Semantic Space Model Research Articles

Deceptive text detection using continuous semantic space models

Deceptive text detection using continuous semantic space models

Eye movements in software traceability link recovery

Information Retrieval (IR) approaches, such as Latent Semantic Indexing (LSI) and Vector Space Model (VSM), are commonly applied to recover software traceability links. Recently, an approach based on developers' eye gazes was proposed to retrieve traceability links. This paper presents a comparative study on IR and eye-gaze based approaches. In addition, it reports on the possibility of using eye gaze links as an alternative benchmark in comparison to commits. The study conducted asked developers to perform bug-localization tasks on the open source subject system JabRef. The iTrace environment, which is an eye tracking enabled Eclipse plugin, was used to collect eye gaze data. During the data collection phase, an eye tracker was used to gather the source code entities (SCE's), developers looked at while solving these tasks. We present an algorithm that uses the collected gaze dataset to produce candidate traceability links related to the tasks. In the evaluation phase, we compared the results of our algorithm with the results of an IR technique, in two different contexts. In the first context, precision and recall metric values are reported for both IR and eye gaze approaches based on commits. In the second context, another set of developers were asked to rate the candidate links from each of the two techniques in terms of how useful they were in fixing the bugs. The eye gaze approach outperforms standard LSI and VSM approaches and reports a 55 % precision and 67 % recall on average for all tasks when compared to how the developers actually fixed the bug. In the second context, the usefulness results show that links generated by our algorithm were considered to be significantly more useful (to fix the bug) than those of the IR technique in a majority of tasks. We discuss the implications of this radically different method of deriving traceability links. Techniques for feature location/bug localization are commonly evaluated on benchmarks formed from commits as is done in the evaluation phase of this study. Although, commits are a reasonable source, they only capture entities that were eventually changed to fix a bug or resolve a feature. We investigate another type of benchmark based on eye tracking data, namely links generated from the bug-localization tasks given to the developers in the data collection phase. The source code entities relevant to subjected bugs recommended from IR methods are evaluated on both commits and links generated from eye gaze. The results of the benchmarking phase show that the use of eye tracking could form an effective (complementary) benchmark and add another interesting perspective in the evaluation of bug-localization techniques.

텐서공간모델 기반 시멘틱 검색 기법

Semantic search is known as a series of activities and techniques to improve the search accuracy by clearly understanding users’ search intent without big cognitive efforts. Usually, semantic search engines requires ontology and semantic metadata to analyze user queries. However, building a particular ontology and semantic metadata intended for large amounts of data is a very time-consuming and costly task. This is why commercialization practices of semantic search are insufficient. In order to resolve this problem, we propose a novel semantic search method which takes advantage of our previous semantic tensor space model. Since each term is represented as the 2nd-order ‘document-by-concept’ tensor (i.e., matrix), and each concept as the 2nd-order ‘document-by-term’ tensor in the model, our proposed semantic search method does not require to build ontology. Nevertheless, through extensive experiments using the OHSUMED document collection and SCOPUS journal abstract data, we show that our proposed method outperforms the vector space model-based search method.

Cross-domain deception detection using support vector networks

Our motivation is to assess the effectiveness of support vector networks (SVN) on the task of detecting deception in texts, as well as to investigate to which degree it is possible to build a domain-independent detector of deception in text using SVN. We experimented with different feature sets for training the SVN: a continuous semantic space model source represented by the latent Dirichlet allocation topics, a word-space model, and dictionary-based features. In this way, a comparison of performance between semantic information and behavioral information is made. We tested several combinations of these features on different datasets designed to identify deception. The datasets used include the DeRev dataset (a corpus of deceptive and truthful opinions about books obtained from Amazon), OpSpam (a corpus of fake and truthful opinions about hotels), and three corpora on controversial topics (abortion, death penalty, and a best friend) on which the subjects were asked to write an idea contrary to what they really believed. We experimented with one-domain setting by training and testing our models separately on each dataset (with fivefold cross-validation), with mixed-domain setting by merging all datasets into one large corpus (again, with fivefold cross-validation), and with cross-domain setting: using one dataset for testing and a concatenation of all other datasets for training. We obtained an average accuracy of 86% in one-domain setting, 75% in mixed-domain setting, and 52 to 64% in cross-domain setting.

