Related Sentences Research Articles

Efficient Conceptual Rule Mining on Text Clusters in Web Documents

Text mining is a modern and computational approach attempts to determine new, formerly unidentified information by pertaining techniques from normal language processing and data mining. Clustering, one of the conventional data mining techniques is an unsubstantiated learning pattern where clustering techniques attempt to recognize intrinsic groupings of the text documents, so that a set of clusters is formed in which clusters reveal high intra-cluster comparison and low inter-cluster similarity. Most current document clustering methods are based on the Vector Space Model (VSM), which is a widely used data representation for text classification and clustering. Moreover, weighting these features accurately also affects the result of the clustering algorithm substantially. The previous work described the conceptual text clustering to web documents, containing various mark up language formats associated with the documents (term extraction mode). In this work, we are going to present a Conceptual rule mining which is generated for the sentence meaning and related sentences in the document. Weights are appropriated for the sentences having higher contribution to the topic of the document. Conditional probability is evaluated for the sentence weights. Probability ratio is identified for the sentence similarity from which unique sentence meaning contributing to the document topic are listed. Experiments are conducted with the web documents extracted from the research repositories to evaluate the efficiency of the proposed efficient conceptual rule mining on text clusters in web documents and compared with an existing Model for Concept Based Clustering and Classification in terms of Topic related rules, Weights of the influential sentence, Topic Sensitivity..

Action-related semantic content and negation polarity modulate motor areas during sentence reading: An event-related desynchronization study

Our study evaluated motor cortex involvement during silent reading of sentences referring to hand actions. We aimed at defining whether sentential polarity (affirmative vs. negative) would modulate motor cortex activation using the event-related desynchronization (ERD) analysis of the mu rhythm. Eleven healthy volunteers performed a reading task involving 160 sentences (80 affirmative: 40 hand-related, 40 abstract; 80 negative: 40 hand-related, 40 abstract). After reading each sentence, subjects had to decide whether the verb was high or low frequency in Italian. Electroencephalographic (EEG) activity was recorded with 32 surface electrodes and mu ERD analyses were performed for each subject. Hand-action related sentences induced a greater mu ERD over the left premotor and motor hand areas compared to abstract sentences. Mu ERD was greater and temporally delayed when the hand-related verbs were presented in the negative versus affirmative form. As predicted by the "embodied semantic" theory of language understanding, motor areas were activated during sentences referring to hand actions. In addition, motor cortex activation was larger for negative than affirmative motor sentences, a finding compatible with the hypothesis that comprehension is more demanding in the specific case of motor content negation.

Semantic binding, not attentional control, generates coherent global structure in children's narrative memory

Encoding and retrieving global narrative structure influences children's narrative recall. The influence of age and attentional/executive resources on binding processes during sentence list recall was examined in 5- to 6- and 8- to 9-year-old children. Older and younger children showed superior recall of lists, and achieved higher scores on two metrics of chunking; access to different sentences (i.e., number of chunks) and sentence completion (i.e., chunk size), when lists were presented within a coherent global structure. Children's list recall and sentence access, but not their sentence completion scores, were affected by a concurrent self-paced attention-demanding task. Children, unlike adults, engage in active storage of verbal information in thematically related sentence lists. The coherence-advantage effect was stable across age groups and insensitive to the secondary task. Overall, findings imply that semantic binding generates stronger memory representations and superior recall for sentences within a story context than for sentence sets that lack global narrative structure.

Immediate use of prosody and context in predicting a syntactic structure

Numerous studies have reported an effect of prosodic information on parsing but whether prosody can impact even the initial parsing decision is still not evident. In a visual world eye-tracking experiment, we investigated the influence of contrastive intonation and visual context on processing temporarily ambiguous relative clause sentences in Japanese. Our results showed that listeners used the prosodic cue to make a structural prediction before hearing disambiguating information. Importantly, the effect was limited to cases where the visual scene provided an appropriate context for the prosodic cue, thus eliminating the explanation that listeners have simply associated marked prosodic information with a less frequent structure. Furthermore, the influence of the prosodic information was also evident following disambiguating information, in a way that reflected the initial analysis. The current study demonstrates that prosody, when provided with an appropriate context, influences the initial syntactic analysis and also the subsequent cost at disambiguating information. The results also provide first evidence for pre-head structural prediction driven by prosodic and contextual information with a head-final construction.

How do people produce ungrammatical utterances?

