The ability to create and interact with large-scale domain-specific knowledge bases from unstructured/semi-structured data is the foundation for many industry-focused cognitive systems. We will demonstrate the Content Services system that provides cloud services for creating and querying high-quality domain-specific knowledge bases by analyzing and integrating multiple (un/semi)structured content sources. We will showcase an instantiation of the system for a financial domain. We will also demonstrate both cross-lingual natural language queries and programmatic API calls for interacting with this knowledge base.

Building industry-specific knowledge bases relies heavily on collecting and representing domain knowledge over time. Domain knowledge includes: (1) the logical schema, constraints and domain vocabulary of the application, (2) the models and algorithms to populate instances of that schema, and (3) the data necessary to build and maintain those models and algorithms. In IBM Watson we are using an ontology-driven approach for the creation and consumption of industry-specific knowledge bases. The creation of such knowledge bases involves well known building blocks: natural language processing, entity resolution, data transformation, etc. It is critical that the models and algorithms that implement these building blocks be transparent and optimizable for efficient execution.

Alan Akbik, Laura Chiticariu, Marina Danilevsky, Yunyao Li, Shivakumar Vaithyanathan, Huaiyu Zhu. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

SystemML aims at declarative, large-scale machine learning (ML) on top of MapReduce, where high-level ML scripts with R-like syntax are compiled to programs of MR jobs. The declarative specification of ML algorithms enables---in contrast to existing large-scale machine learning libraries---automatic optimization. SystemML's primary focus is on data parallelism but many ML algorithms inherently exhibit opportunities for task parallelism as well. A major challenge is how to efficiently combine both types of parallelism for arbitrary ML scripts and workloads. In this paper, we present a systematic approach for combining task and data parallelism for large-scale machine learning on top of MapReduce. We employ a generic Parallel FOR construct (ParFOR) as known from high performance computing (HPC). Our core contributions are (1) complementary parallelization strategies for exploiting multi-core and cluster parallelism, as well as (2) a novel cost-based optimization framework for automatically creating optimal parallel execution plans. Experiments on a variety of use cases showed that this achieves both efficiency and scalability due to automatic adaptation to ad-hoc workloads and unknown data characteristics.

Social media is an interactive vehicle for communication accessed on a daily basis by hundreds of millions of people. Unlike conventional media, which is a one-way street for information exchange, social media enables people to write content as well as provide feedback and recommend content to other users. There are multiple enterprise applications, such as customer retention, new customer acquisition, campaign management and lead generation that can significantly benefit from the consumer insights hidden in the massive amounts of social media content. Defining, extracting and representing entities such as people, organization and products, and their inter-relationships enables the building of comprehensive consumer profiles that can be leveraged in enterprise applications. Building these social media profiles requires a combination of text and entity analytics, while the utilization of such profiles makes heavy use of statistical models and machine learning. In this talk I will briefly describe the work in progress at IBM Research - Almaden on how such consumer insights, both at the level of an individual and at the level of appropriate micro-segments, can be used in enterprise applications in companies ranging from movie studios to financial services and insurance companies. I will also provide a brief overview of text, entity and statistical modeling tools that can operate in a distributed fashion over very large amounts of data.

MapReduce is emerging as a generic parallel programming paradigm for large clusters of machines. This trend combined with the growing need to run machine learning (ML) algorithms on massive datasets has led to an increased interest in implementing ML algorithms on MapReduce. However, the cost of implementing a large class of ML algorithms as low-level MapReduce jobs on varying data and machine cluster sizes can be prohibitive. In this paper, we propose SystemML in which ML algorithms are expressed in a higher-level language and are compiled and executed in a MapReduce environment. This higher-level language exposes several constructs including linear algebra primitives that constitute key building blocks for a broad class of supervised and unsupervised ML algorithms. The algorithms expressed in SystemML are compiled and optimized into a set of MapReduce jobs that can run on a cluster of machines. We describe and empirically evaluate a number of optimization strategies for efficiently executing these algorithms on Hadoop, an open-source MapReduce implementation. We report an extensive performance evaluation on three ML algorithms on varying data and cluster sizes.

Recently, there has been increasing interest in extending relational query processing to efficiently support extraction operators, such as dictionaries and regular expressions, over text data. Many text processing queries are sophisticated in that they involve multiple extraction and join operators, resulting in many possible query plans. However, there has been little research on building the selectivity or cost estimation for these extraction operators, which is crucial for an optimizer to pick a good query plan. In this paper, we define the problem of selectivity estimation for dictionaries and regular expressions, and propose to develop document synopses over a text corpus, from which the selectivity can be estimated. We first adapt the language models in the Natural Language Processing literature to form the top-k n-gram synopsis as the baseline document synopsis. Then we develop two classes of novel document synopses: stratified bloom filter synopsis and roll-up synopsis. We also develop techniques to decompose a complicated regular expression into subparts to achieve more effective and accurate estimation. We conduct experiments over the Enron email corpus using both real-world and synthetic workloads to compare the accuracy of the selectivity estimation over different classes and variations of synopses. The results show that, the top-k stratified bloom filter synopsis and the roll-up synopsis is the most accurate in dictionary and regular expression selectivity estimation respectively.

