Sentence Clustering Research Articles

Analysis of Particular Parameters of a Social Situation of the Development of a Pre-School Aged Child in Conditions of the Family and Pre-School Education Institutions

The changing conditions of social development give considerable relevance to a study of parameters of a social situation of the development of the individual at the stage of childhood. The aim of the study: research of characteristics of a social situation of the development of a pre-school aged child at the present stage of society. The study was conducted in the cities of Minsk and Zhlobin (The Republic of Belarus); children of pre-school education institutions (n=100) and their parents (n=28) participated in the study. Diagnostic tools: “Parents composition”, “Choice in action”, “Stair”, “Finish a story”, a conversation on three clusters of unfinished sentences. The results of the empirical study revealed a predominance of non-constructive child-parent interaction in the respondents’ families. The analysis of a child’s position in a group of an education institution generally revealed the existence of a favourable climate in the given subsystem of relations. Preferences in one or another type of interactions are connected with the self-assessment, a position in a group and a level of awareness of ethical norms and values. Optimization of the main parameters of pre-school aged children interaction is a relevant direction of the support of positive socialization.

BiDETS: Binary Differential Evolutionary based Text Summarization

In extraction-based automatic text summarization (ATS) applications, feature scoring is the cornerstone of the summarization process since it is used for selecting the candidate summary sentences. Handling all features equally leads to generating disqualified summaries. Feature Weighting (FW) is an important approach used to weight the scores of the features based on their presence importance in the current context. Therefore, some of the ATS researchers have proposed evolutionary-based machine learning methods, such as Particle Swarm Optimization (PSO) and Genetic Algorithm (GA), to extract superior weights to their assigned features. Then the extracted weights are used to tune the scored-features in order to generate a high qualified summary. In this paper, the Differential Evolution (DE) algorithm was proposed to act as a feature weighting machine learning method for extraction-based ATS problems. In addition to enabling the DE to represent and control the assigned features in binary dimension space, it was modulated into a binary coded format. Simple mathematical calculation features have been selected from various literature and employed in this study. The sentences in the documents are first clustered according to a multi-objective clustering concept. DE approach simultaneously optimizes two objective functions, which are compactness measuring and separating the sentence clusters based on these objectives. In order to automatically detect a number of sentence clusters contained in a document, representative sentences from various clusters are chosen with certain sentence scoring features to produce the summary. The method was tested and trained using DUC2002 dataset to learn the weight of each feature. To create comparative and competitive findings, the proposed DE method was compared with evolutionary methods: PSO and GA. The DE was also compared against the best and worst systems benchmark in DUC 2002. The performance of the BiDETS model is scored with 49% similar to human performance (52%) in ROUGE-1; 26% which is over the human performance (23%) using ROUGE-2; and lastly 45% similar to human performance (48%) using ROUGE-L. These results showed that the proposed method outperformed all other methods in terms of F-measure using the ROUGE evaluation tool.

A Multilingual Study of Multi-Sentence Compression using Word Vertex-Labeled Graphs and Integer Linear Programming

Multi-Sentence Compression (MSC) aims to generate a short sentence with the key information from a cluster of similar sentences. MSC enables summarization and question-answering systems to generate outputs combining fully formed sentences from one or several documents. This paper describes an Integer Linear Programming method for MSC using a vertex-labeled graph to select different keywords, with the goal of generating more informative sentences while maintaining their grammaticality. Our system is of good quality and outperforms the state of the art for evaluations led on news datasets in three languages: French, Portuguese and Spanish. We led both automatic and manual evaluations to determine the informativeness and the grammaticality of compressions for each dataset. In additional tests, which take advantage of the fact that the length of compressions can be modulated, we still improve ROUGE scores with shorter output sentences.

A semantic approach to extractive multi-document summarization: Applying sentence expansion for tuning of conceptual densities

Today, due to a vast amount of textual data, automated extractive text summarization is one of the most common and practical techniques for organizing information. Extractive summarization selects the most appropriate sentences from the text and provide a representative summary. The sentences, as individual textual units, usually are too short for major text processing techniques to provide appropriate performance. Hence, it seems vital to bridge the gap between short text units and conventional text processing methods.In this study, we propose a semantic method for implementing an extractive multi-document summarizer system by using a combination of statistical, machine learning based, and graph-based methods. It is a language-independent and unsupervised system. The proposed framework learns the semantic representation of words from a set of given documents via word2vec method. It expands each sentence through an innovative method with the most informative and the least redundant words related to the main topic of sentence. Sentence expansion implicitly performs word sense disambiguation and tunes the conceptual densities towards the central topic of each sentence. Then, it estimates the importance of sentences by using the graph representation of the documents. To identify the most important topics of the documents, we propose an inventive clustering approach. It autonomously determines the number of clusters and their initial centroids, and clusters sentences accordingly. The system selects the best sentences from appropriate clusters for the final summary with respect to information salience, minimum redundancy, and adequate coverage.A set of extensive experiments on DUC2002 and DUC2006 datasets was conducted for investigating the proposed scheme. Experimental results showed that the proposed sentence expansion algorithm and clustering approach could considerably enhance the performance of the summarization system. Also, comparative experiments demonstrated that the proposed framework outperforms most of the state-of-the-art summarizer systems and can impressively assist the task of extractive text summarization.

Modeling coherence by ordering paragraphs using pointer networks

Coherence is a distinctive feature in well-written documents. One method to study coherence is to analyze how sentences are ordered in a document. In Multi-document Summarization, sentences from different sources need to be ordered. Cluster-based ordering algorithms aim to study various themes or topics that are present in a set of sentences. After the clusters of sentences have been identified, sentences are ordered within each cluster in isolation. One challenge that remains is to order these clusters or paragraphs to obtain a coherent ordering of information. Inspired by the success of deep neural networks in several NLP tasks, we propose an RNN-based encoder–decoder system to predict order for a given set of loose clusters or paragraphs. Universal Sentence Encoder (USE) is used to encode paragraphs into high dimensional embeddings, which are then fed into an LSTM encoder and consecutively passed to a pointer network, which finally outputs the paragraph order. Since Wikipedia is a source of well- structured articles, it is used to generate multiple datasets. Based on our experimental results, the proposed model satisfactorily outperforms the baseline model across multiple datasets. We observe a two-fold increase in Kendall’s tau values for the final paragraph orderings.

Extracting Phrases as Software Features From Overlapping Sentence Clusters in Product Descriptions

Extracting software features from the public product descriptions in the natural language is beneficial for developing new products. Because software features are often expressed in phrases, many approaches currently propose to define phrase patterns and extract phrases as features from product descriptions accordingly. However, there are often lots of noisy phrases extracted because public product descriptions are described freely by different designers and it is difficult to obtain accurate phrase patterns in practice. It is also not suitable to filter those noisy phrases according to frequencies because some important features may be infrequent. To address such issues, this paper proposes a feature extraction approach by extracting phrases as features from the sentence clusters among product descriptions rather than directly from the product descriptions. Considering that more than one feature can be described in one sentence, a new algorithm is designed to detect the overlapping sentence clusters from public product descriptions. It can detect all potential sentence clusters and reduce the affection of noisy descriptions. By taking bigram collocations as the phrase pattern, the bigram collocations containing cluster keywords are elicited as features from each detected sentence cluster. The evaluations conducted on the public software product descriptions from the application market of Softpedia.com, have shown that the proposed approach has better performance than the competitive approaches in terms of precision and time consumption.

