Search

A phrase is a natural, meaningful, and essential semantic unit. In topic modeling, visualizing phrases for individual topics is an effective way to explore and understand unstructured text corpora. However, from phrase quality and topical cohesion perspectives, the outcomes of existing approaches remain to be improved. Usually, the process of topical phrase mining is twofold: phrase mining and topic modeling. For phrase mining, existing approaches often suffer from order sensitive and inappropriate segmentation problems, which make them often extract inferior quality phrases. For topic modeling, traditional topic models do not fully consider the constraints induced by phrases, which may weaken the cohesion. Moreover, existing approaches often suffer from losing domain terminologies since they neglect the impact of domain-level topical distribution. In this paper, we propose an efficient method for high quality and cohesive topical phrase mining. A high quality phrase should satisfy frequency, phraseness, completeness, and appropriateness criteria. In our framework, we integrate quality guaranteed phrase mining method, a novel topic model incorporating the constraint of phrases, and a novel document clustering method into an iterative framework to improve both phrase quality and topical cohesion. We also describe efficient algorithmic designs to execute these methods efficiently. The empirical verification demonstrates that our method outperforms the state-of-the-art methods from the aspects of both interpretability and efficiency. [ABSTRACT FROM AUTHOR]

Many problems in natural language processing, data mining, information retrieval, and bioinformatics can be formalized as string transformation, which is a task as follows. Given an input string, the system generates the $k$ most likely output strings corresponding to the input string. This paper proposes a novel and probabilistic approach to string transformation, which is both accurate and efficient. The approach includes the use of a log linear model, a method for training the model, and an algorithm for generating the top $k$ candidates, whether there is or is not a predefined dictionary. The log linear model is defined as a conditional probability distribution of an output string and a rule set for the transformation conditioned on an input string. The learning method employs maximum likelihood estimation for parameter estimation. The string generation algorithm based on pruning is guaranteed to generate the optimal top $k$ candidates. The proposed method is applied to correction of spelling errors in queries as well as reformulation of queries in web search. Experimental results on large scale data show that the proposed approach is very accurate and efficient improving upon existing methods in terms of accuracy and efficiency in different settings. [ABSTRACT FROM AUTHOR]

The two most important tasks in information extraction from the Web are webpage structure understanding and natural language sentences processing. However, little work has been done toward an integrated statistical model for understanding webpage structures and processing natural language sentences within the HTML elements. Our recent work on webpage understanding introduces a joint model of Hierarchical Conditional Random Fields (HCRFs) and extended Semi-Markov Conditional Random Fields (Semi-CRFs) to leverage the page structure understanding results in free text segmentation and labeling. In this top-down integration model, the decision of the HCRF model could guide the decision making of the Semi-CRF model. However, the drawback of the top-down integration strategy is also apparent, i.e., the decision of the Semi-CRF model could not be used by the HCRF model to guide its decision making. This paper proposed a novel framework called WebNLP, which enables bidirectional integration of page structure understanding and text understanding in an iterative manner. We have applied the proposed framework to local business entity extraction and Chinese person and organization name extraction. Experiments show that the WebNLP framework achieved significantly better performance than existing methods. [ABSTRACT FROM AUTHOR]

Reputation-based trust models are widely used in e-commerce applications, and feedback ratings are aggregated to compute sellers’ reputation trust scores. The “all good reputation” problem, however, is prevalent in current reputation systems—reputation scores are universally high for sellers and it is difficult for potential buyers to select trustworthy sellers. In this paper, based on the observation that buyers often express opinions openly in free text feedback comments, we propose CommTrust for trust evaluation by mining feedback comments. Our main contributions include: 1) we propose a multidimensional trust model for computing reputation scores from user feedback comments; and 2) we propose an algorithm for mining feedback comments for dimension ratings and weights, combining techniques of natural language processing, opinion mining, and topic modeling. Extensive experiments on eBay and Amazon data demonstrate that CommTrust can effectively address the “all good reputation” issue and rank sellers effectively. To the best of our knowledge, our research is the first piece of work on trust evaluation by mining feedback comments. [ABSTRACT FROM PUBLISHER]