We investigate whether people might come to produce utterances that they regard as ungrammatical by examining the production of ungrammatical verb-construction combinations (e.g., The dancer donates the soldier the apple) after exposure to both grammatical and ungrammatical sentences. We contrast two accounts of how such production might take place: an abstract structural persistence account, according to which it is caused by increased activation of an abstract structural rule; and a lexically-driven persistence account, according to which it requires previous exposure to the same (ungrammatical) verb-construction combination. In four structural priming experiments, we found that sentences with ungrammatical verb-construction combinations were produced only after exposure to similar ungrammatical exemplars containing the same verb, but not after such sentences with a different verb, or grammatical sentences with the same construction. These results indicate that people can produce sentences with ungrammatical verb-construction combinations after brief exposure to related sentences, and provide support for the lexically-driven persistence account of such production.

Mutually Reinforced Manifold-Ranking Based Relevance Propagation Model for Query-Focused Multi-Document Summarization

Manifold-ranking has been recently exploited for query-focused summarization. It propagates query relevance from the given query to the document sentences by making use of both the relationships among the sentences and the relationships between the given query and the sentences. The sentences in a document set can be grouped into several topic themes with each theme represented by a cluster of highly related sentences. However, it is a well-recognized fact that a document set often covers a number of such topic themes. In this paper, we present a novel model to enhance manifold-ranking based relevance propagation via mutual reinforcement between sentences and theme clusters. Based on the proposed model, we develop two new sentence ranking algorithms, namely the reinforcement after relevance propagation (RARP) algorithm and the reinforcement during relevance propagation (RDRP) algorithm. The convergence issues of the two algorithms are examined. When evaluated on the DUC2005-2007 datasets and TAC2008 dataset, the performance of the two proposed algorithms is comparable with that of the top three systems. The results also demonstrate that the RDRP algorithm is more effective than the RARP algorithm.

Automatically building templates for entity summary construction

In this paper, we propose a novel approach to automatic generation of summary templates from given collections of summary articles. We first develop an entity-aspect LDA model to simultaneously cluster both sentences and words into aspects. We then apply frequent subtree pattern mining on the dependency parse trees of the clustered and labeled sentences to discover sentence patterns that well represent the aspects. Finally, we use the generated templates to construct summaries for new entities. Key features of our method include automatic grouping of semantically related sentence patterns and automatic identification of template slots that need to be filled in. Also, we implement a new sentence compression algorithm which use dependency tree instead of parser tree. We apply our method on five Wikipedia entity categories and compare our method with three baseline methods. Both quantitative evaluation based on human judgment and qualitative comparison demonstrate the effectiveness and advantages of our method.

Effects of Local and Global Context on Processing Sentences with Subject and Object Relative Clauses

An eye tracking study investigated the effects of local and global discourse context on the processing of subject and object relative clauses, whereby the contexts favored either a subject relative clause interpretation or an object relative clause interpretation. The fixation data replicated previous studies showing that object relative clause sentences were more difficult to process than subject relative sentences. Crucially, however, the reading difficulty asymmetry between subject and object relative clause sentences disappeared when the sentences were presented with a local or a global discourse context that favored the objects in the object relative clauses. These findings demonstrate that the evidence for a syntax-based account of sentence processing is found when sentences are presented in isolation. However, if sentences are placed more naturally, in context, discourse factors outweigh the initial structural assignment.

The Influence of Story Context on a Working Memory Span Task

The purpose of the present study was to examine factors that could influence whether recall performance in the reading span task (Daneman & Carpenter, 1980 ) would benefit from the contextual information from the sentences in the processing component of the task. More specifically, we investigated whether people would benefit from sentence sets that formed short stories or when the entire span task was one continuous story. Overall, there was a clear benefit for contextually related sentence sets (i.e., the story span tasks) compared to the traditional reading span task. However, the benefit was eliminated when the entire set formed one continuous story. These results support the recall reconstruction hypothesis for working memory (Towse, Cowan, Hitch, & Horton, 2008 ), which suggests that people may strategically use the content of the sentences from the processing component of the reading span task as memorial cues to reconstruct the target words of the storage component. However, this benefit is constrained to scenarios when the contextual cues are unique to a specific set.