A Novel Sentence Embedding Based Topic Detection Method for Microblogs

Topic detection is a difficult challenging task, especially when the exact number of topics is unknown. In this article, we present a novel topic detection approach based on neural computing to detect topics in a microblogging dataset. We use an unsupervised neural sentence embedding model to map blogs to an embedding space. The proposed model is a weighted power mean sentence embedding model in which weights are calculated by a targeted attention mechanism. The experimental results show that our embedding model performs better than baseline in sentence clustering. In addition, we propose a clustering algorithm, referred to as Relationship-Aware DBSCAN (RADBSCAN), to discover topics from a microblogging dataset in which the number of topics is automatically determined by the characteristics of the dataset. Moreover, to provide parameter insensibility, we use the forwarding relationship in the blogs as a bridge of two independent clusters. Finally, we validate the proposed method on a dataset from the Sina microblog. The results show that our approach can detect all topics successfully and can extract the keywords of each topic.

Compressive approaches for cross-language multi-document summarization

The popularization of social networks and digital documents has quickly increased the multilingual information available on the Internet. However, this huge amount of data cannot be analyzed manually. This paper deals with Cross-Language Text Summarization (CLTS) that produces a summary in a different language from the source documents. We describe three compressive CLTS approaches that analyze the text in the source and target languages to compute the relevance of sentences. Our systems compress sentences at two levels: clusters of similar sentences are compressed using a multi-sentence compression (MSC) method and single sentences are compressed using a Neural Network model. The version of our approach using multi-sentence compression generated more informative French-to-English cross-lingual summaries than extractive state-of-the-art systems. Moreover, these cross-lingual summaries have a grammatical quality similar to extractive approaches.

Ensemble-based deep reinforcement learning for chatbots

Trainable chatbots that exhibit fluent and human-like conversations remain a big challenge in artificial intelligence. Deep Reinforcement Learning (DRL) is promising for addressing this challenge, but its successful application remains an open question. This article describes a novel ensemble-based approach applied to value-based DRL chatbots, which use finite action sets as a form of meaning representation. In our approach, while dialogue actions are derived from sentence clustering, the training datasets in our ensemble are derived from dialogue clustering. The latter aim to induce specialised agents that learn to interact in a particular style. In order to facilitate neural chatbot training using our proposed approach, we assume dialogue data in raw text only – without any manually-labelled data. Experimental results using chitchat data reveal that (1) near human-like dialogue policies can be induced, (2) generalisation to unseen data is a difficult problem, and (3) training an ensemble of chatbot agents is essential for improved performance over using a single agent. In addition to evaluations using held-out data, our results are further supported by a human evaluation that rated dialogues in terms of fluency, engagingness and consistency – which revealed that our proposed dialogue rewards strongly correlate with human judgements.

Word Sense Disambiguation in Bengali language using unsupervised methodology with modifications

In this work, Word Sense Disambiguation (WSD) in Bengali language is implemented using unsupervised methodology. In the first phase of this experiment, sentence clustering is performed using Maximum Entropy method and the clusters are labelled with their innate senses by manual intervention, as these sense-tagged clusters could be used as sense inventories for further experiment. In the next phase, when a test data comes to be disambiguated, the Cosine Similarity Measure is used to find the closeness of that test data with the initially sense-tagged clusters. The minimum distance of that test data from a particular sense-tagged cluster assigns the same sense to the test data as that of the cluster it is assigned with. This strategy is considered as the baseline strategy, which produces 35% accurate result in WSD task. Next, two extensions are adopted over this baseline strategy: (a) Principal Component Analysis (PCA) over the feature vector, which produces 52% accuracy in WSD task and (b) Context Expansion of the sentences using Bengali WordNet coupled with PCA, which produces 61% accuracy in WSD task. The data sets that are used in this work are obtained from the Bengali corpus, developed under the Technology Development for the Indian Languages (TDIL) project of the Government of India, and the lexical knowledge base (i.e., the Bengali WordNet) used in the work is developed at the Indian Statistical Institute, Kolkata, under the Indradhanush Project of the DeitY, Government of India. The challenges and the pitfalls of this work are also described in detail in the pre-conclusion section.

