Filtering out "forbidden" documents during information retrieval

New method optimizes the twin demands of retrieving relevant content and filtering out bad content.

Content owners make a lot of effort to eliminate bad content that may adversely affect their customers. Bad content can take many forms, such as fake news, paid reviews, spam, offensive language, etc. We call such data items (documents) forbidden docs, or f-docs, for short.

Any data-cleaning process, however, is susceptible to errors. No matter how much effort goes into the cleaning process, some bad content might remain. This week at the annual meeting of the ACM Special Interest Group on Information Retrieval (SIGIR), the Alexa Shopping research team presented a paper on information retrieval (IR) in the presence of f-docs. In particular, we’re trying to optimize the twin demands of retrieving content relevant to customer requests and filtering out f-docs.

For example, consider a question posed on a community question-answering (CQA) site, where our goal is to rank answers according to their quality and relevance while filtering out bad ones. The next table presents some answers to the question “Is the Brand X sports watch waterproof?” While some of the answers are helpful, or at least fair, there are a few that should not be exposed to our users as they significantly hurt the search experience.

Forbidden docs.png
A new metric enables information retrieval models to jointly optimize the ordering of query results and the filtration of "forbidden" content.

Filtering algorithms, however, are prone to two types of errors: (1) false positives (i.e., filtering non-f-docs) and (2) false negatives (i.e., including f-docs in the results).

Typically, ranking quality and filtering accuracy are measured independently. However, the number of f-docs left in the ranked list after filtering and their ranking positions heavily affect both the ranking score and the filtering score. Therefore, it is desirable to evaluate the system’s ranking quality as filtering decisions are being made.

The right metric

We look for an evaluation metric that reinforces a ranker according to three criteria: it (1) prunes as many f-docs from the retrieved list as possible; (2) does not prune non-f-docs from the list; and (3) ranks remaining docs according to their relevance to the query while pushing f-docs down the list.

In our paper, my colleagues Nachshon Cohen, Amir Ingber, Elad Kravi, and I analyze the types of metrics that can be used to measure the ranking and filtering quality of the search results. The natural choice is normalized discounted cumulative gain (nDCG), a metric that discounts the relevance of results that appear further down the list; that is, it evaluates a ranking algorithm according to both relevance and rank ordering.

Related content
Locality-sensitive hashing enables cache to hold more than three times as many query results.

With nDCG, relevant labels are associated with positive scores, non-relevant labels with a zero score, and the “forbidden labels” with negative scores. The nDCG score sums the scores of the individual list items, so the score for a ranked list containing f-docs will reflect the number of f-docs in the list, their relative positions in the ranking, and their degree of forbiddenness.

NDCG differs from the ordinary DCG (discounted cumulative gain) score in that the results are normalized by the DCG score of the ideal ranked list — the list ranked according to the ground truth labels. It can be interpreted as a distance between the given rank and the ideal rank.

When all label scores are non-negative — i.e,. no f-docs are among the top k documents in the results — nDCG is bounded in the range [0, 1], where 0 means that all search results are non-relevant, while 1 means that the ranking is ideal.

However, in the presence of negatively scored labels, nDCG is unbounded and therefore unreliable. For instance, unboundedness may lead to extreme over- or undervaluation on some queries, with disproportionate effect on the average metric score.

The nDCGmin metric, a modification of nDCG suggested by Gienapp et al. at CIKM’20, solves this unboundedness problem for the case of negatively scored labels. It measures the DCG scores of both the worst possible ranked list (the reverse of the ideal ranked list) and the ideal list and then performs min-max normalization with these two extreme scores.

Related content
Method using hyperboloid embeddings improves on methods that use vector embeddings by up to 33%.

However, we show in our paper that when ranking and filtering are carried out together — i.e., when the ranker is allowed to retrieve (and to rank) a sublist of the search results — nDCGmin becomes unbounded. As an alternative, we propose nDCGf, a modification of nDCGmin that solves this second unboundedness problem by modifying the normalization scheme in order to handle sublist retrieval.

In particular, nDCGf measures the DCG score of the ideal and the worst sublists over all possible sublists of the results list and then uses the extreme scores of these sublists for min-max normalization.

