Artwork

Konten disediakan oleh Zeta Alpha. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh Zeta Alpha atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.player.fm/legal.
Player FM - Aplikasi Podcast
Offline dengan aplikasi Player FM !

Task-aware Retrieval with Instructions

1:11:13
 
Bagikan
 

Manage episode 355037182 series 3446693
Konten disediakan oleh Zeta Alpha. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh Zeta Alpha atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.player.fm/legal.

Andrew Yates (Assistant Prof 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

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

  continue reading

13 episode

Artwork
iconBagikan
 
Manage episode 355037182 series 3446693
Konten disediakan oleh Zeta Alpha. Semua konten podcast termasuk episode, grafik, dan deskripsi podcast diunggah dan disediakan langsung oleh Zeta Alpha atau mitra platform podcast mereka. Jika Anda yakin seseorang menggunakan karya berhak cipta Anda tanpa izin, Anda dapat mengikuti proses yang diuraikan di sini https://id.player.fm/legal.

Andrew Yates (Assistant Prof 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

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

  continue reading

13 episode

Semua episode

×
 
Loading …

Selamat datang di Player FM!

Player FM memindai web untuk mencari podcast berkualitas tinggi untuk Anda nikmati saat ini. Ini adalah aplikasi podcast terbaik dan bekerja untuk Android, iPhone, dan web. Daftar untuk menyinkronkan langganan di seluruh perangkat.

 

Panduan Referensi Cepat