Neural sentence fusion for diversity driven abstractive multi-document summarization

The lack of multi-document based models and the inaccuracy in representing multiple long documents into a fixed size vector inspired us to solve abstractive multi-document summarization. Also, there is lack of good multi-document based human-authored datasets to train any encoder-decoder models. To overcome this, we have designed complementary models for two different tasks such as sentence clustering and neural sentence fusion. In this work, we minimize the risk of producing incorrect fact by encoding a related set of sentences as an input to the encoder. We have applied our complementary models to implement a full abstractive multi-document summarization system which simultaneously considers importance, coverage, and diversity under a desired length limit. We conduct extensive experiments for all the proposed models which bring significant improvements over the state-of-the-art methods across different evaluation metrics.

Multimodal Neural Machine Translation With Weakly Labeled Images

Machine translation refers to a fully automated process that translates a user’s input text into a target language. To improve the accuracy of machine translation, studies usually exploit not only the input text itself but also various background knowledge related to the text, such as visual information or prior knowledge. Herein, in this paper, we propose a multimodal neural machine translation system that uses both texts and their related images to translate Korean image captions into English. The data in the experiment is a set of unlabeled images only containing bilingual captions. To train the system with a supervised learning approach, we propose a weak-labeling method that selects a keyword from an image caption using feature selection methods. The keywords are used to roughly determine an image label. We also introduce an improved feature selection method using sentence clustering to select keywords that reflect the characteristics of the image captions more accurately. We found that our multimodal system achieves an improved performance compared to a text-only neural machine translation system (baseline). Furthermore, the additional images have positive impacts on addressing the issue of under-translation, where some words in a source sentence are falsely translated or not translated at all.

EmoCo: Visual Analysis of Emotion Coherence in Presentation Videos.

Emotions play a key role in human communication and public presentations. Human emotions are usually expressed through multiple modalities. Therefore, exploring multimodal emotions and their coherence is of great value for understanding emotional expressions in presentations and improving presentation skills. However, manually watching and studying presentation videos is often tedious and time-consuming. There is a lack of tool support to help conduct an efficient and in-depth multi-level analysis. Thus, in this paper, we introduce EmoCo, an interactive visual analytics system to facilitate efficient analysis of emotion coherence across facial, text, and audio modalities in presentation videos. Our visualization system features a channel coherence view and a sentence clustering view that together enable users to obtain a quick overview of emotion coherence and its temporal evolution. In addition, a detail view and word view enable detailed exploration and comparison from the sentence level and word level, respectively. We thoroughly evaluate the proposed system and visualization techniques through two usage scenarios based on TED Talk videos and interviews with two domain experts. The results demonstrate the effectiveness of our system in gaining insights into emotion coherence in presentations.

Nudge the judge? Theorizing the interaction between heuristics, sentencing guidelines and sentence clustering

Although it has long been acknowledged that heuristics influence judicial decision making, researchers have yet to explore how sentencing guidelines might interact with heuristics to shape sentencing decisions. This article contributes to addressing this gap in the literature in three ways: first, by considering how heuristics might help produce the phenomenon of sentence clustering, in which a significant proportion of sentences are concentrated around a small number of outcomes; second, by reflecting on the role of sentencing guidelines as a feature of the environment within which sentencing decisions are made; and third, by analysing the guidelines from Minnesota and from England and Wales, theorizing how their content might interact with heuristics to make clustering more or less likely. Ultimately, we argue that sentencing guidelines likely affect the role played by heuristics in shaping sentencing decisions and, consequently, that their design should be informed by research evidence from the decision sciences.