We show both theoretically and empirically that while nDCGmin is not suitable for the evaluation task of simultaneous ranking and filtering, nDCGf is a reliable metric. Reliability is a standard measure of a metric’s ability to capture the actual difference in performance among rankers, by measuring deviation stability over a test-set of queries.

The next figure shows the reliability of nDCG, nDCGmin, and nDCGf over datasets released for the web-track information retrieval challenge at the Text Retrieval Conference (TREC) for the years 2010-2014. For all years, the reliability of nDCG and nDCGmin is significantly lower than that of nDCGf, due to their improper normalization when negative labels and partial retrieval are allowed.

Metric reliability.png
Reliability of nDCG, nDCGmin, and nDCGf over TREC Web-track datasets for the years 2010–2014.

Model building

After establishing the relevant metric, our paper then shifts focus to jointly learning to rank and filter (LTRF). We assume an LTRF model that optimizes the ranking of the search results while also tuning a filtering threshold such that any document whose score is below this threshold is filtered out.

We experiment with two tasks for which both ranking and filtering are required, using two datasets we compiled: PR (for product reviews) and CQA (for community question answering). We have publicly released the CQA dataset to support further research by the IR community on LTRF tasks.

Related content
A new metric-learning loss function groups together superclasses and learns commonalities within them.

In the PR dataset, our task is to rank product reviews according to their helpfulness while filtering those marked as spam. Similarly, in the CQA dataset our task is to rank lists of human answers to particular questions while filtering bad answers. We show that both ranking only and filtering only fail to provide high-quality ranked-and-filtered lists, measured by nDCGf score.

A key component for model training in any learning-to-rank framework is the loss function to be optimized, which determines the “loss” of the current model with respect to an optimal model. We experiment with several loss functions for model training for the two tasks, demonstrating their success in producing effective LTRF models for the simultaneous-learning-and-filtering task.

LTRF is a new research direction that poses many challenges that deserve further investigation. While our LTRF models succeed at ranking and filtering, the volume of f-docs in the retrieved lists is still too high. Improving the LTRF models is an open challenge, and we hope that our work will encourage other researchers to tackle it.

