How to teach Transformers to care about word order

New position encoding scheme improves state-of-the-art performance on several natural-language-processing tasks.

The Transformer is a neural-network architecture that has proven extremely useful for natural-language-processing tasks because it can recognize long-range dependencies. It could, for instance, recognize that in a sentence that includes the word “rented”, the word “flat” is more likely to mean “apartment” than it would be otherwise, even if “rented” is the second word in the sentence and “flat” the 10th.

In its most basic form, the Transformer is indifferent to word order. It can recognize the relationship between “rented” and “flat”, but it doesn’t care which comes first.

Word order, however, can make a big difference to meaning. Consider, for instance, the sentences “We rented a small but clean, well-equipped two-bed flat” and “We rented a small but clean, well-equipped flat-bed truck”.

Position embedding.png
These images map 252 words of an input text sequence (y-axis) against the 512 latent position features identified by two different position-encoding schemes. Lighter colors indicate higher values for features, darker colors lower values. FLOATER (bottom) produces a more regular encoding than an earlier scheme (top), which also learns its position feature set from training data. The vertical lines toward the bottom of the top visualization indicate that the encoding model is simply using the same encoding for input sequences longer than those it saw during training, while FLOATER’s smooth gradation from light to dark demonstrates that its encoding generalizes easily to longer sequences.

Starting with the paper that introduced the Transformer, researchers have proposed a series of position encoders that inject word-order information into the Transformer model. But last week, at the International Conference on Machine Learning, we presented a new position encoder that enables better performance than its predecessors on a range of natural-language-processing (NLP) tasks.

We designed our position encoder so that it can be integrated into existing Transformer models, conferring its benefits to NLP systems that already have been trained extensively on large data sets.

Before the Transformer was introduced in 2017, the most popular architecture for NLP was the long short-term memory, or LSTM. LSTMs process sequenced inputs in order, and each output reflects both the inputs and the outputs that preceded it.

LSTMs are very good at inferring local relationships — a word’s relationships, both syntactic and semantic, with the two or three words that immediately precede it — but they’re not as good at modeling long-range dependencies. That’s where the Transformer excels.

Position encodings are an attempt to achieve the best of both worlds: an awareness of long-range dependencies and a sensitivity to local word order. The ideal position encoding should have three properties:

  1. It should be able to handle sequences of arbitrary length; that is, it shouldn’t be locked in to some maximum sequence length.
  2. It should be learnable from training data; different encodings may work better for different tasks.
  3. It should be efficient; adding position encoding shouldn’t unreasonably inflate the size of the neural model.

Past position encoding schemes have met at best two of these criteria. For instance, the original Transformer paper proposed an encoding based on a family of sinusoidal functions; that encoding remains popular, but it is not learnable.

Our scheme, which we call FLOATER, is the first to meet all three criteria.

The naïve way to encode position would be simply to assign successive numbers to successive words in an input sequence. But this has drawbacks in a machine learning context. If at runtime the model sees a sequence of a length it did not encounter during training, it will be flummoxed about how to proceed.

So most position encoding schemes instead use position vectors, which carry information that can be used to deduce the relative positions of two inputs. If those schemes are fully learnable, however, they tend to inflate the model size; or, to keep model inflation under control, they limit the distances across which relative position can be compared.

Functional approach

Instead of learning to directly compute a position vector from each word in an input sequence, FLOATER learns a function that computes each word’s position vector from that of the word that preceded it.

Learning a general function rather than direct mappings makes FLOATER much more space efficient than other learnable encoding schemes. But a general function can also be applied to any word in a sequence, regardless of its position, so FLOATER is indifferent to sequence length.

Any given manually engineered position function — such as the sinusoidal functions proposed in the original Transformer paper — can be thought of as a special case of the general FLOATER function. So in a pretrained network, we can simply substitute FLOATER for any such function and then fine-tune it on a small set of training data.

Past work on position encoding has shown that re-encoding position information at every layer of a Transformer network improves performance on NLP tasks. If we allowed FLOATER to learn a different function for every layer, the model size would again begin to inflate.