The results of a search engine can be improved by consulting auxiliary data. In a search database system, the association between the user query and the auxiliary data is driven by rewrite rules that augment the user query with a set of alternative queries. This paper develops a framework that formalizes the notion of a rewrite program, which is essentially a collection of hedge-rewriting rules. When applied to a search query, the rewrite program produces a set of alternative queries that constitutes a least fixpoint (lfp). The main focus of the paper is on the lfp-convergence of a rewrite program, where a rewrite program is lfp-convergent if the least fixpoint of every search query is finite. Determining whether a given rewrite program is lfp-convergent is undecidable; to accommodate that, the paper proposes a safety condition, and shows that safety guarantees lfp-convergence, and that safety can be decided in polynomial time. The effectiveness of the safety condition in capturing lfp-convergence is illustrated by an application to a rewrite program in an implemented system that is intended for widespread use.

Information Extraction (IE)-the problem of extracting structured information from unstructured text - has become the key enabler for many enterprise applications such as semantic search, business analytics and regulatory compliance. While rule-based IE systems are widely used in practice due to their well-known "explainability," developing high-quality information extraction rules is known to be a labor-intensive and time-consuming iterative process.

It is well known that a search engine can significantly benefit from an auxiliary database, which can suggest interpretations of the search query by means of the involved concepts and their interrelationship. The difficulty is to translate abstract notions like concept and interpretation into a concrete search algorithm that operates over the auxiliary database. To surpass existing heuristics, there is a need for a formal basis, which is realized in this paper through the framework of a search database system, where an interpretation is identified as a parse. It is shown that the parses of a query can be generated in polynomial time in the combined size of the input and the output, even if parses are restricted to those having a nonempty evaluation. Identifying that one parse is more specific than another is important for ranking answers, and this framework captures the precise semantics of being more specific; moreover, performing this comparison between parses is tractable. Lastly, the paper studies the problem of finding the most specific parses. Unfortunately, this problem turns out to be intractable in the general case. However, under reasonable assumptions, the parses can be enumerated in an order of decreasing specificity, with polynomial delay and polynomial space.

The primary goal of the Midas project is to build a system that enables easy and scalable integration of unstructured and semi-structured information present across multiple data sources. As a first step in this direction, we have built a system that extracts and integrates information from regulatory filings submitted to the U.S. Securities and Exchange Commission (SEC) and the Federal Deposit Insurance Corporation (FDIC). Midas creates a repository of entities, events, and relationships by extracting, conceptualizing, integrating, and aggregating data from unstructured and semi-structured documents. This repository enables applications to use the extracted and integrated data in a variety of ways including mashups with other public data and complex risk analysis.

Rule-based information extraction is a process by which structured objects are extracted from text based on user-defined rules. The compositional nature of rule-based information extraction also allows rules to be expressed over previously extracted objects. Such extraction is inherently uncertain, due to the varying precision associated with the rules used in a specific extraction task. Quantifying this uncertainty is crucial for querying the extracted objects in probabilistic databases, and for improving the recall of extraction tasks that use compositional rules. In this paper, we provide a probabilistic framework for handling the uncertainty in rule-based information extraction. Specifically, for each extraction task, we build a parametric exponential model of uncertainty that captures the interaction between the different rules, as well as the compositional nature of the rules; the exponential form of our model follows from maximum-entropy considerations. We also give model-decomposition techniques that make the learning algorithms scalable to large numbers of rules and constraints. Experiments over multiple real-world extraction tasks confirm that our approach yields accurate probability estimates with only a small performance overhead. Moreover, our framework supports incremental pay-as-you-go improvements in the accuracy of probability estimates as new rules, data, or constraints are added.

Traditional approaches to rule-based information extraction (IE) have primarily been based on regular expression grammars. However, these grammar-based systems have difficulty scaling to large data sets and large numbers of rules. Inspired by traditional database research, we propose an algebraic approach to rule-based IE that addresses these scalability issues through query optimization. The operators of our algebra are motivated by our experience in building several rule-based extraction programs over diverse data sets. We present the operators of our algebra and propose several optimization strategies motivated by the text-specific characteristics of our operators. Finally we validate the potential benefits of our approach by extensive experiments over real-world blog data.

Despite the success of web search engines, search over large enterprise intranets still suffers from poor result quality. Earlier work [6] that compared intranets and the Internet from the view point of keyword search has pointed to several reasons why the search problem is quite different in these two domains. In this paper, we address the problem of providing high quality answers to navigational queries in the intranet (e.g., queries intended to find product or personal home pages, service pages, etc.). Our approach is based on offline identification of navigational pages, intelligent generation of term-variants to associate with each page, and the construction of separate indices exclusively devoted to answering navigational queries. Using a testbed of 5.5M pages from the IBM intranet, we present evaluation results that demonstrate that for navigational queries, our approach of using custom indices produces results of significantly higher precision than those produced by a general purpose search algorithm.

