Search (123 results, page 2 of 7)

0.0026473717 = product of:
  0.0052947435 = sum of:
    0.0052947435 = product of:
      0.010589487 = sum of:
        0.010589487 = weight(_text_:a in 1150) [ClassicSimilarity], result of:
          0.010589487 = score(doc=1150,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19940455 = fieldWeight in 1150, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1150)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Voice search is becoming a popular mode for interacting with search engines. As a result, research has gone into building better voice transcription engines, interfaces, and search engines that better handle inherent verbosity of queries. However, when one considers its use by non- native speakers of English, another aspect that becomes important is the formulation of the query by users. In this paper, we present the results of a preliminary study that we conducted with non-native English speakers who formulate queries for given retrieval tasks. Our results show that the current search engines are sensitive in their rankings to the query formulation, and thus highlights the need for developing more robust ranking methods.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 1338) [ClassicSimilarity], result of:
          0.010148063 = score(doc=1338,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 1338, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1338)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

A user's query is considered to be an imprecise description of their information need. Automatic query expansion is the process of reformulating the original query with the goal of improving retrieval effectiveness. Many successful query expansion techniques model syntagmatic associations that infer two terms co-occur more often than by chance in natural language. However, structural linguistics relies on both syntagmatic and paradigmatic associations to deduce the meaning of a word. Given the success of dependency-based approaches to query expansion and the reliance on word meanings in the query formulation process, we argue that modeling both syntagmatic and paradigmatic information in the query expansion process improves retrieval effectiveness. This article develops and evaluates a new query expansion technique that is based on a formal, corpus-based model of word meaning that models syntagmatic and paradigmatic associations. We demonstrate that when sufficient statistical information exists, as in the case of longer queries, including paradigmatic information alone provides significant improvements in retrieval effectiveness across a wide variety of data sets. More generally, when our new query expansion approach is applied to large-scale web retrieval it demonstrates significant improvements in retrieval effectiveness over a strong baseline system, based on a commercial search engine.

Type

a

0.0025370158 = product of:
  0.0050740317 = sum of:
    0.0050740317 = product of:
      0.010148063 = sum of:
        0.010148063 = weight(_text_:a in 3488) [ClassicSimilarity], result of:
          0.010148063 = score(doc=3488,freq=18.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.19109234 = fieldWeight in 3488, product of:
              4.2426405 = tf(freq=18.0), with freq of:
                18.0 = termFreq=18.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3488)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

There are many endeavors aiming to offer users more effective ways of getting relevant information from web. One of them is represented by a concept of Linked Data, which provides interconnected data sources. But querying these types of data is difficult not only for the conventional web users but also for ex-perts in this field. Therefore, a more comfortable way of user query would be of great value. One direction could be to allow the user to use a natural language. To make this task easier we have proposed a method for translating natural language query to SPARQL query. It is based on a sentence structure - utilizing dependen-cies between the words in user queries. Dependencies are used to map the query to the semantic web structure, which is in the next step translated to SPARQL query. According to our first experiments we are able to answer a significant group of user queries.

Source

Semantic keyword-based search on structured data sources: COST Action IC1302. Second International KEYSTONE Conference, IKC 2016, Cluj-Napoca, Romania, September 8-9, 2016, Revised Selected Papers. Eds.: A. Calì, A. et al

Type

a

0.0024857575 = product of:
  0.004971515 = sum of:
    0.004971515 = product of:
      0.00994303 = sum of:
        0.00994303 = weight(_text_:a in 2096) [ClassicSimilarity], result of:
          0.00994303 = score(doc=2096,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18723148 = fieldWeight in 2096, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=2096)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

We describe the use of a domain-independent method to extend a natural language processing (NLP) application, SemRep (Rindflesch, Fiszman, & Libbus, 2005), based on the knowledge sources afforded by the Unified Medical Language System (UMLS®; Humphreys, Lindberg, Schoolman, & Barnett, 1998) to support the area of health promotion within the public health domain. Public health professionals require good information about successful health promotion policies and programs that might be considered for application within their own communities. Our effort seeks to improve access to relevant information for the public health profession, to help those in the field remain an information-savvy workforce. Natural language processing and semantic techniques hold promise to help public health professionals navigate the growing ocean of information by organizing and structuring this knowledge into a focused public health framework paired with a user-friendly visualization application as a way to summarize results of PubMed® searches in this field of knowledge.