So instead, we learn a single function that is applied at every layer. This results in different position encodings at each layer, however, because the inputs are different. Our experiments indicate that this approach strikes a good balance between model size and performance improvements.

In one set of experiments, we compared our position encoder to its two leading predecessors on four different machine translation tasks and found that it delivered the best results across the board.

In another set of experiments, we added our position encoder to Transformer models that had previously been trained on three different language-understanding and question-answering tasks.

Of 23 distinct tasks, the addition of our position encoder improved performance on 21. The two on which its performance fell slightly short were low-data versions of tasks on which, with larger sets of training data, it improved performance.

Related content

US, MA, North Reading
Are you excited about developing generative AI and foundation models to revolutionize automation, robotics and computer vision? Are you looking for opportunities to build and deploy them on real problems at truly vast scale? At Amazon Fulfillment Technologies and Robotics we are on a mission to build high-performance autonomous systems that perceive and act to further improve our world-class customer experience - at Amazon scale. We are looking for scientists, engineers and program managers for a variety of roles. The Research team at Amazon Robotics is seeking a passionate, hands-on Sr. Applied Scientist to help create the world’s first foundation model for a many-robot system. The focus of this position is how to predict the future state of our warehouses that feature a thousand or more mobile robots in constant motion making deliveries around the building. It includes designing, training, and deploying large-scale models using data from hundreds of warehouses under different operating conditions. This work spans from research such as alternative state representations of the many-robot system for training, to experimenting using simulation tools, to running large-scale A/B tests on robots in our facilities. Key job responsibilities * Research vision - Where should we be focusing our efforts * Research delivery - Proving/dis-proving strategies in offline data or in simulation * Production studies - Insights from production data or ad-hoc experimentation * Production implementation - Building key parts of deployed algorithms or models About the team You would join our multi-disciplinary science team that includes scientists with backgrounds in planning and scheduling, grasping and manipulation, machine learning, and operations research. We develop novel planning algorithms and machine learning methods and apply them to real-word robotic warehouses, including: - Planning and coordinating the paths of thousands of robots - Dynamic allocation and scheduling of tasks to thousands of robots - Learning how to adapt system behavior to varying operating conditions - Co-design of robotic logistics processes and the algorithms to optimize them Our team also serves as a hub to foster innovation and support scientists across Amazon Robotics. We also coordinate research engagements with academia, such as the Robotics section of the Amazon Research Awards. We are open to hiring candidates to work out of one of the following locations: North Reading, MA, USA | Westborough, MA, USA
US, WA, Bellevue
Are you excited about developing state-of-the-art deep learning foundation models, applied to the automation of labor for the future of Amazon’s Fulfillment network? Are you looking for opportunities to build and deploy them on real problems at truly vast scale? At Amazon Fulfillment Technologies and Robotics we are on a mission to build high-performance autonomous systems that perceive and act to further improve our world-class customer experience - at Amazon scale. To this end, we are looking for an Applied Scientist who will build and deploy models that help automate labor utilizing a wide array of multi-modal signals. Together, we will be pushing beyond the state of the art in optimization of one of the most complex systems in the world: Amazon's Fulfillment Network. Key job responsibilities In this role, you will build models that can identify potential problems with Amazon’s vast inventory, including discrepancies between the physical and virtual manifest and efficient execution of inventory audit operations. You will work with a diverse set of real world structured, unstructured and potentially multimodal datasets to train deep learning models that identify current inventory management problems and anticipate future ones. Datasets include multiple separate inventory management event streams, item images and natural language. You will face a high level of research ambiguity and problems that require creative, ambitious, and inventive solutions. About the team Amazon Fulfillment Technologies (AFT) powers Amazon’s global fulfillment network. We invent and deliver software, hardware, and data science solutions that orchestrate processes, robots, machines, and people. We harmonize the physical and virtual world so Amazon customers can get what they want, when they want it. The AFT AI team has deep expertise developing cutting edge AI solutions at scale and successfully applying them to business problems in the Amazon Fulfillment Network. These solutions typically utilize machine learning and computer vision techniques, applied to text, sequences of events, images or video from existing or new hardware. We influence each stage of innovation from inception to deployment, developing a research plan, creating and testing prototype solutions, and shepherding the production versions to launch. We are open to hiring candidates to work out of one of the following locations: Bellevue, WA, USA
