Learning general functional dependencies between arbitrary input and output spaces is one of the key challenges in computational intelligence. While recent progress in machine learning has mainly focused on designing flexible and powerful input representations, this paper addresses the complementary issue of designing classification algorithms that can deal with more complex outputs, such as trees, sequences, or sets. More generally, we consider problems involving multiple dependent output variables, structured output spaces, and classification problems with class attributes. In order to accomplish this, we propose to appropriately generalize the well-known notion of a separation margin and derive a corresponding maximum-margin formulation. While this leads to a quadratic program with a potentially prohibitive, i.e. exponential, number of constraints, we present a cutting plane algorithm that solves the optimization problem in polynomial time for a large class of problems. The proposed method has important applications in areas such as computational biology, natural language processing, information retrieval/extraction, and optical character recognition. Experiments from various domains involving different types of output spaces emphasize the breadth and generality of our approach.

Often, in the real world, entities have two or more representations in databases. Duplicate records do not share a common key and/or they contain errors that make duplicate matching a difficult task. Errors are introduced as the result of transcription errors, incomplete information, lack of standard formats, or any combination of these factors. In this paper, we present a thorough analysis of the literature on duplicate record detection. We cover similarity metrics that are commonly used to detect similar field entries, and we present an extensive set of duplicate detection algorithms that can detect approximately duplicate records in a database. We also cover multiple techniques for improving the efficiency and scalability of approximate duplicate detection algorithms. We conclude with coverage of existing tools and with a brief discussion of the big open problems in the area.

Using an open-source, Java toolkit of name-matching methods, we experimentally compare string distance metrics on the task of matching entity names. We investigate a number of different metrics proposed by different communities, including edit-distance metrics, fast heuristic string comparators, token-based distance metrics, and hybrid methods. Overall, the best-performing method is a hybrid scheme combining a TFIDF weighting scheme, which is widely used in information retrieval, with the Jaro-Winkler string-distance scheme, which was developed in the probabilistic record linkage community.

The problem of identifying approximately duplicate records in databases is an essential step for data cleaning and data integration processes. Most existing approaches have relied on generic or manually tuned distance metrics for estimating the similarity of potential duplicates. In this paper, we present a framework for improving duplicate detection using trainable measures of textual similarity. We propose to employ learnable text distance functions for each database field, and show that such measures are capable of adapting to the specific notion of similarity that is appropriate for the field's domain. We present two learnable text similarity measures suitable for this task: an extended variant of learnable string edit distance, and a novel vector-space based measure that employs a Support Vector Machine (SVM) for training. Experimental results on a range of datasets show that our framework can improve duplicate detection accuracy over traditional techniques.

Many databases contain uncertain and imprecise references to real-world entities. The absence of identifiers for the underlying entities often results in a database which contains multiple references to the same entity. This can lead not only to data redundancy, but also inaccuracies in query processing and knowledge extraction. These problems can be alleviated through the use of entity resolution. Entity resolution involves discovering the underlying entities and mapping each database reference to these entities. Traditionally, entities are resolved using pairwise similarity over the attributes of references. However, there is often additional relational information in the data. Specifically, references to different entities may cooccur. In these cases, collective entity resolution, in which entities for cooccurring references are determined jointly rather than independently, can improve entity resolution accuracy. We propose a novel relational clustering algorithm that uses both attribute and relational information for determining the underlying domain entities, and we give an efficient implementation. We investigate the impact that different relational similarity measures have on entity resolution quality. We evaluate our collective entity resolution algorithm on multiple real-world databases. We show that it improves entity resolution performance over both attribute-based baselines and over algorithms that consider relational information but do not resolve entities collectively. In addition, we perform detailed experiments on synthetically generated data to identify data characteristics that favor collective relational resolution over purely attribute-based algorithms.

We describe an open-source Java toolkit of methods for matching names and records. We summarize results obtained from using various string distance metrics on the task of matching entity names. These metrics include distance functions proposed by several different communities, such as edit-distance metrics, fast heuristic string comparators, token-based distance metrics, and hybrid methods. We then describe an extension to the toolkit which allows records to be compared. We discuss

In this paper we address the problem of reference disambiguation. Specifically, we consider a situation where entities in the database are referred to using descriptions (e.g., a set of instantiated attributes). The objective of reference disambiguation is to identify the unique entity to which each description corresponds. The key difference between the approach we propose (called RelDC) and the traditional techniques is that RelDC analyzes not only object features but also inter-object relationships to improve the disambiguation quality. Our extensive experiments over two real datasets and also over synthetic datasets show that analysis of relationships significantly improves quality of the result.

Record linkage, the problem of determining when two records refer to the same entity, has applications for both data cleaning (deduplication) and for integrating data from multiple sources. Traditional approaches use a similarity measure that compares tuples ’ attribute values; tuples with similarity scores above a certain threshold are declared to be matches. While this method can perform quite well in many domains, particularly domains where there is not a large amount of noise in the data, in some domains looking only at tuple values is not enough. By also examining the context of the tuple, i.e. the other tuples to which it is linked, we can come up with a more accurate linkage decision. But this additional accuracy comes at a price. In order to correctly find all duplicates, we may need to make multiple passes over the data; as linkages are discovered, they may in turn

This paper presents a method for inducing translation lexicons based on transduction models of cognate pairs via bridge languages. Bilingual lexicons within languages families are induced using probabilistic string edit distance models. Translation lexicons for arbitrary distant language pairs are then generated by a combination of these intra-family translation models and one or more cross-family online dictionaries. Up to 95% exact match accuracy is achieved on the target vocabulary (30-68% of inter-family test pairs). Thus substantial portions of translation lexicons can be generated accurately for languages where no bilingual dictionary or parallel corpora may exist.

In this article, we address the problem of reference disambiguation. Specifically, we consider a situation where entities in the database are referred to using descriptions (e.g., a set of instantiated attributes). The objective of reference disambiguation is to identify the unique entity to which each description corresponds. The key difference between the approach we propose (called RELDC) and the traditional techniques is that RELDC analyzes not only object features but also inter-object relationships to improve the disambiguation quality. Our extensive experiments over two real data sets and over synthetic datasets show that analysis of relationships significantly improves quality of the result.