In this episode of Neural Search Talks, Andrew Yates (Assistant Professor at University of Amsterdam) and Sergi Castella (Analyst at Zeta Alpha) discuss the paper "Task-aware Retrieval with Instructions" by Akari Asai et al. This paper proposes to augment a conglomerate of existing retrieval and NLP datasets with natural language instructions (BERRI, Bank of Explicit RetRieval Instructions) and use it to train TART (Multi-task Instructed Retriever).
📄 Paper: https://arxiv.org/abs/2211.09260
🍻 BEIR benchmark: https://arxiv.org/abs/2104.08663
📈 LOTTE (Long-Tail Topic-stratified Evaluation, introduced in ColBERT v2): https://arxiv.org/abs/2112.01488
🔊 Audio-only podcast: https://anchor.fm/neural-ir-talks/episodes/Task-aware-Retrieval-with-Instructions-e1u31ct
Timestamps:
00:00 Intro: "Task-aware Retrieval with Instructions"
02:20 BERRI, TART, X^2 evaluation
04:00 Background: recent works in domain adaptation
06:50 Instruction Tuning
08:50 Retrieval with descriptions
11:30 Retrieval with instructions
17:28 BERRI, Bank of Explicit RetRieval Instructions
21:48 Repurposing NLP tasks as retrieval tasks
23:53 Negative document selection
27:47 TART, Multi-task Instructed Retriever
31:50 Evaluation: Zero-shot and X^2 evaluation
39:20 Results on Table 3 (BEIR, LOTTE)
50:30 Results on Table 4 (X^2-Retrieval)
55:50 Ablations
57:17 Discussion: user modeling, future work, scale
ความคิดเห็น