US, CA, Santa Clara
About Amazon Health Amazon Health’s mission is to make it dramatically easier for customers to access the healthcare products and services they need to get and stay healthy. Towards this mission, we (Health Storefront and Shared Tech) are building the technology, products and services, that help customers find, buy, and engage with the healthcare solutions they need. Job summary We are seeking an exceptional Applied Scientist to join a team of experts in the field of machine learning, and work together to break new ground in the world of healthcare to make personalized and empathetic care accessible, convenient, and cost-effective. We leverage and train state-of-the-art large-language-models (LLMs) and develop entirely new experiences to help customers find the right products and services to address their health needs. We work on machine learning problems for intent detection, dialogue systems, and information retrieval. You will work in a highly collaborative environment where you can pursue both near-term productization opportunities to make immediate, meaningful customer impacts while pursuing ambitious, long-term research. You will work on hard science problems that have not been solved before, conduct rapid prototyping to validate your hypothesis, and deploy your algorithmic ideas at scale. You will get the opportunity to pursue work that makes people's lives better and pushes the envelop of science. Key job responsibilities - Translate product and CX requirements into science metrics and rigorous testing methodologies. - Invent and develop scalable methodologies to evaluate LLM outputs against metrics and guardrails. - Design and implement the best-in-class semantic retrieval system by creating high-quality knowledge base and optimizing embedding models and similarity measures. - Conduct tuning, training, and optimization of LLMs to achieve a compelling CX while reducing operational cost to be scalable. A day in the life In a fast-paced innovation environment, you work closely with product, UX, and business teams to understand customer's challenges. You translate product and business requirements into science problems. You dive deep into challenging science problems, enabling entirely new ML and LLM-driven customer experiences. You identify hypothesis and conduct rapid prototyping to learn quickly. You develop and deploy models at scale to pursue productizations. You mentor junior science team members and help influence our org in scientific best practices. About the team We are the ML Science and Engineering team, with a strong focus on Generative AI. The team consists of top-notch ML Scientists with diverse background in healthcare, robotics, customer analytics, and communication. We are committed to building and deploying the most advanced scientific capabilities and solutions for the products and services at Amazon Health. We are open to hiring candidates to work out of one of the following locations: Santa Clara, CA, USA
US, WA, Seattle
We are designing the future. If you are in quest of an iterative fast-paced environment, where you can drive innovation through scientific inquiry, and provide tangible benefit to hundreds of thousands of our associates worldwide, this is your opportunity. Come work on the Amazon Worldwide Fulfillment Design & Engineering Team! We are looking for an experienced and senior Research Scientist with background in Ergonomics and Industrial Human Factors, someone that is excited to work on complex real-world challenges for which a comprehensive scientific approach is necessary to drive solutions. Your investigations will define human factor / ergonomic thresholds resulting in design and implementation of safe and efficient workspaces and processes for our associates. Your role will entail assessment and design of manual material handling tasks throughout the entire Amazon network. You will identify fundamental questions pertaining to the human capabilities and tolerances in a myriad of work environments, and will initiate and lead studies that will drive decision making on an extreme scale. .You will provide definitive human factors/ ergonomics input and participate in design with every single design group in our network, including Amazon Robotics, Engineering R&D, and Operations Engineering. You will work closely with our Worldwide Health and Safety organization to gain feedback on designs and work tenaciously to continuously improve our associate’s experience. Key job responsibilities - Collaborating and designing work processes and workspaces that adhere to human factors / ergonomics standards worldwide. - Producing comprehensive and assessments of workstations and processes covering biomechanical, physiological, and psychophysical demands. - Effectively communicate your design rationale to multiple engineering and operations entities. - Identifying gaps in current human factors standards and guidelines, and lead comprehensive studies to redefine “industry best practices” based on solid scientific foundations. - Continuously strive to gain in-depth knowledge of your profession, as well as branch out to learn about intersecting fields, such as robotics and mechatronics. - Travelling to our various sites to perform thorough assessments and gain in-depth operational feedback, approximately 25%-50% of the time. We are open to hiring candidates to work out of one of the following locations: Seattle, WA, USA