Many searches on the web have a transactional intent. We argue that pages satisfying transactional needs can be distinguished from the more common pages that have some information and links, but cannot be used to execute a transaction. Based on this hypothesis, we provide a recipe for constructing a transaction annotator. By constructing an annotator with one corpus and then demonstrating its classification performance on another,we establish its robustness. Finally, we show experimentally that a search procedure that exploits such pre-annotation greatly outperforms traditional search for retrieving transactional pages.

This tutorial makes the case for developing a unified framework that manages information extraction from unstructured data (focusing in particular on text). We first survey research on information extraction in the database, AI, NLP, IR, and Web communities in recent years. Then we discuss why this is the right time for the database community to actively participate and address the problem of managing information extraction (including in particular the challenges of maintaining and querying the extracted information, and accounting for the imprecision and uncertainty inherent in the extraction process). Finally, we show how interested researchers can take the next step, by pointing to open problems, available datasets, applicable standards, and software tools. We do not assume prior knowledge of text management, NLP, extraction techniques, or machine learning.

We present Avatar Semantic Search, a prototype search engine that exploits annotations in the context of classical keyword search. The process of annotations is accomplished offline by using high-precision information extraction techniques to extract facts, con-cepts, and relationships from text. These facts and concepts are represented and indexed in a structured data store. At runtime, keyword queries are interpreted in the context of these extracted facts and converted into one or more precise queries over the structured store. In this demonstration we describe the overall architecture of the Avatar Semantic Search engine. We also demonstrate the superiority of the AVATAR approach over traditional keyword search engines using Enron email data set and a blog corpus.

In this paper we describe a systematic approach to uncovering multiple clusterings underlying a dataset. In contrast to previous approaches, the proposed method uses information about structures that are not desired and consequently is very useful in an exploratory datamining setting. Specifically, the problem is formulated as constrained model-based clustering where the constraints are placed at a model-level. Two variants of an EM algorithm, for this constrained model, are derived. The performance of both variants is compared against a state-of-the-art information bottleneck algorithm on both synthetic and real datasets.

Sentiment classification is the task of labeling a review document according to the polarity of its prevailing opinion (favorable or unfavorable). In approaching this problem, a model builder often has three sources of information available: a small collection of labeled documents, a large collection of unlabeled documents, and human understanding of language. Ideally, a learning method will utilize all three sources. To accomplish this goal, we generalize an existing procedure that uses the latter two.We extend this procedure by re-interpreting it as a Naive Bayes model for document sentiment. Viewed as such, it can also be seen to extract a pair of derived features that are linearly combined to predict sentiment. This perspective allows us to improve upon previous methods, primarily through two strategies: incorporating additional derived features into the model and, where possible, using labeled data to estimate their relative influence.

We develop a novel formalism for modeling speech signals which are irregularly or incompletely sampled. This situation can arise in real world applications where the speech signal is being transmitted over an error prone channel where parts of the signal can be dropped. Typical speech systems based on hidden Markov models, cannot handle such data since HMMs rely on the assumption that observations are complete and made at regular intervals. We introduce the asynchronous HMM, a variant of the inhomogeneous HMM commonly used in bioinformatics, and show how it can be used to model irregularly or incompletely sampled data. A nested EM algorithm is presented in brief which can be used to learn the parameters of this asynchronous HMM. Evaluation on real world speech data, which has been modified to simulate channel errors, shows that this model and its variants significantly outperform the standard HMM and methods based on data interpolation.

We consider the problem of classifying documents not by topic, but by overall sentiment, e.g., determining whether a review is positive or negative. Using movie reviews as data, we find that standard machine learning techniques definitively outperform human-produced baselines. However, the three machine learning methods we employed (Naive Bayes, maximum entropy classification, and support vector machines) do not perform as well on sentiment classification as on traditional topic-based categorization. We conclude by examining factors that make the sentiment classification problem more challenging.

article Free Access Share on Exploiting clustering and phrases for context-based information retrieval Authors: Peter G. Anick Digital Equipment Corporation, Stow, MA and Brandeis University, Waltham, MA Digital Equipment Corporation, Stow, MA and Brandeis University, Waltham, MAView Profile , Shivakumar Vaithyanathan IBM Almaden Research Center, San Jose, CA IBM Almaden Research Center, San Jose, CAView Profile Authors Info & Claims ACM SIGIR ForumVolume 31Issue SIDecember 1997pp 314–323https://doi.org/10.1145/278459.258601Published:01 July 1997Publication History 68citation1,735DownloadsMetricsTotal Citations68Total Downloads1,735Last 12 Months71Last 6 weeks13 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteeReaderPDF