search