US, CA, Santa Monica
Amazon Advertising is looking for a motivated and analytical self-starter to help pave the way for the next generation of insights and advertising products. You will use large-scale data, advertising effectiveness knowledge and business information needs of our advertising clients to envision new advertising measurement products and tools. You will facilitate innovation on behalf of our customers through end-to-end delivery of measurement solutions leveraging experiments, machine learning and causal inference. You will partner with our engineering teams to develop and scale successful solutions to production. This role requires strong hands-on skills in terms of effectively working with data, coding, and MLOps. However, the ideal candidate will also bring strong interpersonal and communication skills to engage with cross-functional partners, as well as to stay connected to insights needs of account teams and advertisers. This is a truly exciting and versatile position in that it allows you to apply and develop your hands-on data modeling and coding skills, to work with other scientists on research in new measurement solutions while at the same time partner with cross-functional stakeholders to deliver product impact. Key job responsibilities As an Applied Scientist on the Advertising Incrementality Measurement team you will: - Create new analytical products from conception to prototyping and scaling the product end-to-end through to production. - Scope and define new business problems in the realm of advertising effectiveness. Use machine learning and experiments to develop effective and scalable solutions. - Partner closely with the Engineering team. - Partner with Economists, Data Scientists, and other Applied Scientists to conduct research on advertising effectiveness using machine learning and causal inference. Make findings available via white papers. - Act as a liaison to product teams to help productize new measurement solutions. About the team Advertising Incrementality Measurement combines experiments with econometric analysis and machine learning to provide rigorous causal measurement of advertising effectiveness to internal and external customers. We are open to hiring candidates to work out of one of the following locations: Arlington, VA, USA | Boulder, CO, USA | New York, NY, USA | Santa Monica, CA, USA
US, NY, New York
Amazon Advertising is one of Amazon's fastest growing and most profitable businesses, responsible for defining and delivering a collection of advertising products that drive discovery and sales. Our products are strategically important to our Retail and Marketplace businesses driving long term growth. We deliver billions of ad impressions and millions of clicks and break fresh ground in product and technical innovations every day! The Ad Measurement team develops and deploys solutions fueled by machine learning to support Amazon Advertisers in their strategic campaign planning. Leaning on rich data points, we provide measurements, predictions and diagnostics that separate Amazon Advertising from all other media. As a Data Scientist on this team, you will: - Solve real-world problems by getting and analyzing large amounts of data, diving deep to identify business insights and opportunities, design simulations and experiments, developing statistical and ML models by tailoring to business needs, and collaborating with Scientists, Engineers, BIE's, and Product Managers. - Write code (Python, R, Scala, SQL, etc.) to obtain, manipulate, and analyze data - Apply statistical and machine learning knowledge to specific business problems and data. - Build decision-making models and propose solution for the business problem you define. - Retrieve, synthesize, and present critical data in a format that is immediately useful to answering specific questions or improving system performance. - Analyze historical data to identify trends and support optimal decision making. - Formalize assumptions about how our systems are expected to work, create statistical definition of the outlier, and develop methods to systematically identify outliers. Work out why such examples are outliers and define if any actions needed. - Given anecdotes about anomalies or generate automatic scripts to define anomalies, deep dive to explain why they happen, and identify fixes. - Conduct written and verbal presentations to share insights to audiences of varying levels of technical sophistication. Why you will love this opportunity: Amazon has invested heavily in building a world-class advertising business. This team defines and delivers a collection of advertising products that drive discovery and sales. Our solutions generate billions in revenue and drive long-term growth for Amazon’s Retail and Marketplace businesses. We deliver billions of ad impressions, millions of clicks daily, and break fresh ground to create world-class products. We are a highly motivated, collaborative, and fun-loving team with an entrepreneurial spirit - with a broad mandate to experiment and innovate. Impact and Career Growth: You will invent new experiences and influence customer-facing shopping experiences to help suppliers grow their retail business and the auction dynamics that leverage native advertising; this is your opportunity to work within the fastest-growing businesses across all of Amazon! Define a long-term science vision for our advertising business, driven from our customers' needs, translating that direction into specific plans for research and applied scientists, as well as engineering and product teams. This role combines science leadership, organizational ability, technical strength, product focus, and business understanding. We are open to hiring candidates to work out of one of the following locations: New York, NY, USA
