Neural Search Talks — Zeta Alpha

In this episode of Neural Search Talks, Andrew Yates (Assistant Prof at the University of Amsterdam) Sergi Castella (Analyst at Zeta Alpha), and Gabriel Bénédict (PhD student at the University of Amsterdam) discuss the prospect of using GPT-like models as a replacement for conventional search engines. Generative Information Retrieval (Gen IR) SIGIR Workshop Workshop organized by Gabriel Bénédict, Ruqing Zhang, and Donald Metzler https://coda.io/@sigir/gen-ir Resources on Gen IR: https://github.com/gabriben/awesome-generative-information-retrieval References Rethinking Search: https://arxiv.org/abs/2105.02274 Survey on Augmented Language Models: https://arxiv.org/abs/2302.07842 Differentiable Search Index: https://arxiv.org/abs/2202.06991 Recommender Systems with Generative Retrieval: https://shashankrajput.github.io/Generative.pdf Timestamps: 00:00 Introduction, ChatGPT Plugins 02:01 ChatGPT plugins, LangChain 04:37 What is even Information Retrieval? 06:14 Index-centric vs. model-centric Retrieval 12:22 Generative Information Retrieval (Gen IR) 21:34 Gen IR emerging applications 24:19 How Retrieval Augmented LMs incorporate external knowledge 29:19 What is hallucination? 35:04 Factuality and Faithfulness 41:04 Evaluating generation of Language Models 47:44 Do we even need to "measure" performance? 54:07 How would you evaluate Bing's Sydney? 57:22 Will language models take over commercial search? 1:01:44 NLP academic research in the times of GPT-4 1:06:59 Outro

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

Marzieh Fadaee, an NLP Research Lead at Zeta Alpha, discusses her innovative work on using large language models like GPT-3 to generate domain-specific training data. The conversation dives into her papers, 'InPars' and 'Promptagator,' highlighting methods for high-quality data augmentation with minimal human intervention. Fadaee explores the challenges of leveraging LMs in information retrieval, the intricacies of prompt engineering, and the potential pitfalls of synthetic data. Her insights pave the way for future research in optimizing neural retrieval systems.

Andrew Yates (Assistant Professor at the University of Amsterdam) and Sergi Castella (Analyst at Zeta Alpha) discus the two influential papers introducing ColBERT (from 2020) and ColBERT v2 (from 2022), which mainly propose a fast late interaction operation to achieve a performance close to full cross-encoders but at a more manageable computational cost at inference; along with many other optimizations. 📄 ColBERT: "ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT" by Omar Khattab and Matei Zaharia. https://arxiv.org/abs/2004.12832 📄 ColBERTv2: "ColBERTv2: Effective and Efficient Retrieval via Lightweight Late Interaction" by Keshav Santhanam, Omar Khattab, Jon Saad-Falcon, Christopher Potts, and Matei Zaharia. https://arxiv.org/abs/2112.01488 📄 PLAID: "An Efficient Engine for Late Interaction Retrieval" by Keshav Santhanam, Omar Khattab, Christopher Potts, and Matei Zaharia. https://arxiv.org/abs/2205.09707 📄 CEDR: "CEDR: Contextualized Embeddings for Document Ranking" by Sean MacAvaney, Andrew Yates, Arman Cohan, and Nazli Goharian. https://arxiv.org/abs/1904.07094 🪃 Feedback form: https://scastella.typeform.com/to/rg7a5GfJ Timestamps: 00:00 Introduction 00:42 Why ColBERT? 03:34 Retrieval paradigms recap 08:04 ColBERT query formulation and architecture 09:04 Using ColBERT as a reranker or as an end-to-end retriever 11:28 Space Footprint vs. MRR on MS MARCO 12:24 Methodology: datasets and negative sampling 14:37 Terminology for cross encoders, interaction-based models, etc. 16:12 Results (ColBERT v1) on MS MARCO 18:41 Ablations on model components 20:34 Max pooling vs. mean pooling 22:54 Why did ColBERT have a big impact? 26:31 ColBERTv2: knowledge distillation 29:34 ColBERTv2: indexing improvements 33:59 Effects of clustering compression in performance 35:19 Results (ColBERT v2): MS MARCO 38:54 Results (ColBERT v2): BEIR 41:27 Takeaway: strong specially in out-of-domain evaluation 43:59 Qualitatively how do ColBERT scores look like? 46:21 What's the most promising of all current neural IR paradigms 49:34 How come there's still so much interest in Dense retrieval? 51:09 Many to many similarity at different granularities 53:44 What would ColBERT v3 include? 56:39 PLAID: An Efficient Engine for Late Interaction Retrieval Contact: castella@zeta-alpha.com