Related content

US, WA, Seattle
Note that this posting is for a handful of teams within Amazon Robotics. Teams include: Robotics, Computer Vision, Machine Learning, Optimization, and more.Are you excited about building high-performance robotic systems that can perceive and learn to help deliver for customers? The Amazon Robotics team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.Amazon Robotics is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. We will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. Come join us!A day in the lifeAs an intern you will develop a new algorithm to solve one of the challenging computer vision and manipulation problems in Amazon's robotic warehouses. Your project will fit your academic research experience and interests. You will code and test out your solutions in increasingly realistic scenarios and iterate on the idea with your mentor to find the best solution to the problem.
US, WA, Bellevue
The Global Supply Chain-ACES organization aims to raise the bar on Amazon’s customer experience by delivering holistic solutions for Global Customer Fulfillment that facilitate the effective and efficient movement of product through our supply chain. We develop strategies, processes, material handling and technology solutions, reporting and other mechanisms, which are simple, technology enabled, globally scalable, and locally relevant. We achieve this through cross-functional partnerships, listening to the needs of our customers and prioritizing initiatives to deliver maximum impact across the value chain. Within the organization, our Quality team balances tactical operation with operations partners with global engagement on programs to deliver improved inventory accuracy in our network. The organization is looking for an experienced Principal Data Scientist to partner with senior leadership to develop long term strategic solutions. As a Principal Scientist, they will lead critical initiatives for Global Supply Chain, leveraging complex data analysis and visualization to:a. Collaborate with business teams to define data requirements and processes;b. Automate data pipelines;c. Design, develop, and maintain scalable (automated) reports and dashboards that track progress towards plans;d. Define, track and report program success metrics.e. Serve as a technical science lead on our most demanding, cross-functional projects.
US, MA, North Reading
Are you inspired by invention? Is problem solving through teamwork in your DNA? Do you like the idea of seeing how your work impacts the bigger picture? Answer yes to any of these and you’ll fit right in here at Amazon Robotics. We are a smart team of doers that work passionately to apply cutting edge advances in robotics and software to solve real-world challenges that will transform our customers’ experiences in ways we can’t even imagine yet. We invent new improvements every day. We are Amazon Robotics and we will give you the tools and support you need to invent with us in ways that are rewarding, fulfilling and fun. The Research Science team at Amazon Robotics is seeking interns with a passion for robotic research to work on cutting edge algorithms for robotics. Our team works on challenging and high-impact projects, including allocating resources to complete a million orders a day, coordinating the motion of thousands of robots, autonomous navigation in warehouses, and learning how to grasp all the products Amazon sells. We are seeking internship candidates with backgrounds in computer vision, machine learning, resource allocation, discrete optimization, search, planning/scheduling, and reinforcement learning. As an intern you will develop a new algorithm to solve one of the challenging computer vision and manipulation problems in Amazon's robotic warehouses. Your project will fit your academic research experience and interests. You will code and test out your solutions in increasingly realistic scenarios and iterate on the idea with your mentor to find the best solution to the problem.
US, WA, Seattle
Are you excited about building high-performance robotic systems that can perceive, learn, and act intelligently alongside humans? The Robotics AI team is creating new science products and technologies that make this possible, at Amazon scale. We work at the intersection of computer vision, machine learning, robotic manipulation, navigation, and human-robot interaction.The Amazon Robotics team is seeking broad, curious applied scientists and engineering interns to join our diverse, full-stack team. In addition to designing, building, and delivering end-to-end robotic systems, our team is responsible for core infrastructure and tools that serve as the backbone of our robotic applications, enabling roboticists, applied scientists, software and hardware engineers to collaborate and deploy systems in the lab and in the field. Come join us!
US, WA, Bellevue
Employer: Amazon.com Services LLCPosition: Research Scientist IILocation: Bellevue, WA Multiple Positions Available1. Research, build and implement highly effective and innovative methods in Statistical Modeling, Machine Learning, and other quantitative techniques such as operational research and optimization to deliver algorithms that solve real business problems.2. Take initiative to scope and plan research projects based on roadmap of business owners and enable data-driven solutions. Participate in shaping roadmap for the research team.3. Ensure data quality throughout all stages of acquisition and processing of the data, including such areas as data sourcing/collection, ground truth generation, data analysis, experiment, evaluation and visualization etc.4. Navigate a variety of data sources, understand the business reality behind large-scale data and develop meaningful science solutions.5. Partner closely with product or/and program owners, as well as scientists and engineers in cross-functional teams with a clear path to business impact and deliver on demanding projects.6. Present proposals and results in a clear manner backed by data and coupled with conclusions to business customers and leadership team with various levels of technical knowledge, educating them about underlying systems, as well as sharing insights.7. Perform experiments to validate the feature additions as requested by domain expert teams.8. Some telecommuting benefits available.The pay range for this position in Bellevue, WA is $136,000-$184,000 (yr); however, base pay offered may vary depending on job-related knowledge, skills, and experience. A sign-on bonus and restricted stock units may be provided as part of the compensation package, in addition to a full range of medical, financial, and/or other benefits, dependent on the position offered. This information is provided by the Washington Equal Pay Act. Base pay information is based on market location. Applicants should apply via Amazon's internal or external careers site.#0000
US, VA, Arlington