Disentangling narrow and coarse semantic networks in the brain: The role of computational models of word meaning.

There has been a recent boom in research relating semantic space computational models to fMRI data, in an effort to better understand how the brain represents semantic information. In the first study reported here, we expanded on a previous study to examine how different semantic space models and modeling parameters affect the abilities of these computational models to predict brain activation in a data-driven set of 500 selected voxels. The findings suggest that these computational models may contain distinct types of semantic information that relate to different brain areas in different ways. On the basis of these findings, in a second study we conducted an additional exploratory analysis of theoretically motivated brain regions in the language network. We demonstrated that data-driven computational models can be successfully integrated into theoretical frameworks to inform and test theories of semantic representation and processing. The findings from our work are discussed in light of future directions for neuroimaging and computational research.

Applying an exemplar model to an implicit rule-learning task: Implicit learning of semantic structure.

Studies of implicit learning often examine peoples' sensitivity to sequential structure. Computational accounts have evolved to reflect this bias. An experiment conducted by Neil and Higham [Neil, G.J., & Higham, P. A.(2012). Implicit learning of conjunctive rule sets: An alternative to artificial grammars. Consciousness and Cognition, 21, 1393-1400] points to limitations in the sequential approach. In the experiment, participants studied words selected according to a conjunctive rule. At test, participants discriminated rule-consistent from rule-violating words but could not verbalize the rule. Although the data elude explanation by sequential models, an exemplar model of implicit learning can explain them. To make the case, we simulate the full pattern of results by incorporating vector representations for the words used in the experiment, derived from the large-scale semantic space models LSA and BEAGLE, into an exemplar model of memory, MINERVA 2. We show that basic memory processes in a classic model of memory capture implicit learning of non-sequential rules, provided that stimuli are appropriately represented.

A lectometric analysis of aggregated lexical variation in written Standard English with Semantic Vector Space models

Lectometry is a corpus-based methodology that explores how multiple language-external dimensions shape language usage in an aggregate perspective. The paper combines this methodology with Semantic Vector Space modeling to investigate lexical variability in written Standard English, as sampled in the original Brown family of corpora (Brown, LOB, Frown and F-LOB). Based on a joint analysis of 303 lexical variables, which are semi-automatically extracted by means of a SVS, we find that lexical variation in the Brown family is systematically related to three lectal dimensions: discourse type (informative versus imaginative), standard variety (British English versus American English), and time period (1960s versus 1990s). It turns out that most lexical variables are sensitive to at least one of these three language-external dimensions, yet not every dimension has dedicated lexical variables: in particular, distinctive lexical variables for the real time dimension fail to emerge.

Meaning change in a petri dish: constructions, semantic vector spaces, and motion charts

AbstractThis paper explores how the visualization tool of motion charts can be used for the analysis of meaning change in linguistic constructions. In previous work, linguistic motion charts have been used to represent diachronic frequency trends and changes in the morphosyntactic behavior of linguistic units. The present paper builds on that work, but it shifts the focus to the study of semantic change. How can motion charts be used to visualize semantic change over time? In order to answer this question, we draw on semantic vector space modeling to visualize aspects of linguistic meaning. As an analogy to this approach, the title of this paper alludes to a petri dish in which the growth and development of biological microorganisms can be observed. On the basis of diachronic corpus data, we monitor developments in the semantic ecology of a construction. This allows us to observe processes such as semantic broadening, semantic narrowing, or semantic shift. We illustrate our approach on the basis of a case study that investigates the diachrony of an English construction that we call the ‘many a NOUN’ construction.

An improved focused crawler based on Semantic Similarity Vector Space Model

A focused crawler is topic-specific and aims selectively to collect web pages that are relevant to a given topic from the Internet. In many studies, the Vector Space Model (VSM) and Semantic Similarity Retrieval Model (SSRM) take advantage of cosine similarity and semantic similarity to compute similarities between web pages and the given topic. However, if there are no common terms between a web page and the given topic, the VSM will not obtain the proper topical similarity of the web page. In addition, if all of the terms between them are synonyms, then the SSRM will also not obtain the proper topical similarity. To address these problems, this paper proposes an improved retrieval model, the Semantic Similarity Vector Space Model (SSVSM), which integrates the TF*IDF values of the terms and the semantic similarities among the terms to construct topic and document semantic vectors that are mapped to the same double-term set, and computes the cosine similarities between these semantic vectors as topic-relevant similarities of documents, including the full texts and anchor texts of unvisited hyperlinks. Next, the proposed model predicts the priorities of the unvisited hyperlinks by integrating the full text and anchor text topic-relevant similarities. The experimental results demonstrate that this approach improves the performance of the focused crawlers and outperforms other focused crawlers based on Breadth-First, VSM and SSRM. In conclusion, this method is significant and effective for focused crawlers.