How much of the training and test sets in TREC or MS Marco overlap? Can we evaluate on different splits of the data to isolate the extrapolation performance? In this episode of Neural Information Retrieval Talks, Andrew Yates and Sergi Castella i Sapé discuss the paper "Evaluating Extrapolation Performance of Dense Retrieval" byJingtao Zhan, Xiaohui Xie, Jiaxin Mao, Yiqun Liu, Min Zhang, and Shaoping Ma. 📄 Paper: https://arxiv.org/abs/2204.11447 ❓ About MS Marco: https://microsoft.github.io/msmarco/ ❓About TREC: https://trec.nist.gov/ 🪃 Feedback form: https://scastella.typeform.com/to/rg7a5GfJ   Timestamps:  00:00 Introduction  01:08 Evaluation in Information Retrieval, why is it exciting  07:40 Extrapolation Performance in Dense Retrieval  10:30 Learning in High Dimension Always Amounts to Extrapolation  11:40 3 Research questions  16:18 Defining Train-Test label overlap: entity and query intent overlap  21:00 Train-test Overlap in existing benchmarks TREC  23:29 Resampling evaluation methods: constructing distinct train-test sets  25:37 Baselines and results: ColBERT, SPLADE 29:36 Table 6: interpolation vs. extrapolation performance in TREC  33:06 Table 7: interplation vs. extrapolation in MS Marco  35:55 Table 8: Comparing different DR training approaches  40:00 Research Question 1 resolved: cross encoders are more robust than dense retrieval in extrapolation  42:00 Extrapolation and Domain Transfer: BEIR benchmark.  44:46 Figure 2: correlation between extrapolation performance and domain transfer performance  48:35 Broad strokes takeaways from this work  52:30 Is there any intuition behind the results where Dense Retrieval generalizes worse than Cross Encoders?  56:14 Will this have an impact on the IR benchmarking culture?  57:40 Outro    Contact: castella@zeta-alpha.com

Andrew Yates (Assistant Professor at the University of Amsterdam) and Sergi Castella i Sapé discuss the recent "Open Pre-trained Transformer (OPT) Language Models" from Meta AI (formerly Facebook). In this replication work, Meta developed and trained a 175 Billion parameter Transformer very similar to GPT-3 from OpenAI, documenting the process in detail to share their findings with the community. The code, pretrained weights, and logbook are available on their Github repository (links below).  Links  ❓Feedback Form: https://scastella.typeform.com/to/rg7a5GfJ 📄 OPT paper: https://arxiv.org/abs/2205.01068 👾 Code: https://github.com/facebookresearch/metaseq 📒 Logbook: https://github.com/facebookresearch/metaseq/blob/main/projects/OPT/chronicles/OPT175B_Logbook.pdf ✍️ OPT Official Blog Post: https://ai.facebook.com/blog/democratizing-access-to-large-scale-language-models-with-opt-175b/   OpenAI Embeddings API: https://openai.com/blog/introducing-text-and-code-embeddings/ Nils Reimers' critique of OpenAI Embeddings API: https://medium.com/@nils_reimers/openai-gpt-3-text-embeddings-really-a-new-state-of-the-art-in-dense-text-embeddings-6571fe3ec9d9  Timestamps:  00:00 Introduction and housekeeping: new feedback form, ACL conference highlights  02:42 The convergence between NLP and Neural IR techniques  06:43 Open Pretrained Transformer motivation and scope, reproducing GPT-3 and open-sourcing  08:16 Basics of OPT: architecture, pre-training objective, teacher forcing, tokenizer, training data  13:40 Preliminary experiments findings: hyperparameters, training stability, spikiness  20:08 Problems that appear at scale when training with 992 GPUs 23:01 Using temperature to check whether GPUs are working 25:00 Training the largest model: what to do when the loss explodes? (which happens quite often) 29:15 When they switched away from AdamW to SGD 32:00 Results: successful but not quite GPT-3 level. Toxicity? 35:45 Replicability of Large Language Models research. Was GPT-3 replicable? What difference does it make? 37:25 What makes a paper replicable? 40:33 Directions in which large Language Models are applied to Information Retrieval 45:15 Final thoughts and takeaways