The Central Science Team within Amazon’s People Experience and Technology org (PXTCS) uses economics, behavioral science, statistics, and machine learning to proactively identify mechanisms and process improvements which simultaneously improve Amazon and the lives, well-being, and the value of work to Amazonians. We are an interdisciplinary team, which combines the talents of science and engineering to develop and deliver solutions that measurably achieve this goal. As Director for PXT Central Science Technology, you will be responsible for leading multiple teams through rapidly evolving complex demands and define, develop, deliver and execute on our science roadmap and vision. You will provide thought leadership to scientists and engineers to invent and implement scalable machine learning recommendations and data driven algorithms supporting flexible UI frameworks. You will manage and be responsible for delivering some of our most strategic technical initiatives. You will design, develop and operate new, highly scalable software systems that support Amazon’s efforts to be Earth’s Best Employer and have a significant impact on Amazon’s commitment to our employees and communities where we both serve and employ 1.3 million Amazonians. As Director of Applied Science, you will be part of the larger technical leadership community at Amazon. This community forms the backbone of the company, plays a critical role in the broad business planning, works closely with senior executives to develop business targets and resource requirements, influences our long-term technical and business strategy, helps hire and develop engineering leaders and developers, and ultimately enables us to deliver engineering innovations.This role is posted for Arlington, VA, but we are flexible on location at many of our offices in the US and Canada.
US, VA, Arlington
Employer: Amazon.com Services LLCPosition: Data Scientist IILocation: Arlington, VAMultiple Positions Available1. Manage and execute entire projects or components of large projects from start to finish including data gathering and manipulation, synthesis and modeling, problem solving, and communication of insights and recommendations.2. Oversee the development and implementation of data integration and analytic strategies to support population health initiatives.3. Leverage big data to explore and introduce areas of analytics and technologies.4. Analyze data to identify opportunities to impact populations.5. Perform advanced integrated comprehensive reporting, consultative, and analytical expertise to provide healthcare cost and utilization data and translate findings into actionable information for internal and external stakeholders.6. Oversee the collection of data, ensuring timelines are met, data is accurate and within established format.7. Act as a data and technical resource and escalation point for data issues, ensuring they are brought to resolution.8. Serve as the subject matter expert on health care benefits data modeling, system architecture, data governance, and business intelligence tools. #0000
US, TX, Dallas
Employer: Amazon.com Services LLCPosition: Data Scientist II (multiple positions available)Location: Dallas, TX Multiple Positions Available:1. Assist customers to deliver Machine Learning (ML) and Deep Learning (DL) projects from beginning to end, by aggregating data, exploring data, building and validating predictive models, and deploying completed models to deliver business impact to the organization;2. Apply understanding of the customer’s business need and guide them to a solution using AWS AI Services, AWS AI Platforms, AWS AI Frameworks, and AWS AI EC2 Instances;3. Use Deep Learning frameworks like MXNet, PyTorch, Caffe 2, Tensorflow, Theano, CNTK, and Keras to help our customers build DL models;4. Research, design, implement and evaluate novel computer vision algorithms and ML/DL algorithms;5. Work with data architects and engineers to analyze, extract, normalize, and label relevant data;6. Work with DevOps engineers to help customers operationalize models after they are built;7. Assist customers with identifying model drift and retraining models;8. Research and implement novel ML and DL approaches, including using FPGA;9. Develop computer vision and machine learning methods and algorithms to address real-world customer use-cases; and10. Design and run experiments, research new algorithms, and work closely with engineers to put algorithms and models into practice to help solve customers' most challenging problems.11. Approximately 15% domestic and international travel required.12. Telecommuting benefits are available.#0000
US, WA, Seattle
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Manager III, Data ScienceLocation: Bellevue, WashingtonPosition Responsibilities:Manage a team of data scientists working to build large-scale, technical solutions to increase effectiveness of Amazon Fulfillment systems. Define key business goals and map them to the success of technical solutions. Aggregate, analyze and model data from multiple sources to inform business decisions. Manage and quantify improvement in the customer experience resulting from research outcomes. Develop and manage a long-term research vision and portfolio of research initiatives, with algorithms and models that to be integrated in production systems. Hire and mentor junior scientists.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000
US, VA, Arlington
MULTIPLE POSITIONS AVAILABLECompany: AMAZON.COM SERVICES LLCPosition Title: Data Scientist IILocation: Arlington, VirginiaPosition Responsibilities:Design and implement scalable and reliable approaches to support or automate decision making throughout the business. Apply a range of data science techniques and tools combined with subject matter expertise to solve difficult business problems and cases in which the solution approach is unclear. Acquire data by building the necessary SQL / ETL queries. Import processes through various company specific interfaces for accessing Oracle, RedShift, and Spark storage systems. Build relationships with stakeholders and counterparts. Analyze data for trends and input validity by inspecting univariate distributions, exploring bivariate relationships, constructing appropriate transformations, and tracking down the source and meaning of anomalies. Build models using statistical modeling, mathematical modeling, econometric modeling, network modeling, social network modeling, natural language processing, machine learning algorithms, genetic algorithms, and neural networks. Validate models against alternative approaches, expected and observed outcome, and other business defined key performance indicators. Implement models that comply with evaluations of the computational demands, accuracy, and reliability of the relevant ETL processes at various stages of production.Amazon.com is an Equal Opportunity-Affirmative Action Employer – Minority / Female / Disability / Veteran / Gender Identity / Sexual Orientation #0000