A Semantic Aspect-Based Vector Space Model to Identify the Event Evolution Relationship within Topics

Understanding how the topic evolves is an important and challenging task. A topic usually consists of multiple related events, and the accurate identification of event evolution relationship plays an important role in topic evolution analysis. Existing research has used the traditional vector space model to represent the event, which cannot be used to accurately compute the semantic similarity between events. This has led to poor performance in identifying event evolution relationship. This paper suggests constructing a semantic aspect-based vector space model to represent the event: First, use hierarchical Dirichlet process to mine the semantic aspects. Then, construct a semantic aspect-based vector space model according to these aspects. Finally, represent each event as a point and measure the semantic relatedness between events in the space. According to our evaluation experiments, the performance of our proposed technique is promising and significantly outperforms the baseline methods.

Performance impact of stop lists and morphological decomposition on word-word corpus-based semantic space models.

Corpus-based semantic space models, which primarily rely on lexical co-occurrence statistics, have proven effective in modeling and predicting human behavior in a number of experimental paradigms that explore semantic memory representation. The most widely studied extant models, however, are strongly influenced by orthographic word frequency (e.g., Shaoul & Westbury, Behavior Research Methods, 38, 190-195, 2006). This has the implication that high-frequency closed-class words can potentially bias co-occurrence statistics. Because these closed-class words are purported to carry primarily syntactic, rather than semantic, information, the performance of corpus-based semantic space models may be improved by excluding closed-class words (using stop lists) from co-occurrence statistics, while retaining their syntactic information through other means (e.g., part-of-speech tagging and/or affixes from inflected word forms). Additionally, very little work has been done to explore the effect of employing morphological decomposition on the inflected forms of words in corpora prior to compiling co-occurrence statistics, despite (controversial) evidence that humans perform early morphological decomposition in semantic processing. In this study, we explored the impact of these factors on corpus-based semantic space models. From this study, morphological decomposition appears to significantly improve performance in word-word co-occurrence semantic space models, providing some support for the claim that sublexical information-specifically, word morphology-plays a role in lexical semantic processing. An overall decrease in performance was observed in models employing stop lists (e.g., excluding closed-class words). Furthermore, we found some evidence that weakens the claim that closed-class words supply primarily syntactic information in word-word co-occurrence semantic space models.

Hidden processes in structural representations: A reply to Abbott, Austerweil, and Griffiths (2015).

In recent work exploring the semantic fluency task, we found evidence indicative of optimal foraging policies in memory search that mirror search in physical environments. We determined that a 2-stage cue-switching model applied to a memory representation from a semantic space model best explained the human data. Abbott, Austerweil, and Griffiths demonstrate how these patterns could also emerge from a random walk applied to a network representation of memory based on human free-association norms. However, a major representational issue limits any conclusions that can be drawn about the process model comparison: Our process model operated on a memory space constructed from a learning model, whereas their model used human behavioral data from a task that is quite similar to the behavior they attempt to explain. Predicting semantic fluency (e.g., how likely it is to say cat after dog in a sequence of animals) from free association (how likely it is to say cat when given dog as a cue) should be possible with a relatively simple retrieval mechanism. The 2 tasks both tap memory, but they also share a common process of retrieval. Assuming that semantic memory is a network from free-association behavior embeds variance due to the shared retrieval process directly into the representation. A simple process mechanism is then sufficient to simulate semantic fluency because much of the requisite process complexity may already be hidden in the representation. (PsycINFO Database Record

Encoding sequential information in semantic space models: comparing holographic reduced representation and random permutation.