Sentence processing in Lewy body spectrum disorder: The role of working memory

Prior work has related sentence processing to executive deficits in non-demented patients with Parkinson’s disease (PD). We extended this investigation to patients with dementia with Lewy bodies (DLB) and PD dementia (PDD) by examining grammatical and working memory components of sentence processing in the full range of patients with Lewy body spectrum disorder (LBSD). Thirty-three patients with LBSD were given a two-alternative, forced-choice sentence-picture matching task. Sentence type, working memory, and grammatical structure were systematically manipulated in the sentences. We found that patients with PDD and DLB were significantly impaired relative to non-demented PD patients and healthy controls. The deficit in PDD/DLB was most pronounced for sentences lengthened by the strategic placement of an additional prepositional phrase and for sentences with an additional proposition due to a center-embedded clause. However, there was no effect for subject-relative versus object-relative grammatical structure. An MRI voxel-based morphometry analysis in a subset of patients showed significant gray matter thinning in the frontal lobe bilaterally, and this extended to temporal, parietal and occipital regions. A regression analysis related sentence processing difficulty in LBSD to frontal neocortex, including inferior prefrontal, premotor, and dorsolateral prefrontal regions, as well as right superior temporal cortex. These findings are consistent with the hypothesis that patients with PDD and DLB have difficulty processing sentences with increased working memory demands and that this deficit is related in part to their frontal disease.

TMS-induced modulation of action sentence priming in the ventral premotor cortex

Despite accumulating evidence that cortical motor areas, particularly the lateral premotor cortex, are activated during language comprehension, the question of whether motor processes help mediate the semantic encoding of language remains controversial. To address this issue, we examined whether low frequency (1Hz) repetitive transcranial magnetic stimulation (rTMS) of the left ventral premotor cortex (PMv) can interfere with the comprehension of sentences describing manual actions, visual properties of manipulable and non-manipulable objects, and actions of the lips and mouth. Using a primed semantic decision task, sixteen participants were asked to determine for a given sentence whether or not an auditorily presented target word was congruent with the sentence. We hypothesized that if the left PMv is contributing semantic information that is used to comprehend action and object related sentences, then TMS applied over PMv should result in a disruption of semantic priming. Our results show that TMS reduces semantic priming, induces a shift in response bias, and increases response sensitivity, but does so only during the processing of manual action sentences. This suggests a preferential contribution of PMv to the processing of sentences describing manual actions compared to other types of sentences.

Finding Universal Word for Bangla Language: Attribute Analysis Approach

Universal natural language (UNL) deals with communication across nations of different languages. It covers many different related disciplines which are linguistic, epistemology etc. UNL helps to overcome the language barrier among people of different nations to solve problems of globalization and geopolitical interdependence. This paper examines bangla root words semantically to find out the universal words according to the usage of words into sentences in relation to the universal network language. The paper also shows different techniques to find the semantic attributes which are the indicators to make rule set. Also, it discusses semantic coverage issues for Bangla to explore the development of universal network language.

Enhancing sentence‐level clustering with integrated and interactive frameworks for theme‐based summarization

AbstractSentence clustering plays a pivotal role in theme‐based summarization, which discovers topic themes defined as the clusters of highly related sentences to avoid redundancy and cover more diverse information. As the length of sentences is short and the content it contains is limited, the bag‐of‐words cosine similarity traditionally used for document clustering is no longer suitable. Special treatment for measuring sentence similarity is necessary. In this article, we study the sentence‐level clustering problem. After exploiting concept‐ and context‐enriched sentence vector representations, we develop two co‐clustering frameworks to enhance sentence‐level clustering for theme‐based summarization—integrated clustering and interactive clustering—both allowing word and document to play an explicit role in sentence clustering as independent text objects rather than using word or concept as features of a sentence in a document set. In each framework, we experiment with two‐level co‐clustering (i.e., sentence‐word co‐clustering or sentence‐document co‐clustering) and three‐level co‐clustering (i.e., document‐sentence‐word co‐clustering). Compared against concept‐ and context‐oriented sentence‐representation reformation, co‐clustering shows a clear advantage in both intrinsic clustering quality evaluation and extrinsic summarization evaluation conducted on the Document Understanding Conferences (DUC) datasets.

