From 2008-2010 we built an experimental personalized news system where readers subscribe to organized channels of topical information that are curated by experts. AI technology was employed to efficiently present the right information to each reader and to radically reduce the workload of curators. The system went through three implementation cycles and processed over 20 million news stories from about 12,000 RSS feeds on over 8000 topics organized by 160 curators for over 600 registered readers. This paper describes the approach, engineering and AI technology of the system.

Then we add some world knowledge, in the form of commonsense statements, to help in the text understanding. The result combines this knowledge to form a multidimensional space where concepts, people, groups, and projects are all represented as vectors. From that space we retrieve information relevant to lab visitors--dynamically creating their presence in the vector space by creating a vector from the projects they have chosen as favorites. We then use the vector space to determine the relevance of objects in the space to each other--determining which projects are similar, which projects would be good fits for a lab visitor, and which projects fit which lab themes. Additionally, we have designed a user interface that makes this system easy and social to interact with. The following subections discuss our approach to interface design, our methods for extracting semantic information from the text base, and for assessing similarity of user interests with that knowledge.

NewsFinder automates the steps involved in finding, selecting, categorizing, and publishing news stories that meet relevance criteria for the Artificial Intelligence community. The software combines a broad search of online news sources with topic-specific trained models and heuristics. Since August 2010, the program has been used to operate the AI in the News service that is part of the AAAI AITopics website.

From 2008-2010 we built an experimental personalized news system where readers subscribe to organized channels of topical information that are curated by experts. AI technology was employed to efficiently present the right information to each reader and to radically reduce the workload of curators. The system went through three implementation cycles and processed over 20 million news stories from about 12,000 RSS feeds on over 8000 topics organized by 160 curators for over 600 registered readers. This paper describes the approach, engineering and AI technology of the system.

We examine the problem of learning a probabilistic model for melody directly from musical sequences belonging to the same genre. This is a challenging task as one needs to capture not only the rich temporal structure evident in music, but also the complex statistical dependencies among different music components. To address this problem we introduce the Variable-gram Topic Model, which couples the latent topic formalism with a systematic model for contextual information. We evaluate the model on next-step prediction. Additionally, we present a novel way of model evaluation, where we directly compare model samples with data sequences using the Maximum Mean Discrepancy of string kernels, to assess how close is the model distribution to the data distribution. We show that the model has the highest performance under both evaluation measures when compared to LDA, the Topic Bigram and related non-topic models.

We investigate the problem of modeling symbolic sequences of polyphonic music in a completely general piano-roll representation. We introduce a probabilistic model based on distribution estimators conditioned on a recurrent neural network that is able to discover temporal dependencies in high-dimensional sequences. Our approach outperforms many traditional models of polyphonic music on a variety of realistic datasets. We show how our musical language model can serve as a symbolic prior to improve the accuracy of polyphonic transcription.

Much information available on the web is copied, reused or rephrased. The phenomenon that multiple web sources pick up certain information is often called trend. A central problem in the context of web data mining is to detect those web sources that are first to publish information which will give rise to a trend. We present a simple and efficient method for finding trends dominating a pool of web sources and identifying those web sources that publish the information relevant to a trend before others. We validate our approach on real data collected from influential technology news feeds.

We propose Coactive Learning as a model of interaction between a learning system and a human user, where both have the common goal of providing results of maximum utility to the user. At each step, the system (e.g. search engine) receives a context (e.g. query) and predicts an object (e.g. ranking). The user responds by correcting the system if necessary, providing a slightly improved -- but not necessarily optimal -- object as feedback. We argue that such feedback can often be inferred from observable user behavior, for example, from clicks in web-search. Evaluating predictions by their cardinal utility to the user, we propose efficient learning algorithms that have ${\cal O}(\frac{1}{\sqrt{T}})$ average regret, even though the learning algorithm never observes cardinal utility values as in conventional online learning. We demonstrate the applicability of our model and learning algorithms on a movie recommendation task, as well as ranking for web-search.

In many cases it makes sense to model a relationship symmetrically, not implying any particular directionality. Consider the classical example of a recommendation system where the rating of an item by a user should symmetrically be dependent on the attributes of both the user and the item. The attributes of the (known) relationships are also relevant for predicting attributes of entities and for predicting attributes of new relations. In recommendation systems, the exploitation of relational attributes is often referred to as collaborative filtering. Again, in many applications one might prefer to model the collaborative effect in a symmetrical way. In this paper we present a relational model, which is completely symmetrical. The key innovation is that we introduce for each entity (or object) an infinite-dimensional latent variable as part of a Dirichlet process (DP) model. We discuss inference in the model, which is based on a DP Gibbs sampler, i.e., the Chinese restaurant process. We extend the Chinese restaurant process to be applicable to relational modeling. Our approach is evaluated in three applications. One is a recommendation system based on the MovieLens data set. The second application concerns the prediction of the function of yeast genes/proteins on the data set of KDD Cup 2001 using a multi-relational model. The third application involves a relational medical domain. The experimental results show that our model gives significantly improved estimates of attributes describing relationships or entities in complex relational models.

Leaf vein forms the basis of leaf characterization and classification. Different species have different leaf vein patterns. It is seen that leaf vein segmentation will help in maintaining a record of all the leaves according to their specific pattern of veins thus provide an effective way to retrieve and store information regarding various plant species in database as well as provide an effective means to characterize plants on the basis of leaf vein structure which is unique for every species. The algorithm proposes a new way of segmentation of leaf veins with the use of Odd Gabor filters and the use of morphological operations for producing a better output. The Odd Gabor filter gives an efficient output and is robust and scalable as compared with the existing techniques as it detects the fine fiber like veins present in leaves much more efficiently.