This month, we released Facebook AI Similarity Search (Faiss), a library that allows us to quickly search for multimedia documents that are similar to each other -- a challenge where traditional query search engines fall short. We've built nearest-neighbor search implementations for billion-scale data sets that are some 8.5x faster than the previous reported state-of-the-art, along with the fastest k-selection algorithm on the GPU known in the literature. This lets us break some records, including the first k-nearest-neighbor graph constructed on 1 billion high-dimensional vectors. Traditional databases are made up of structured tables containing symbolic information. For example, an image collection would be represented as a table with one row per indexed photo.

In this paper, we address the problem of answering complex information needs by conversing conversations with search engines, in the sense that users can express their queries in natural language, and directly receivethe information they need from a short system response in a conversational manner. Recently, there have been some attempts towards a similar goal, e.g., studies on Conversational Agents (CAs) and Conversational Search (CS). However, they either do not address complex information needs, or they are limited to the development of conceptual frameworks and/or laboratory-based user studies. We pursue two goals in this paper: (1) the creation of a suitable dataset, the Search as a Conversation (SaaC) dataset, for the development of pipelines for conversations with search engines, and (2) the development of astate-of-the-art pipeline for conversations with search engines, the Conversations with Search Engines (CaSE), using this dataset. SaaC is built based on a multi-turn conversational search dataset, where we further employ workers from a crowdsourcing platform to summarize each relevant passage into a short, conversational response. CaSE enhances the state-of-the-art by introducing a supporting token identification module and aprior-aware pointer generator, which enables us to generate more accurate responses. We carry out experiments to show that CaSE is able to outperform strong baselines. We also conduct extensive analyses on the SaaC dataset to show where there is room for further improvement beyond CaSE. Finally, we release the SaaC dataset and the code for CaSE and all models used for comparison to facilitate future research on this topic.

Imagine a collection of books--maybe millions or even billions of them--haphazardly tossed by publishers into a heaping pile in a field. Every day the pile grows exponentially. Those books are brimming with knowledge and answers. But how would a seeker find them? Lacking organization, the books are useless. This is the raw internet in all its unfiltered glory.

In this paper, we introduce a novel approach named TopicsRanksDC for topics ranking based on the distance between two clusters that are generated by each topic. We assume that our data consists of text documents that are associated with two-classes. Our approach ranks each topic contained in these text documents by its significance for separating the two-classes. Firstly, the algorithm detects topics using Latent Dirichlet Allocation (LDA). The words defining each topic are represented as two clusters, where each one is associated with one of the classes. We compute four distance metrics, Single Linkage, Complete Linkage, Average Linkage and distance between the centroid. We compare the results of LDA topics and random topics. The results show that the rank for LDA topics is much higher than random topics. The results of TopicsRanksDC tool are promising for future work to enable search engines to suggest related topics.

In real-world search, recommendation, and advertising systems, the multi-stage ranking architecture is commonly adopted. Such architecture usually consists of matching, pre-ranking, ranking, and re-ranking stages. In the pre-ranking stage, vector-product based models with representation-focused architecture are commonly adopted to account for system efficiency. However, it brings a significant loss to the effectiveness of the system. In this paper, a novel pre-ranking approach is proposed which supports complicated models with interaction-focused architecture. It achieves a better tradeoff between effectiveness and efficiency by utilizing the proposed learnable Feature Selection method based on feature Complexity and variational Dropout (FSCD). Evaluations in a real-world e-commerce sponsored search system for a search engine demonstrate that utilizing the proposed pre-ranking, the effectiveness of the system is significantly improved. Moreover, compared to the systems with conventional pre-ranking models, an identical amount of computational resource is consumed.

Now a team of Google researchers has published a proposal for a radical redesign that throws out the ranking approach and replaces it with a single large AI language model, such as BERT or GPT-3--or a future version of them. The idea is that instead of searching for information in a vast list of web pages, users would ask questions and have a language model trained on those pages answer them directly. Search engines have become faster and more accurate, even as the web has exploded in size. AI is now used to rank results, and Google uses BERT to understand search queries better. Yet beneath these tweaks, all mainstream search engines still work the same way they did 20 years ago: web pages are indexed by crawlers (software that reads the web nonstop and maintains a list of everything it finds), results that match a user's query are gathered from this index, and the results are ranked.

Societal biases resonate in the retrieved contents of information retrieval (IR) systems, resulting in reinforcing existing stereotypes. Approaching this issue requires established measures of fairness in respect to the representation of various social groups in retrieval results, as well as methods to mitigate such biases, particularly in the light of the advances in deep ranking models. In this work, we first provide a novel framework to measure the fairness in the retrieved text contents of ranking models. Introducing a ranker-agnostic measurement, the framework also enables the disentanglement of the effect on fairness of collection from that of rankers. To mitigate these biases, we propose AdvBert, a ranking model achieved by adapting adversarial bias mitigation for IR, which jointly learns to predict relevance and remove protected attributes. We conduct experiments on two passage retrieval collections (MSMARCO Passage Re-ranking and TREC Deep Learning 2019 Passage Re-ranking), which we extend by fairness annotations of a selected subset of queries regarding gender attributes. Our results on the MSMARCO benchmark show that, (1) all ranking models are less fair in comparison with ranker-agnostic baselines, and (2) the fairness of Bert rankers significantly improves when using the proposed AdvBert models. Lastly, we investigate the trade-off between fairness and utility, showing that we can maintain the significant improvements in fairness without any significant loss in utility.

Conversational agent (CA) systems have been applied to healthcare domain, but there is no such a system to answer consumers regarding DS use, although widespread use of DS. In this study, we develop the first CA system for DS use. Methods: Our CA system for DS use developed on the MindeMeld framework, consists of three components: question understanding, DS knowledge base, and answer generation. We collected and annotated 1509 questions to develop natural language understanding module (e.g., question type classifier, named entity recognizer) which was then integrated into MindMeld framework. CA then queries the DS knowledge base (i.e., iDISK) and generates answers using rule-based slot filling techniques. We evaluated algorithms of each component and the CA system as a whole. Results: CNN is the best question classifier with F1 score of 0.81, and CRF is the best named entity recognizer with F1 score of 0.87. The system achieves an overall accuracy of 81% and an average score of 1.82 with succ@3 score as 76.2% and succ@2 as 66% approximately. Conclusion: This study develops the first CA system for DS use using MindMeld framework and iDISK domain knowledge base.

TL;DR: Neural Search is a new approach to retrieving information using neural networks. Traditional techniques to search typically meant writing rules to "understand" the data being searched and return the best results. But with neural search, developers don't need to wrack their brains for these rules; The system learns the rules by itself and gets better as it goes along. Even developers who don't know machine learning can quickly build a search engine using open-source frameworks such as Jina. There is a massive amount of data on the web; how can we effectively search through it for relevant information?

Evaluation efforts such as TREC, CLEF, NTCIR and FIRE, alongside public leaderboard such as MS MARCO, are intended to encourage research and track our progress, addressing big questions in our field. However, the goal is not simply to identify which run is "best", achieving the top score. The goal is to move the field forward by developing new robust techniques, that work in many different settings, and are adopted in research and practice. This paper uses the MS MARCO and TREC Deep Learning Track as our case study, comparing it to the case of TREC ad hoc ranking in the 1990s. We show how the design of the evaluation effort can encourage or discourage certain outcomes, and raising questions about internal and external validity of results. We provide some analysis of certain pitfalls, and a statement of best practices for avoiding such pitfalls. We summarize the progress of the effort so far, and describe our desired end state of "robust usefulness", along with steps that might be required to get us there.