The rhymes that the reader perused confused the meaning: Phonological effects during on-line sentence comprehension

Research on written language comprehension has generally assumed that the phonological properties of a word have little effect on sentence comprehension beyond the processes of word recognition. Two experiments investigated this assumption. Participants silently read relative clauses in which two pairs of words either did or did not have a high degree of phonological overlap. Participants were slower reading and less accurate comprehending the overlap sentences compared to the non-overlapping controls, even though sentences were matched for plausibility and differed by only two words across overlap conditions. A comparison across experiments showed that the overlap effects were larger in the more difficult object relative than in subject relative sentences. The reading patterns showed that phonological representations affect not only memory for recently encountered sentences but also the developing sentence interpretation during on-line processing. Implications for theories of sentence processing and memory are discussed.

A spectral analysis approach to document summarization: Clustering and ranking sentences simultaneously

Automatic document summarization aims to create a compressed summary that preserves the main content of the original documents. It is a well-recognized fact that a document set often covers a number of topic themes with each theme represented by a cluster of highly related sentences. More important, topic themes are not equally important. The sentences in an important theme cluster are generally deemed more salient than the sentences in a trivial theme cluster. Existing clustering-based summarization approaches integrate clustering and ranking in sequence, which unavoidably ignore the interaction between them. In this paper, we propose a novel approach developed based on the spectral analysis to simultaneously clustering and ranking of sentences. Experimental results on the DUC generic summarization datasets demonstrate the improvement of the proposed approach over the other existing clustering-based approaches.

Do Not Resonate with Actions: Sentence Polarity Modulates Cortico-Spinal Excitability during Action-Related Sentence Reading

BackgroundTheories of embodied language suggest that the motor system is differentially called into action when processing motor-related versus abstract content words or sentences. It has been recently shown that processing negative polarity action-related sentences modulates neural activity of premotor and motor cortices.Methods and FindingsWe sought to determine whether reading negative polarity sentences brought about differential modulation of cortico-spinal motor excitability depending on processing hand-action related or abstract sentences. Facilitatory paired-pulses Transcranial Magnetic Stimulation (pp-TMS) was applied to the primary motor representation of the right-hand and the recorded amplitude of induced motor-evoked potentials (MEP) was used to index M1 activity during passive reading of either hand-action related or abstract content sentences presented in both negative and affirmative polarity. Results showed that the cortico-spinal excitability was affected by sentence polarity only in the hand-action related condition. Indeed, in keeping with previous TMS studies, reading positive polarity, hand action-related sentences suppressed cortico-spinal reactivity. This effect was absent when reading hand action-related negative polarity sentences. Moreover, no modulation of cortico-spinal reactivity was associated with either negative or positive polarity abstract sentences.ConclusionsOur results indicate that grammatical cues prompting motor negation reduce the cortico-spinal suppression associated with affirmative action sentences reading and thus suggest that motor simulative processes underlying the embodiment may involve even syntactic features of language.

WE COULD HAVE LOVED AND LOST, OR WE NEVER COULD HAVE LOVE AT ALL

This study investigated sentence-processing strategies adopted by advanced nonnative speakers (NNSs) and native speakers (NSs) of English in the context of an English structure with which NNSs reportedly have an acquisition difficulty (e.g., Swan & Smith, 2001)—namely, modal perfect (MP). Participants read MP sentences such as He could have worked at the shoe factory and closely related analogous sentences (e.g., He could have work at the shoe factory), and reading times and errors were measured in an online grammaticality-judgment task. It was hypothesized that NSs would have a processing preference for MP sentences compared to the analogues, reflecting the primacy of syntactic information in NS processing and a preference for late closure, whereas NNSs would show no such preference because they rely less on syntactic information when processing sentences. The results revealed, however, that both NSs and NNSs read MP sentences more quickly and with fewer errors than the closely related analogues, consistent with a processing preference for MP sentences. Both groups were also influenced by word-category frequency information, which moderated, but did not fundamentally alter, their syntactic preference for MP. The significance of these findings is discussed in terms of models of second-language sentence processing and NNSs’ reported MP acquisition difficulty.

The role of working memory and contextual constraints in children's processing of relative clauses

An auditory sentence comprehension task investigated the extent to which the integration of contextual and structural cues was mediated by verbal memory span with 32 English-speaking six- to eight-year-old children. Spoken relative clause sentences were accompanied by visual context pictures which fully (depicting the actions described within the relative clause) or partially (depicting several referents) met the pragmatic assumptions of relativization. Comprehension of the main and relative clauses of centre-embedded and right-branching structures was compared for each context. Pragmatically appropriate contexts exerted a positive effect on relative clause comprehension, but children with higher memory spans demonstrated a further benefit for main clauses. Comprehension for centre-embedded main clauses was found to be very poor, independently of either context or memory span. The results suggest that children have access to adult-like linguistic processing mechanisms, and that sensitivity to extralinguistic cues is evident in young children and develops as cognitive capacity increases.