Handling WSD using Hierarchical Clustering Algorithm with sentences

Clustering is the process of grouping objects into subsets that have meaning in the context of a particular problem. It does not rely on predefined classes. It is referred to as an unsupervised learning method because no information is provided about the "right answer" for any of the objects. Many clustering algorithms have been proposed and are used based on different applications. Sentence clustering is one of best clustering technique. Hierarchical Clustering Algorithm is applied for multiple levels for accuracy. For tagging purpose POS tagger, porter stemmer is used. WordNet dictionary is utilized for determining the similarity by invoking the Jiang Conrath and Cosine similarity measure. Grouping is performed with respect to the highest similarity measure value with a mean threshold. This paper incorporates many parameters for finding similarity between words. In order to identify the disambiguated words, the sense identification is performed for the adjectives and comparison is performed. semcor and machine learning datasets are employed. On comparing with previous results for WSD, our work has improvised a lot which gives a percentage of 91.2%

CIBS: A biomedical text summarizer using topic-based sentence clustering.

Automatic text summarizers can reduce the time required to read lengthy text documents by extracting the most important parts. Multi-document summarizers should produce a summary that covers the main topics of multiple related input texts to diminish the extent of redundant information. In this paper, we propose a novel summarization method named Clustering and Itemset mining based Biomedical Summarizer (CIBS). The summarizer extracts biomedical concepts from the input documents and employs an itemset mining algorithm to discover main topics. Then, it applies a clustering algorithm to put the sentences into clusters such that those in the same cluster share similar topics. Selecting sentences from all the clusters, the summarizer can produce a summary that covers a wide range of topics of the input text. Using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) toolkit, we evaluate the performance of the CIBS method against four summarizers including a state-of-the-art method. The results show that the CIBS method can improve the performance of single- and multi-document biomedical text summarization. It is shown that the topic-based sentence clustering approach can be effectively used to increase the informative content of summaries, as well as to decrease the redundant information.

Extractive single document summarization using multi-objective optimization: Exploring self-organized differential evolution, grey wolf optimizer and water cycle algorithm

Text summarization techniques become paramount in extracting relevant information from large databa-ses. Current paper attempts to build some extractive single document text summarization (ESDS) systems using multi-objective optimization (MOO) frameworks. Three techniques are proposed: (1) first is an integration of self-organizing map (SOM) and multi-objective differential evolution (MODE) (named as ESDS_SMODE) (2) second is based on multi-objective grey wolf optimizer (ESDS_MGWO) and (3) third is based on multi-objective water cycle algorithm (ESDS_MWCA). The sentences present in the document are first clustered utilizing the concept of multi-objective clustering. Two objective functions measuring compactness and separation of the sentence clusters in two different ways are optimized simultaneously using MOO framework. The proposed approach is able to automatically detect the number of sentence clusters present in a document and then representative sentences are selected from different clusters using some sentence scoring features to generate the summary. The experiments were conducted on two benchmark datasets, DUC2001, and DUC2002, and the obtained results are compared with various state-of-the-art techniques using ROUGE measures. Results illustrate the superiority of our approach in comparison to state-of-the-art techniques in terms of ROUGE−2 score for both datasets. Code of the developed approach ESDS_SMODE is available online at https://drive.google.com/open?id=1WagTeIDLgphttPrKHpnF_eO7QHWJxXxK.

Graph-based biomedical text summarization: An itemset mining and sentence clustering approach

ObjectiveAutomatic text summarization offers an efficient solution to access the ever-growing amounts of both scientific and clinical literature in the biomedical domain by summarizing the source documents while maintaining their most informative contents. In this paper, we propose a novel graph-based summarization method that takes advantage of the domain-specific knowledge and a well-established data mining technique called frequent itemset mining. MethodsOur summarizer exploits the Unified Medical Language System (UMLS) to construct a concept-based model of the source document and mapping the document to the concepts. Then, it discovers frequent itemsets to take the correlations among multiple concepts into account. The method uses these correlations to propose a similarity function based on which a represented graph is constructed. The summarizer then employs a minimum spanning tree based clustering algorithm to discover various subthemes of the document. Eventually, it generates the final summary by selecting the most informative and relative sentences from all subthemes within the text. ResultsWe perform an automatic evaluation over a large number of summaries using the Recall-Oriented Understudy for Gisting Evaluation (ROUGE) metrics. The results demonstrate that the proposed summarization system outperforms various baselines and benchmark approaches. ConclusionThe carried out research suggests that the incorporation of domain-specific knowledge and frequent itemset mining equips the summarization system in a better way to address the informativeness measurement of the sentences. Moreover, clustering the graph nodes (sentences) can enable the summarizer to target different main subthemes of a source document efficiently. The evaluation results show that the proposed approach can significantly improve the performance of the summarization systems in the biomedical domain.