US, WA, Bellevue
At AWS, we use Artificial Intelligence to be able to identify every need of a customer across all AWS services before they have to tell us about it, and then find and seamlessly connect them to the most appropriate resolution for their need, eventually fulfilling the vision of a self-healing cloud. We are looking for Data Scientists with unfettered curiosity and drive to help build “best in the world” support (contact center) experience that customers will love! You will have an opportunity to lead, invent, and design tech that will directly impact every customer across all AWS services. We are building industry-leading technology that cuts across a wide range of ML techniques from Natural Language Processing to Deep Learning and Generative Artificial Intelligence. You will be a key driver in taking something from an idea to an experiment to a prototype and finally to a live production system. Our team packs a punch with principal level engineering, science, product, and leadership talent. We are a results focused team and you have the opportunity to lead and establish a culture for the big things to come. We combine the culture of a startup, the innovation and creativity of a R&D Lab, the work-life balance of a mature organization, and technical challenges at the scale of AWS. We offer a playground of opportunities for builders to build, have fun, and make history! Key job responsibilities Deliver real world production systems at AWS scale. Work closely with the business to understand the problem space, identify the opportunities and formulate the problems. Use machine learning, data mining, statistical techniques, Generative AI and others to create actionable, meaningful, and scalable solutions for the business problems. Analyze and extract relevant information from large amounts of data and derive useful insights. Work with software engineering teams to deliver production systems with your ML models Establish scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation We are open to hiring candidates to work out of one of the following locations: Bellevue, WA, USA | Seattle, WA, USA
US, CA, Santa Clara
Amazon launched the Generative AI Innovation Center (GAIIC) in Jun 2023 to help AWS customers accelerate the use of Generative AI to solve business and operational problems and promote innovation in their organization (https://press.aboutamazon.com/2023/6/aws-announces-generative-ai-innovation-center). GAIIC provides opportunities to innovate in a fast-paced organization that contributes to game-changing projects and technologies that get deployed on devices and in the cloud. As an Applied Science Manager in GAIIC, you'll partner with technology and business teams to build new GenAI solutions that delight our customers. You will be responsible for directing a team of data/research/applied scientists, deep learning architects, and ML engineers to build generative AI models and pipelines, and deliver state-of-the-art solutions to customer’s business and mission problems. Your team will be working with terabytes of text, images, and other types of data to address real-world problems. The successful candidate will possess both technical and customer-facing skills that will allow you to be the technical “face” of AWS within our solution providers’ ecosystem/environment as well as directly to end customers. You will be able to drive discussions with senior technical and management personnel within customers and partners, as well as the technical background that enables them to interact with and give guidance to data/research/applied scientists and software developers. The ideal candidate will also have a demonstrated ability to think strategically about business, product, and technical issues. Finally, and of critical importance, the candidate will be an excellent technical team manager, someone who knows how to hire, develop, and retain high quality technical talent. About the team Here at AWS, it’s in our nature to learn and be curious about diverse perspectives. Our employee-led affinity groups foster a culture of inclusion that empower employees to feel proud of our differences. Ongoing events and learning experiences, including our Conversations on Race and Ethnicity (CORE) and AmazeCon (gender diversity) conferences, inspire us to never stop embracing our uniqueness. We have a career path for you no matter what stage you’re in when you start here. We’re continuously raising our performance bar as we strive to become Earth’s Best Employer. That’s why you’ll find endless knowledge-sharing, mentorship and other career- advancing resources here to help you develop into a better-rounded professional. We are open to hiring candidates to work out of one of the following locations: San Francisco, CA, USA | San Jose, CA, USA | Santa Clara, CA, USA
GB, London