Circular convolution and random permutation have each been proposed as neurally plausible binding operators capable of encoding sequential information in semantic memory. We perform several controlled comparisons of circular convolution and random permutation as means of encoding paired associates as well as encoding sequential information. Random permutations outperformed convolution with respect to the number of paired associates that can be reliably stored in a single memory trace. Performance was equal on semantic tasks when using a small corpus, but random permutations were ultimately capable of achieving superior performance due to their higher scalability to large corpora. Finally, “noisy” permutations in which units are mapped to other units arbitrarily (no one-to-one mapping) perform nearly as well as true permutations. These findings increase the neurological plausibility of random permutations and highlight their utility in vector space models of semantics.

Blog Topic Detection Based on the Model

Constructing and updating model from blog is also the process of topic detection and tracking, then, a detecting method of topics on blog based on model is proposed. It includes the use of measuring method Based on the event information to cluster for post and topic information to cluster event set (blog) which is combined with semantic vector space model, the use of the main idea of information granularity of topic detection and tracking algorithm has to be used and improved in order to generate the final clustering. The experimental results show that the algorithm has an accurate result in blog topic detection

Fuzzy control GA with a novel hybrid semantic similarity strategy for text clustering

This paper proposes a fuzzy control genetic algorithm (GA) in conjunction with a novel hybrid semantic similarity measure for document clustering. Since the common clustering algorithms use vector space model (VSM) to represent document, the conceptual relationships between related terms being ignored, we use semantic similarity measures to solve this problem. In general, the semantic similarity measures can be extensively categorized into two kinds: thesaurus-based methods and corpus-based methods. However, in practice the corpus-based method is rather complicated to tackle. We propose and demonstrate a semantic space model (SSM) as the corpus-based method, where the appropriately reduced dimensions in SSM can capture the true relationship between documents in terms of concepts, rather than specific terms. Thus, the thesaurus-based method is combined with our SSM as a hybrid strategy to represent the semantic similarity measure. In GA field, the balance between the capability to converge to an optimum and the capacity to explore new solutions affects the success of search for the global optimum. We utilize a fuzzy control GA to adaptively adjust the influence between these two factors. Two textual data sets from Reuter document collection and 20-newsgroup corpus are tested in our experiments, and the results show that our fuzzy control GA combined with the hybrid semantic similarity strategy apparently outperforms the conventional GA, FCM and K-means with the traditional cosine similarity in VSM. Moreover, the superiorities of the fuzzy control GA and our hybrid semantic strategy are demonstrated by their better performance, in comparison with conventional GA with the same similarity measures.

A novel semantic level text classification by combining NLP and Thesaurus concepts

Text categorization (also known as text classification or topic spotting) is the task of automatically sorting a set of documents into categories from a predefined set. Automated text classification is attractive because it frees organizations from the need of manually organizing document bases, but it can be too expensive or simply not feasible given the time constraints of the application or the number of documents involved. In the previous approaches only the Wikipedia concepts related to terms in syntactic level are used to represent document in semantic level. This paper proposes a new approach to represent semantic level with the use of Word Net. The semantic weight of terms related to the concepts from Wikipedia and Word Net are used to represent semantic information. The semantic vector space model of terms by combining the Word Net and Wikipedia is being further improved the classification accuracy of the Text classification. Because of, two different concept extractor are gives the concepts related to the terms in the syntactic level o find the better concept vector space for documents. So we obtain the improved classification by using this approach. In this study the classification framework are presented. In classification framework, the primary information is effectively kept and the noise is reduced by compressing the original information, so that this framework can guarantee the quality of the input of all classifiers. This proposed method can help to further improve the performance of classification framework by introducing Wikipedia with Word Net. We find that the proposed

Utilizing Conceptual Indexing to Enhance the Effectiveness of Vector Space Model

One of the main purposes of the semantic Web is to improve the retrieval performance of search systems. Unlike keyword based search systems, the semantic search systems aim to discover pages related to the query's concepts rather than merely collecting all pages instantiating its keywords. To that end, the concepts must be defined to be used as a semantic index instead of the traditional lexical one. In fact, The Arabic language is still far from being semantically searchable. Therefore, this paper proposed a model that exploits the Universal Word Net ontology for producing an Arabic Concepts-Space to be used as the index of Semantic Vector Space Model. The Vector Space Model is one of the most common information retrieval models due to its capability of expressing the documents' structure. However, like all keyword-based search systems, its sensitivity to the query's keywords reduces its retrieval effectiveness. The proposed model allows the VSM to represent Arabic documents by their topic, and thus classify them semantically. This, consequently, enhances the retrieval effectiveness of the search system.