The vast majority of existing approaches to opinion feature extraction rely on mining patterns only from a single review corpus, ignoring the nontrivial disparities in word distributional characteristics of opinion features across different corpora. In this paper, we propose a novel method to identify opinion features from online reviews by exploiting the difference in opinion feature statistics across two corpora, one domain-specific corpus (i.e., the given review corpus) and one domain-independent corpus (i.e., the contrasting corpus). We capture this disparity via a measure called domain relevance (DR), which characterizes the relevance of a term to a text collection. We first extract a list of candidate opinion features from the domain review corpus by defining a set of syntactic dependence rules. For each extracted candidate feature, we then estimate its intrinsic-domain relevance (IDR) and extrinsic-domain relevance (EDR) scores on the domain-dependent and domain-independent corpora, respectively. Candidate features that are less generic (EDR score less than a threshold) and more domain-specific (IDR score greater than another threshold) are then confirmed as opinion features. We call this interval thresholding approach the intrinsic and extrinsic domain relevance (IEDR) criterion. Experimental results on two real-world review domains show the proposed IEDR approach to outperform several other well-established methods in identifying opinion features. [ABSTRACT FROM PUBLISHER]

Technology-supported learning systems have proved to be helpful in many learning situations. These systems require an appropriate representation of the knowledge to be learned, the Domain Module. The authoring of the Domain Module is cost and labor intensive, but its development cost might be lightened by profiting from semiautomatic Domain Module authoring techniques and promoting knowledge reuse. DOM-Sortze is a system that uses natural language processing techniques, heuristic reasoning, and ontologies for the semiautomatic construction of the Domain Module from electronic textbooks. To determine how it might help in the Domain Module authoring process, it has been tested with an electronic textbook, and the gathered knowledge has been compared with the Domain Module that instructional designers developed manually. This paper presents DOM-Sortze and describes the experiment carried out. [ABSTRACT FROM AUTHOR]

Traditional text mining techniques transform free text into flat bags of words representation, which does not preserve sufficient semantics for the purpose of knowledge discovery. In this paper, we present a two-step procedure to mine generalized associations of semantic relations conveyed by the textual content of Web documents. First, RDF (Resource Description Framework) metadata representing semantic relations are extracted from raw text using a myriad of natural language processing techniques. The relation extraction process also creates a term taxonomy in the form of a sense hierarchy inferred from WordNet. Then, a novel generalized association pattern mining algorithm (GP-Close) is applied to discover the underlying relation association patterns on RDF metadata. For pruning the large number of redundant overgeneralized patterns in relation pattern search space, the GP-Close algorithm adopts the notion of generalization closure for systematic overgeneralization reduction. The efficacy of our approach is demonstrated through empirical experiments conducted on an online database of terrorist activities. [ABSTRACT FROM AUTHOR]

This paper introduces a hidden topic-based framework for processing short and sparse documents (e.g., search result snippets, product descriptions, book/movie summaries, and advertising messages) on the Web. The framework focuses on solving two main challenges posed by these kinds of documents: 1) data sparseness and 2) synonyms/homonyms. The former leads to the lack of shared words and contexts among documents while the latter are big linguistic obstacles in natural language processing (NLP) and information retrieval (IR). The underlying idea of the framework is that common hidden topics discovered from large external data sets (universal data sets), when included, can make short documents less sparse and more topic-oriented. Furthermore, hidden topics from universal data sets help handle unseen data better. The proposed framework can also be applied for different natural languages and data domains. We carefully evaluated the framework by carrying out two experiments for two important online applications (Web search result classification and matching/ranking for contextual advertising) with large-scale universal data sets and we achieved significant results. [ABSTRACT FROM PUBLISHER]