My Life, by Louis Kenoyer: Reminiscences of a Grand Ronde Reservation Childhood by Louis Kenoyer, Henry Zenk, and Jedd Schrock Stephen Dow Beckham

125 Reviews REVIEWS MY LIFE, BY LOUIS KENOYER: REMINISCENCES OF A GRAND RONDE RESERVATION CHILDHOOD by Louis Kenoyer, Henry Zenk, and Jedd Schrock foreword by Stephen Dow Beckham Oregon State University Press, Covallis, 2017. Photographs, maps. 320 pages. $35.00, paper. My Life, by Louis Kenoyer is a rare and beautifully contextualized told-to narrative that presents the life and times of Louis Kenoyer and, in doing so, provides invaluable insight into Native-newcomer relations in nineteenth century Oregon. Kenoyer was a member of the first Northwest Oregon tribal group born at Grand Ronde Reservation, of which the vast majority of surviving population was removed in 1856. It is “an extended autobiographical narrative,” originally dictated in the Tualatin dialect of Northern Kalapuya to three linguistic transcribers and as a result is a complete bilingual-Tualatin text (p. 1). This work presents numerous evocative vignettes of daily life told by Kenoyer in his own words and language. There are stories of his experiences in on-reservation schooling, particularly the boarding school known as “the Sisters’ school,” his agricultural work, interactions with newcomers, church and religious teachings, hunting stories, and tales of recreational activities of the era, including horse races. Kenoyer presents his life experiences in a storytelling style inclusive of a number of unique features that the authors astutely contextualize as common among other examples of lower Columbia narrative art. Such unique features of Kenoyer’s narrative style include a focus “on overt action, details of external set and setting being acknowledged only as they help move the action along” (p. 3). My Life is a remarkable work of scholarship for its presentation and analysis of both the content of Kenoyer’s oral history as well as its form. The authors paid great mindfulness to structure the work to best reflect the cultural and personal nuances and subtleties with which Kenoyer spoke. As the authors state: “Our approach to translation is relatively simple. Our goal is to make the English reader’s experience of reading this narrative similar to the Tualatin listener’s experience of hearing it in Tualatin” (p. 54). One way in which the authors set out to accomplish this, and succeed at doing so, is the presentation of the text on the page. The narrative itself is presented in a series of “clusters” that “attempt to present his narrative in a form more reflective of his oral style, as opposed to the artificial confines of English-style paragraphs .” For, “Louis Kenoyer did not speak in paragraphs, so why display his narrative in paragraphs ?” (p. 53). The result is a presentation of the oral history using Kenoyer’s “most common narrative device,” which is “to make a statement and then clarify the idea further in supporting sentences; hence a cluster of sentences takes shape” (p. 53). Of great value is the structural analysis of Kenoyer’s narrative as a work of oral literature and the historical context provided by the authors. In terms of audience, this book will be of keen interest to oral historians, ethnohistorians , anthropologists, linguists, and historians. It will also be of great interest to tribal knowledge holders and Indigenous scholars. This work extends its reach and impact to include the general public interested in Western history , particularly Oregon history and Nativenewcomer histories. Meagan Evelyn Gough Ontario, Canada ...

Optimal sentence clustering for web database using hierarchical fuzzy relational clustering integrated with artificial bee colony algorithm

Optimal sentence clustering for web database using hierarchical fuzzy relational clustering integrated with artificial bee colony algorithm