Lexical acquisition and semantic space models: Learning the semantics of unknown words

AbstractIn recent studies it has been shown that syntax-based semantic space models outperform models in which the context is represented as a bag-of-words in several semantic analysis tasks. This has been generally attributed to the fact that syntax-based models employ corpora that are syntactically annotated by a parser and a computational grammar. However, if the corpora processed contain words which are unknown to the parser and the grammar, a syntax-based model may lose its advantage since the syntactic properties of such words are unavailable. On the other hand, bag-of-words models do not face this issue since they operate on raw, non-annotated corpora and are thus more robust. In this paper, we compare the performance of syntax-based and bag-of-words models when applied to the task of learning the semantics of unknown words. In our experiments, unknown words are considered the words which are not known to the Alpino parser and grammar of Dutch. In our study, the semantics of an unknown word is defined by finding its most similar word incornetto, a Dutch lexico-semantic hierarchy. We show that for unknown words the syntax-based model performs worse than the bag-of-words approach. Furthermore, we show that if we first learn the syntactic properties of unknown words by an appropriate lexical acquisition method, then in fact the syntax-based model does outperform the bag-of-words approach. The conclusion we draw is that, for words unknown to a given grammar, a bag-of-words model is more robust than a syntax-based model. However, the combination of lexical acquisition and syntax-based semantic models is best suited for learning the semantics of unknown words.

A semantic space approach to the computational semantics of noun compounds

AbstractThis study examines the ability of a semantic space model to represent the meaning of noun compounds such as ‘information gathering’ or ‘heart disease.’ For a semantic space model to compute the meaning and the attributional similarity (or semantic relatedness) for unfamiliar noun compounds that do not occur in a corpus, the vector for a noun compound must be computed from the vectors of its constituent words using vector composition algorithms. Six composition algorithms (i.e., centroid, multiplication, circular convolution, predication, comparison, and dilation) are compared in terms of the quality of the computation of the attributional similarity for English and Japanese noun compounds. To evaluate the performance of the computation of the similarity, this study uses three tasks (i.e., related word ranking, similarity correlation, and semantic classification), and two types of semantic spaces (i.e., latent semantic analysis-based and positive pointwise mutual information-based spaces). The result of these tasks is that the dilation algorithm is generally most effective in computing the similarity of noun compounds, while the multiplication algorithm is best suited specifically for the positive pointwise mutual information-based space. In addition, the comparison algorithm works better for unfamiliar noun compounds that do not occur in the corpus. These findings indicate that in general a semantic space model, and in particular the dilation, multiplication, and comparison algorithms have sufficient ability to compute the attributional similarity for noun compounds.

Latent Semantic Engineering – A new conceptual user-centered design approach

User-centered design (UCD) plays a vital role in the product development process. UCD approaches match designs to user needs. Matching designs to needs improves product quality, customer satisfaction, and product success. The goal of this study is to improve matching accuracy. To achieve the goal, this study introduces conceptual UCD and Latent Semantic Engineering (LSE), a new conceptual UCD approach, defines measures for model accuracy (MA), conceptual matching accuracy (CMA), user-centered design accuracy (UCDA), and conceptual design accuracy (CDA), and compares the LSE approach to other approaches. The LSE approach models conceptual design processes more accurately than other approaches. Functional approaches use subjective weights to match functional needs to physical designs. Emotional (aesthetic) approaches use statistical models to match physical designs to emotional needs. The LSE approach uses a LSE semantic space model to create complete conceptual (aspirational, emotional, functional, physical) designs from complete conceptual needs. The LSE approach improves model accuracy (MA) and matching accuracy (CMA, UCDA, and CDA), compared to other approaches. The LSE approach creates design descriptions more accurately than other approaches. The LSE approach matches designs to user choices, needs, and concepts more accurately than other approaches. This study uses the LSE approach to create customized cell phone designs for individual users. The approach can also be used to create other conceptual designs for either individual or multiple users. Study results can be used to improve product quality, customer satisfaction, product success, and the product development process.