List Of Keyphrases Research Articles

Applying Transformer-Based Text Summarization for Keyphrase Generation

Keyphrases are crucial for searching and systematizing scholarly documents. Most current methods for keyphrase extraction are aimed at the extraction of the most significant words in the text. But in practice, the list of keyphrases often includes words that do not appear in the text explicitly. In this case, the list of keyphrases represents an abstractive summary of the source text. In this paper, we experiment with popular transformer-based models for abstractive text summarization using four benchmark datasets for keyphrase extraction. We compare the results obtained with the results of common unsupervised and supervised methods for keyphrase extraction. Our evaluation shows that summarization models are quite effective in generating keyphrases in the terms of the full-match F1-score and BERTScore. However, they produce a lot of words that are absent in the author’s list of keyphrases, which makes summarization models ineffective in terms of ROUGE-1. We also investigate several ordering strategies to concatenate target keyphrases. The results showed that the choice of strategy affects the performance of keyphrase generation.

Categorization of Unorganized Text Corpora for better Domain-Specific Language Modeling

This paper describes the process of categorization of unorganized text data gathered from the Internet to the in-domain and out-of-domain data for better domain-specific language modeling and speech recognition. An algorithm for text categorization and topic detection based on the most frequent key phrases is presented. In this scheme, each document entered into the process of text categorization is represented by a vector space model with term weighting based on computing the term frequency and inverse document frequency. Text documents are then classified to the in-domain and out-of-domain data automatically with predefined threshold using one of the selected distance/similarity measures comparing to the list of key phrases. The experimental results of the language modeling and adaptation to the judicial domain show significant improvement in the model perplexity about 19 % and decreasing of the word error rate of the Slovak transcription and dictation system about 5,54 %, relatively.

Hierarchical Clustering for Keyphrase Extraction from Arabic Documents Based on Word Context

Keyphrase extraction is a process by which the set of words or phrases that best describe a document is specified. The phrases could be extracted from the document words itself, or they could be external and specified from an ontology for a given domain. Extracting keyphrases from documents is critical for many applications such as information retrieval, document summarization or clustering. Many keyphrase extractors view the problem as a classification problem and therefore they need training documents (i.e. documents which their keyphrases are known in advance). Other systems view keyphrase extraction as a ranking problem. In the latter approach, the words or phrases of a document are ranked based on their importance and phrases with high importance (usually located at the beginning of the list) are recommended as possible keyphrases for a document. This abstract explains Shihab; a system for extracting keyphrases from Arabic documents. Shihab views keyphrase extraction as a ranking problem. The list of keyphrases is generated by clustering the phrases of a document. Phrases are built from words which appear in the document. These phrases consist of 1-, 2- or 3-words. The idea is to group phrases which are similar into one cluster. The similarity between phrases is determined by calculating the Dice value of their corresponding contexts. A phrase context is the sentence in which that phrase appears. Agglomerative hierarchical clustering is used in the clustering phase. Once the clusters are ready, then each cluster will nominate a phrase to the set of candidate keyphrases. This phrase is called cluster representative and is determined according to a set of heuristics. Shihab results were compared with other existing keyphrase extractors such as KP-Miner and Arabic-KEA and the results were encouraging.

Testing a Cancer Meta Spider

As in many other applications, the rapid proliferation and unrestricted Web-based publishing of health-related content have made finding pertinent and useful healthcare information increasingly difficult. Although the development of healthcare information retrieval systems such as medical search engines and peer-reviewed medical Web directories has helped alleviate this information and cognitive overload problem, the effectiveness of these systems has been limited by low search precision, poor presentation of search results, and the required user search effort. To address these challenges, we have developed a domain-specific meta-search tool called Cancer Spider. By leveraging post-retrieval document clustering techniques, this system aids users in querying multiple medical data sources to gain an overview of the retrieved documents and locating answers of high quality to a wide spectrum of health questions. The system presents the retrieved documents to users in two different views: (1) Web pages organized by a list of key phrases, and (2) Web pages clustered into regions discussing different topics on a two-dimensional map (self-organizing map). In this paper, we present the major components of the Cancer Spider system and a user evaluation study designed to evaluate the effectiveness and efficiency of our approach. Initial results comparing Cancer Spider with NLM Gateway, a premium medical search site, have shown that they achieved comparable performances measured by precision, recall, and F-measure. Cancer Spider required less user searching time, fewer documents that need to be browsed, and less user effort.