Richard Beckwith

Bio: Richard Beckwith is an academic researcher from Intel. The author has contributed to research in topics: Ubiquitous computing & Context (language use). The author has an hindex of 16, co-authored 44 publications receiving 6465 citations. Previous affiliations of Richard Beckwith include Princeton University & Columbia University.

Introduction to WordNet: An On-line Lexical Database

Abstract: Standard alphabetical procedures for organizing lexical information put together words that are spelled alike and scatter words with similar or related meanings haphazardly through the list. Unfortunately, there is no obvious alternative, no other simple way for lexicographers to keep track of what has been done or for readers to find the word they are looking for. But a frequent objection to this solution is that finding things on an alphabetical list can be tedious and time-consuming. Many people who would like to refer to a dictionary decide not to bother with it because finding the information would interrupt their work and break their train of thought.

Vineyard computing: sensor networks in agricultural production

Abstract: Using ethnographic research methods, the authors studied the structure of the needs and priorities of people working in a vineyard to gain a better understanding of the potential for sensor networks in agriculture. We discuss an extended study of vineyard workers and their work practices to assess the potential for sensor network systems to aid work in this environment. The major purpose is to find new directions and new topics that pervasive computing and sensor networks might address in designing technologies to support a broader range of users and activities.

Exploring Privacy Concerns about Personal Sensing

Abstract: More and more personal devices such as mobile phones and multimedia players use embedded sensing. This means that people are wearing and carrying devices capable of sensing details about them such as their activity, location, and environment. In this paper, we explore privacy concerns about such personal sensing through interviews with 24 participants who took part in a three month study that used personal sensing to detect their physical activities. Our results show that concerns often depended on what was being recorded, the context in which participants worked and lived and thus would be sensed, and the value they perceived would be provided. We suggest ways in which personal sensing can be made more privacy-sensitive to address these concerns.

Report from the field: results from an agricultural wireless sensor network

Abstract: This paper reports the results of a 6-month deployment of a 65-node multi-hop network in a vineyard setting. This deployment specifically looked to discover ways in which a farm setting could find a return on investment for deploying such a network. Our ongoing collaborations of over two years ultimately have included everyone from the vineyard owners to the technology developers. We have been able to find several areas where wireless sensor networks deliver valuable information and provide a return on investment.

Designing for ubiquity: the perception of privacy

Abstract: Ubicomp researchers have long argued that privacy is a design issue, and it goes without saying that successful design requires that we understand the desires, concerns, and awareness of the technology's users. Yet, because ubicomp systems are relatively unusual, too little empirical research exists to inform designers about potential users. Complicating design further is the fact that ubicomp systems are typically embedded or invisible, making it difficult for users to know when invisible devices are present and functioning. As early as 1993, ubicomp researchers recognized that embedded technology's unobtrusiveness both belies and contributes to its potential for supporting potentially invasive applications. Not surprisingly, users' inability to see a technology makes it difficult for them to understand how it might affect their privacy. Unobtrusiveness, nevertheless, is a reasonable goal because such systems must minimize the demands on users. To investigate these issues further, I conducted an ethnographic study of what I believe is the first US eldercare facility to use a sensor-rich environment. Our subjects were normal civilians (rather than ubicomp researchers) who lived or worked in a ubiquitous computing environment. We interviewed residents, their family members, and the facility's caregivers and managers. Our questions focused on how people understood both the ubiquitous technology and its effect on their privacy. Although the embedded technology played a central role in how people viewed the environment, they had a limited understanding of the technology, thus raising several privacy, design, and safety issues.

WordNet: a lexical database for English

Abstract: Because meaningful sentences are composed of meaningful words, any system that hopes to process natural languages as people do must have information about words and their meanings. This information is traditionally provided through dictionaries, and machine-readable dictionaries are now widely available. But dictionary entries evolved for the convenience of human readers, not for machines. WordNet1 provides a more effective combination of traditional lexicographic information and modern computing. WordNet is an online lexical database designed for use under program control. English nouns, verbs, adjectives, and adverbs are organized into sets of synonyms, each representing a lexicalized concept. Semantic relations link the synonym sets [4].

WordNet : an electronic lexical database

Abstract: Part 1 The lexical database: nouns in WordNet, George A. Miller modifiers in WordNet, Katherine J. Miller a semantic network of English verbs, Christiane Fellbaum design and implementation of the WordNet lexical database and searching software, Randee I. Tengi. Part 2: automated discovery of WordNet relations, Marti A. Hearst representing verb alterations in WordNet, Karen T. Kohl et al the formalization of WordNet by methods of relational concept analysis, Uta E. Priss. Part 3 Applications of WordNet: building semantic concordances, Shari Landes et al performance and confidence in a semantic annotation task, Christiane Fellbaum et al WordNet and class-based probabilities, Philip Resnik combining local context and WordNet similarity for word sense identification, Claudia Leacock and Martin Chodorow using WordNet for text retrieval, Ellen M. Voorhees lexical chains as representations of context for the detection and correction of malapropisms, Graeme Hirst and David St-Onge temporal indexing through lexical chaining, Reem Al-Halimi and Rick Kazman COLOR-X - using knowledge from WordNet for conceptual modelling, J.F.M. Burg and R.P. van de Riet knowledge processing on an extended WordNet, Sanda M. Harabagiu and Dan I Moldovan appendix - obtaining and using WordNet.

YOLO9000: Better, Faster, Stronger

Abstract: We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. Using a novel, multi-scale training method the same YOLOv2 model can run at varying sizes, offering an easy tradeoff between speed and accuracy. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that dont have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. YOLO9000 predicts detections for more than 9000 different object categories, all in real-time.

YOLO9000: Better, Faster, Stronger

Abstract: We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prior work. The improved model, YOLOv2, is state-of-the-art on standard detection tasks like PASCAL VOC and COCO. At 67 FPS, YOLOv2 gets 76.8 mAP on VOC 2007. At 40 FPS, YOLOv2 gets 78.6 mAP, outperforming state-of-the-art methods like Faster RCNN with ResNet and SSD while still running significantly faster. Finally we propose a method to jointly train on object detection and classification. Using this method we train YOLO9000 simultaneously on the COCO detection dataset and the ImageNet classification dataset. Our joint training allows YOLO9000 to predict detections for object classes that don't have labelled detection data. We validate our approach on the ImageNet detection task. YOLO9000 gets 19.7 mAP on the ImageNet detection validation set despite only having detection data for 44 of the 200 classes. On the 156 classes not in COCO, YOLO9000 gets 16.0 mAP. But YOLO can detect more than just 200 classes; it predicts detections for more than 9000 different object categories. And it still runs in real-time.

Mining and summarizing customer reviews

Abstract: Merchants selling products on the Web often ask their customers to review the products that they have purchased and the associated services. As e-commerce is becoming more and more popular, the number of customer reviews that a product receives grows rapidly. For a popular product, the number of reviews can be in hundreds or even thousands. This makes it difficult for a potential customer to read them to make an informed decision on whether to purchase the product. It also makes it difficult for the manufacturer of the product to keep track and to manage customer opinions. For the manufacturer, there are additional difficulties because many merchant sites may sell the same product and the manufacturer normally produces many kinds of products. In this research, we aim to mine and to summarize all the customer reviews of a product. This summarization task is different from traditional text summarization because we only mine the features of the product on which the customers have expressed their opinions and whether the opinions are positive or negative. We do not summarize the reviews by selecting a subset or rewrite some of the original sentences from the reviews to capture the main points as in the classic text summarization. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online demonstrate the effectiveness of the techniques.