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.  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 an explicit conversation to query rewriting step. Timestamps: 00:00 Introduction 00:50 Conversational AI and Conversational Search 05:40 What makes Conversational Search challenging 07:00 ConvDR paper introduction 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

Andrew Yates and Sergi Castella discuss the paper titled "Transformer Memory as a Differentiable Search Index" by Yi Tay et al at Google. This work proposes a new approach to document retrieval in which document ids are memorized by a transformer during training (or "indexing") and for retrieval, a query is fed to the model, which then generates autoregressively relevant doc ids for that query. Paper: https://arxiv.org/abs/2202.06991 Timestamps: 00:00 Intro: Transformer memory as a Differentiable Search Index (DSI) 01:15 The gist of the paper, motivation 4:20 Related work: Autoregressive Entity Linking 7:38 What is an index? Conventional vs. "differentiable" 10:20 Indexing and Retrieval definitions in the context of the DSI 12:40 Learning representations for documents 17:20 How to represent document ids: atomic, string, semantically relevant 22:00 Zero-shot vs. finetuned settings 24:10 Datasets and baselines 27:08 Dinetuned results 36:40 Zero-shot results 43:50 Ablation results 47:15 Where could this model be useds? 52:00 Is memory efficiency a fundamental problem of this approach? 55:14 What about semantically relevant doc ids? 60:30 Closing remarks  Contact: castella@zeta-alpha.com

In this third episode of the Neural Information Retrieval Talks podcast, Andrew Yates and Sergi Castella discuss the paper "Learning to Retrieve Passages without Supervision" by Ori Ram et al.   Despite the massive advances in Neural Information Retrieval in the past few years, statistical models still overperform neural models when no annotations are available at all. This paper proposes a new self-supervised pertaining task for Dense Information Retrieval that manages to beat BM25 on some benchmarks without using any label.   Paper: https://arxiv.org/abs/2112.07708  Timestamps: 00:00 Introduction 00:36 "Learning to Retrieve Passages Without Supervision" 02:20 Open Domain Question Answering 05:05 Related work: Families of Retrieval Models 08:30 Contrastive Learning 11:18 Siamese Networks, Bi-Encoders and Dual-Encoders 13:33 Choosing Negative Samples 17:46 Self supervision: how to train IR models without labels. 21:31 The modern recipe for SOTA Retrieval Models 23:50 Methodology: a new proposed self supervision task 26:40 Datasets, metrics and baselines \33:50 Results: Zero-Shot performance 43:07 Results: Few-shot performance 47:15 Practically, is not using labels relevant after all? 51:37 How would you "break" the Spider model? 53:23 How long until Neural IR models outperform BM25 out-of-the-box robustly? 54:50 Models as a service: OpenAI's text embeddings API Contact: castella@zeta-alpha.com

We discuss the Information Retrieval publication "The Curse of Dense Low-Dimensional Information Retrieval for Large Index Sizes" by Nils Reimers and Iryna Gurevych, which explores how Dense Passage Retrieval performance degrades as the index size varies and how it compares to traditional sparse or keyword-based methods. Timestamps: 00:00 Co-host introduction 00:26 Paper introduction 02:18 Dense vs. Sparse retrieval 05:46 Theoretical analysis of false positives(1) 08:17 What is low vs. high dimensional representations 11:49 Theoretical analysis o false positives (2) 20:10 First results: growing the MS-Marco index 28:35 Adding random strings to the index 39:17 Discussion, takeaways 44:26 Will dense retrieval replace or coexist with sparse methods? 50:50 Sparse, Dense and Attentional Representations for Text Retrieval Referenced work: Sparse, Dense and Attentional Representations for Text Retrieval by Yi Luan et al. 2020.