Unarticulated comparison classes

Relative gradable adjectives (“tall”, “big”) raise serious problems in semantics. First, I explore a few intuitions about relative gradable predicates and clarify some points. Second, I propose a multipropositionalist, Perry-inspired, perspective on relative gradable predicate utterances. Perry’s version of multipropositionalism introduces many different propositions or contents, including indexical content, referential content, and designational content, which are carried by the utterance of a single sentence. It also offers a new approach to relative gradable predicates, and suggests an explanation for the way relative predicates work in linguistic communication and for the divergent intuitions about these predicates. My approach focuses on the cognitive significance of relative gradable sentence utterances.

Disentangling Leibniz's Views on Relations and Extrinsic Denominations

Disentangling Leibniz's Views on Relations and Extrinsic Denominations Anja Jauernig (bio) 1. Introduction Most commentators agree that Leibniz advocates some version of a doctrine of the ideality or reducibility of relations, but there is considerable disagreement on the question of what exactly this doctrine is supposed to amount to. This question is pressing because of the central place that Leibniz's theory of relations occupies in his philosophy. How one understands Leibniz's views on relations will influence how one understands Leibniz's complete concept doctrine, his (super)essentialism, the principle of the identity of indiscernibles, his account of compossibility, and his theory of space and time, to name just a few examples.1 [End Page 171] The most divisive question in this context is whether Leibniz is what I will call a "reductionist," i.e., whether he advocates some form of "reductionism" about relations. There are several ways in which this question could be understood, depending on how the term 'reductionism' is explicated. A reductionist about relations could be said to hold that all there is in the world are individuals and their intrinsic properties, or that a complete description of the world is possible in purely non-relational terms, or that all relations and extrinsic properties (strongly) supervene on intrinsic properties—which are popular ways in which Leibniz's views on relations and extrinsic denominations have been interpreted. The question of whether Leibniz is a reductionist splits commentators into two camps: those who answer the question in the affirmative,2 and those who answer it in the negative.3 Despite much good work on this topic, the proponents of the two camps have been talking past each other to a considerable extent. One of the main factors [End Page 172] hampering the discussion is the widespread, if only implicit, assumption that there must be one unified thesis, or, at most, a small number of closely related theses, that Leibniz is trying to articulate in his various pronouncements on relations and extrinsic denominations. On my view, this assumption is clearly false.4 Another obstacle to exegetical progress is the frequent inadequate appreciation of Leibniz's division of reality into different ontological levels. The failure to take this level distinction into account tends to obscure the complex and multi-faceted nature of Leibniz's views on relations and extrinsic denominations. Once Leibniz's various theses about relations and extrinsic properties have been sorted out, it becomes clear that both camps of commentators are correct about some aspects of Leibniz's views, even though the overall flavor of Leibniz's position on relations remains non-reductionist. The argument of this paper will proceed as follows. Section 2 covers some preliminaries and background material, including a sketch of Leibniz's tiered ontology. In section 3, I discuss Leibniz's thesis of the ideality of abstract relations. Section 4 explicates the sense in which all phenomenal extrinsic properties can be reduced to the perceptions of monads, and addresses the question of whether monads have irreducibly extrinsic properties. In section 5, I analyze Leibniz's notorious claims that there are no purely extrinsic denominations and that every extrinsic denomination has a foundation in the thing denominated, which I take to be concerned primarily with the phenomenal level of reality. I argue that these claims do not commit Leibniz to reductionism, but they warrant ascribing to him five other weaker theses about extrinsic denominations and their relation to intrinsic denominations. In the sixth and final section, I revisit Leibniz's much discussed project of reformulating relational sentences into non-relational ones, and identify two more Leibnizian theses about relations and extrinsic properties. 2. Preliminaries and Background The main focus of this paper is on Leibniz's views on relations and extrinsic properties in his mature philosophy, which I take to have been in place by the mid-1680s, at least as far as its main doctrines and principles are concerned, several changes in emphasis and presentation style notwithstanding.5 An important step toward disentangling these views is a careful appreciation of Leibniz's division of reality into several ontological levels. This level-distinction is widely acknowledged in the literature, but there are different views...