Important Keyphrases Research Articles

KEST: A graph-based keyphrase extraction technique for tweets summarization using Markov Decision Process

Multi-document summarization finds its application in many downstream information retrieval and natural language processing tasks. In the light of recent developments in social media data mining, Tweet summarization has emerged as a fundamental task of automatically detecting important keyphrases from a set of Tweets about current happenings. In the existing literature, the graph-based keyphrase extraction techniques are well-established unsupervised algorithms to capture summaries from dynamically evolving data. We argue that the traditional multi-tweet summarization technique may or may not capture user’s interest-specific keyphrases during tweet summarization. The nature of user-generated factual short-text is different from well-formed descriptive and perceptual long-text due to their repetitive nature. In this context, we introduce a simple yet effective interest-specific keyphrase extraction technique for tweet summarization as KEST: Key Extraction for Summarization of Tweets using Markov Decision Process (MDP). In this research work, we generate a path as evolving chain of highly interconnected words from sub-components in graph of words. We evaluate the effectiveness of our computationally, inexpensive, graph-based, abstractive keyphrase extraction approach over two datasets which we make publicly available.

THE CONCEPT MODERN LIFE IN MODERN UKRAINIAN LINGUACULTURE

In this article, consideration is given to the investigation of the meaning and peculiarities of the semantic structure of the linguacultural concept MODERN LIFE functioning in modern Ukrainian worldview. Linguacultural concept is treated as a multi-layered mental formation in culture that organizes the knowledge of a certain fragment of reality in the consciousness of a certain language and cultural community. Linguacultural concept accumulates knowledge about a certain fragment of reality in the collective consciousness of a certain national language and cultural community, it is objectified by its linguistic form and marked by language and cultural specifics. The concept MODERN LIFE plays an important role in the life of every civilized man. Its significance for Ukrainian culture is grounded because it serves as one of the most important key phrases with high emotional intensity and broad associative field. Aiming to determine the main lexical means that stand for the investigated concept this research demonstrates the strong connection between language and culture and theirinfluence on each other.The article focuses on the peculiarities of the free association experiment and the receptive experiment. Associative experiment allows to reconstruct the relations of language units in the language consciousness of native speakers and to specify the peculiarities of the occurrence of these units in language consciousness. The advantage of this method is also reflected in the fact that it can reveal more distinctive features of the concept, and through the frequency of reactions to define the relevance of these features in language consciousness. The receptive experiment aims at discovering the specifics of understanding and perception of a concept, its subjective definition. It allows obtaining more information about the understanding of specific units in the process of concept verbalization. Moreover, by application of receptive and associative experiments the article aims at specifying the thematic fields in the semantic representation of the concept. The interpretation of experimental data, allowing to specify the meanings associated with the concept in the minds of Ukrainian native speakers provides the analysis of semantic modifications caused by social and political events in Ukrainian realis, history and society. Receptive and associative experiments were held with 87 Ukrainian speaking students, graduate students (81 females and 6 males) at Foreign Languages Department of Ternopil Volodymyr Hnatiuk National Pedagogical University, Ukraine. The respondents’ age was from 18 to 22.With the help of the free word association test the connections of the concept MODERN LIFE in the Ukrainian language consciousness and the semantic zones of this stimulus phrase were determined. Psycholinguistic ideas about modern life in Ukraine are manifested in the ambivalence of the components, the semantic clues of which are “technology/gadgets”, “internet/online” and “communication”. Qualitative analysis of the results of the free word association test helped to build the respondents’ images of modern Ukrainian hallmarks (borshch, EuroMaydan / Maidan and war). The linguacultural concept MODERN LIFE functioning in modern Ukrainian worldview bears negative connotation. Next, we subtracted the highest and lowest values displayed above the group of bars andmade comparison between the with the reference to results, the tallest vertical bar for the value The essential components of this concept are “self-confidence” and very close to it is “strong family”. Thus, the benefits of the methods of the experimental study of the concepts in the study of the features of the national worldview are stated in the research.

KeyVector: Unsupervised Keyphrase Extraction Using Weighted Topic via Semantic Related

Keyphrase extraction is a task of automatically selecting topical phrases from a document. We present KeyVector, an unsupervised approach with weighted topics via semantic relatedness for keyphrase extraction. Our method relies on various measures of semantic relatedness of documents, topics and keyphrases in the same vector space, which allow us to compute three keyphrase ranking scores: global semantic score, find more important keyphrases for a given document by measuring the semantic relation between documents and keyphrase embeddings; topic weight, pruning/selecting the candidate keyphrases on the topic level; topic inner score, ranking the keyphrases inside each topic. Keyphrases are then generated by ranking the values of combined three scores for each candidate. We conducted experiments on three evaluation data sets of different length documents and domains. Results show that KeyVector out performs state of the art methods on short, medium and long documents.

Efficient sequential pattern mining with wildcards for keyphrase extraction

A keyphrase (a multi-word unit) in a document denotes one or multiple keywords capturing a main topic of the underlying document. Finding good keyphrases of a document can quickly summarize knowledge for efficient decision making and benefit domains involving intensive text information. To date, existing keyphrase extraction methods cannot be customized to each specific document, mainly because their patterns used to form paraphrases are too restrictive and may not capture flexible keyword relationships inside the text. In this paper, we propose a sequential pattern mining based document-specific keyphrase extraction method. Our key innovation is to use wildcards (or gap constraints) to help extract sequential patterns, so the flexible wildcard constraints within a pattern can capture semantic relationships between words, and the system will have full flexibility to discover different types of sequential patterns as candidates for keyphrase extraction. To achieve the goal, we regard each single document as a sequential dataset, and propose an efficient algorithm to mine sequential patterns with wildcard and one-off conditions that allows important keyphrases to be captured during the mining process. For each extracted keyphrase candidate, we use some statistical pattern features to characterize it, and further collect all keyphrases from the document to form a training set. A supervised learning classifier is trained to identify keyphrases from a test document. Because our pattern mining and pattern characterization processes are customized to each single document, keyphases extracted from our method are highly specific for each document. Experimental results demonstrate that the proposed sequential pattern mining method outperforms existing pattern mining methods in both runtime performance and completeness. Comparisons on keyphrase benchmark datasets also confirm that the proposed document-specific keyphrase extraction method is effective in improving the quality of extracted keyphrases.

An Enhanced Automated Test Item Creation Based on Learners Preferred Concept Space

Recently, research has become increasingly inter-ested in developing tools that are able to automatically create test items out of text-based learning contents. Such tools might not only support instructors in creating tests or exams but also learners in self-assessing their learning progress. This paper presents an enhanced automatic question-creation tool (EAQC) that has been recently developed. EAQC extracts the most important key phrases (concepts) out of a textual learning content and automatically creates test items based on these concepts. Moreover, this paper discusses two studies for the evaluation of EAQC application in real learning settings. The first study showed that concepts extracted by the EAQC often but not always reflect the concepts extracted by learners. Learners typically extracted fewer concepts than the EAQC and there was a great inter-individual variation between learners with regard to which concepts they experienced as relevant. Accordingly, the second study investigated whether the functionality of the EAQC can be improved in a way that valid test items are created if the tool was fed with concepts provided by learners. The results showed that the quality of semi-automated creation of test items were satisfactory. Moreover, this depicts the EAQC flexibility in adapting its workflow to the individual needs of the learners.