Automatic text summarization is a fundamental natural language processing (NLP) application that aims to condense a source text into a shorter version. The rapid increase in multimedia data transmission over the Internet necessitates multi-modal summarization (MMS) from asynchronous collections of text, image, audio, and video. In this work, we propose an extractive MMS method that unites the techniques of NLP, speech processing, and computer vision to explore the rich information contained in multi-modal data and to improve the quality of multimedia news summarization. The key idea is to bridge the semantic gaps between multi-modal content. Audio and visual are main modalities in the video. For audio information, we design an approach to selectively use its transcription and to infer the salience of the transcription with audio signals. For visual information, we learn the joint representations of text and images using a neural network. Then, we capture the coverage of the generated summary for important visual information through text-image matching or multi-modal topic modeling. Finally, all the multi-modal aspects are considered to generate a textual summary by maximizing the salience, non-redundancy, readability, and coverage through the budgeted optimization of submodular functions. We further introduce a publicly available MMS corpus in English and Chinese.1 The experimental results obtained on our dataset demonstrate that our methods based on image matching and image topic framework outperform other competitive baseline methods. [ABSTRACT FROM AUTHOR]

Sentence auto-completion is an important feature that saves users many keystrokes in typing the entire sentence by providing suggestions as they type. Despite its value, the existing sentence auto-completion methods, such as query completion models, can hardly be applied to solving the object completion problem in sentences with the form of (subject, verb, object), due to the complex natural language description and the data deficiency problem. Towards this goal, we treat an SVO sentence as a three-element triple (subject, sentence pattern, object), and cast the sentence object completion problem as an element inference problem. These elements in all triples are encoded into a unified low-dimensional embedding space by our proposed TRANSFER model, which leverages the external knowledge base to strengthen the representation learning performance. With such representations, we can provide reliable candidates for the desired missing element by a linear model. Extensive experiments on a real-world dataset have well-validated our model. Meanwhile, we have successfully applied our proposed model to factoid question answering systems for answer candidate selection, which further demonstrates the applicability of the TRANSFER model. [ABSTRACT FROM PUBLISHER]

Taxonomy learning is an important task for knowledge acquisition, sharing, and classification as well as application development and utilization in various domains. To reduce human effort to build a taxonomy from scratch and improve the quality of the learned taxonomy, we propose a new taxonomy learning approach, named TaxoFinder. TaxoFinder takes three steps to automatically build a taxonomy. First, it identifies domain-specific concepts from a domain text corpus. Second, it builds a graph representing how such concepts are associated together based on their co-occurrences. As the key method in TaxoFinder, we propose a method for measuring associative strengths among the concepts, which quantify how strongly they are associated in the graph, using similarities between sentences and spatial distances between sentences. Lastly, TaxoFinder induces a taxonomy from the graph using a graph analytic algorithm. TaxoFinder aims to build a taxonomy in such a way that it maximizes the overall associative strengths among the concepts in the graph to build a taxonomy. We evaluate TaxoFinder using gold-standard evaluation on three different domains: emergency management for mass gatherings, autism research, and disease domains. In our evaluation, we compare TaxoFinder with a state-of-the-art subsumption method and show that TaxoFinder is an effective approach significantly outperforming the subsumption method. [ABSTRACT FROM AUTHOR]

In this work, Web-based metrics that compute the semantic similarity between words or terms are presented and compared with the state of the art. Starting from the fundamental assumption that similarity of context implies similarity of meaning, relevant Web documents are downloaded via a Web search engine and the contextual information of words of interest is compared (context-based similarity metrics). The proposed algorithms work automatically, do not require any human-annotated knowledge resources, e.g., ontologies, and can be generalized and applied to different languages. Context-based metrics are evaluated both on the Charles-Miller data set and on a medical term data set. It is shown that context-based similarity metrics significantly outperform co-occurrence-based metrics, in terms of correlation with human judgment, for both tasks. In addition, the proposed unsupervised context-based similarity computation algorithms are shown to be competitive with the state-of-the-art supervised semantic similarity algorithms that employ language-specific knowledge resources. Specifically, context-based metrics achieve correlation scores of up to 0.88 and 0.74 for the Charles-Miller and medical data sets, respectively. The effect of stop word filtering is also investigated for word and term similarity computation. Finally, the performance of context-based term similarity metrics is evaluated as a function of the number of Web documents used and for various feature weighting schemes. [ABSTRACT FROM PUBLISHER]