Amazon Advertising is looking for a Data Scientist to join its brand new initiative that powers Amazon’s contextual advertising products. Advertising at Amazon is a fast-growing multi-billion dollar business that spans across desktop, mobile and connected devices; encompasses ads on Amazon and a vast network of hundreds of thousands of third party publishers; and extends across US, EU and an increasing number of international geographies. The Supply Quality organization has the charter to solve optimization problems for ad-programs in Amazon and ensure high-quality ad-impressions. We develop advanced algorithms and infrastructure systems to optimize performance for our advertisers and publishers. We are focused on solving a wide variety of problems in computational advertising like traffic quality prediction (robot and fraud detection), Security forensics and research, Viewability prediction, Brand Safety, Contextual data processing and classification. Our team includes experts in the areas of distributed computing, machine learning, statistics, optimization, text mining, information theory and big data systems. We are looking for a dynamic, innovative and accomplished Data Scientist to work on data science initiatives for contextual data processing and classification that power our contextual advertising solutions. Are you an experienced user of sophisticated analytical techniques that can be applied to answer business questions and chart a sustainable vision? Are you exited by the prospect of communicating insights and recommendations to audiences of varying levels of technical sophistication? Above all, are you an innovator at heart and have a track record of resolving ambiguity to deliver result? As a data scientist, you help our data science team build cutting edge models and measurement solutions to power our contextual classification technology. As this is a new initiative, you will get an opportunity to act as a thought leader, work backwards from the customer needs, dive deep into data to understand the issues, define metrics, conceptualize and build algorithms and collaborate with multiple cross-functional teams. Key job responsibilities * Define a long-term science vision for contextual-classification tech, driven fundamentally from the needs of our advertisers and publishers, translating that direction into specific plans for the science team. Interpret complex and interrelated data points and anecdotes to build and communicate this vision. * Collaborate with software engineering teams to Identify and implement elegant statistical and machine learning solutions * Oversee the design, development, and implementation of production level code that handles billions of ad requests. Own the full development cycle: idea, design, prototype, impact assessment, A/B testing (including interpretation of results) and production deployment. * Promote the culture of experimentation and applied science at Amazon. * Demonstrated ability to meet deadlines while managing multiple projects. * Excellent communication and presentation skills working with multiple peer groups and different levels of management * Influence and continuously improve a sustainable team culture that exemplifies Amazon’s leadership principles. We are open to hiring candidates to work out of one of the following locations: London, GBR
JP, 13, Tokyo
We are seeking a Principal Economist to be the science leader in Amazon's customer growth and engagement. The wide remit covers Prime, delivery experiences, loyalty program (Amazon Points), and marketing. We look forward to partnering with you to advance our innovation on customers’ behalf. Amazon has a trailblazing track record of working with Ph.D. economists in the tech industry and offers a unique environment for economists to thrive. As an economist at Amazon, you will apply the frontier of econometric and economic methods to Amazon’s terabytes of data and intriguing customer problems. Your expertise in building reduced-form or structural causal inference models is exemplary in Amazon. Your strategic thinking in designing mechanisms and products influences how Amazon evolves. In this role, you will build ground-breaking, state-of-the-art econometric models to guide multi-billion-dollar investment decisions around the global Amazon marketplaces. You will own, execute, and expand a research roadmap that connects science, business, and engineering and contributes to Amazon's long term success. As one of the first economists outside North America/EU, you will make an outsized impact to our international marketplaces and pioneer in expanding Amazon’s economist community in Asia. The ideal candidate will be an experienced economist in empirical industrial organization, labour economics, or related structural/reduced-form causal inference fields. You are a self-starter who enjoys ambiguity in a fast-paced and ever-changing environment. You think big on the next game-changing opportunity but also dive deep into every detail that matters. You insist on the highest standards and are consistent in delivering results. Key job responsibilities - Work with Product, Finance, Data Science, and Data Engineering teams across the globe to deliver data-driven insights and products for regional and world-wide launches. - Innovate on how Amazon can leverage data analytics to better serve our customers through selection and pricing. - Contribute to building a strong data science community in Amazon Asia. We are open to hiring candidates to work out of one of the following locations: Tokyo, 13, JPN