Type

a

0.0024857575 = product of:
  0.004971515 = sum of:
    0.004971515 = product of:
      0.00994303 = sum of:
        0.00994303 = weight(_text_:a in 2339) [ClassicSimilarity], result of:
          0.00994303 = score(doc=2339,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18723148 = fieldWeight in 2339, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=2339)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Text classification (TC) is a core technique for text mining and information retrieval. It has been applied to many applications in many different research and industrial areas. Term-weighting schemes assign an appropriate weight to each term to obtain a high TC performance. Although term weighting is one of the important modules for TC and TC has different peculiarities from those in information retrieval, many term-weighting schemes used in information retrieval, such as term frequency-inverse document frequency (tf-idf), have been used in TC in the same manner. The peculiarity of TC that differs most from information retrieval is the existence of class information. This article proposes a new term-weighting scheme that uses class information using positive and negative class distributions. As a result, the proposed scheme, log tf-TRR, consistently performs better than do other schemes using class information as well as traditional schemes such as tf-idf.

Type

a

0.0024857575 = product of:
  0.004971515 = sum of:
    0.004971515 = product of:
      0.00994303 = sum of:
        0.00994303 = weight(_text_:a in 2697) [ClassicSimilarity], result of:
          0.00994303 = score(doc=2697,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18723148 = fieldWeight in 2697, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=2697)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Text mining and natural language processing are fast growing areas of research, with numerous applications in business, science and creative industries. This paper presents TextFlows, a web-based text mining and natural language processing platform supporting workflow construction, sharing and execution. The platform enables visual construction of text mining workflows through a web browser, and the execution of the constructed workflows on a processing cloud. This makes TextFlows an adaptable infrastructure for the construction and sharing of text processing workflows, which can be reused in various applications. The paper presents the implemented text mining and language processing modules, and describes some precomposed workflows. Their features are demonstrated on three use cases: comparison of document classifiers and of different part-of-speech taggers on a text categorization problem, and outlier detection in document corpora.

Type

a

0.0024857575 = product of:
  0.004971515 = sum of:
    0.004971515 = product of:
      0.00994303 = sum of:
        0.00994303 = weight(_text_:a in 4094) [ClassicSimilarity], result of:
          0.00994303 = score(doc=4094,freq=12.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18723148 = fieldWeight in 4094, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=4094)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This paper presents a methodology for the automatic extraction of specialized Arabic, English and French verbs of the field of computing. Since nominal terms are predominant in terminology, our interest is to explore to what extent verbs can also be part of a terminological analysis. Hence, our objective is to verify how an existing extraction tool will perform when it comes to specialized verbs in a given specialized domain. Furthermore, we want to investigate any particularities that a language can represent regarding verbal terms from the automatic extraction perspective. Our choice to operate on three different languages reflects our desire to see whether the chosen tool can perform better on one language compared to the others. Moreover, given that Arabic is a morphologically rich and complex language, we consider investigating the results yielded by the extraction tool. The extractor used for our experiment is TermoStat (Drouin 2003). So far, our results show that the extraction of verbs of computing represents certain differences in terms of quality and particularities of these units in this specialized domain between the languages under question.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 246) [ClassicSimilarity], result of:
          0.009567685 = score(doc=246,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 246, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=246)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

We present a new, two-stage, self-supervised algorithm for author disambiguation in large bibliographic databases. In the first "bootstrap" stage, a collection of high-precision features is used to bootstrap a training set with positive and negative examples of coreferring authors. A supervised feature-based classifier is then trained on the bootstrap clusters and used to cluster the authors in a larger unlabeled dataset. Our self-supervised approach shares the advantages of unsupervised approaches (no need for expensive hand labels) as well as supervised approaches (a rich set of features that can be discriminatively trained). The algorithm disambiguates 54,000,000 author instances in Thomson Reuters' Web of Knowledge with B3 F1 of.807. We analyze parameters and features, particularly those from citation networks, which have not been deeply investigated in author disambiguation. The most important citation feature is self-citation, which can be approximated without expensive extraction of the full network. For the supervised stage, the minor improvement due to other citation features (increasing F1 from.748 to.767) suggests they may not be worth the trouble of extracting from databases that don't already have them. A lean feature set without expensive abstract and title features performs 130 times faster with about equal F1.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 283) [ClassicSimilarity], result of:
          0.009567685 = score(doc=283,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 283, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=283)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Detecting negative and speculative information is essential in most biomedical text-mining tasks where these language forms are used to express impressions, hypotheses, or explanations of experimental results. Our research is focused on developing a system based on machine-learning techniques that identifies negation and speculation signals and their scope in clinical texts. The proposed system works in two consecutive phases: first, a classifier decides whether each token in a sentence is a negation/speculation signal or not. Then another classifier determines, at sentence level, the tokens which are affected by the signals previously identified. The system was trained and evaluated on the clinical texts of the BioScope corpus, a freely available resource consisting of medical and biological texts: full-length articles, scientific abstracts, and clinical reports. The results obtained by our system were compared with those of two different systems, one based on regular expressions and the other based on machine learning. Our system's results outperformed the results obtained by these two systems. In the signal detection task, the F-score value was 97.3% in negation and 94.9% in speculation. In the scope-finding task, a token was correctly classified if it had been properly identified as being inside or outside the scope of all the negation signals present in the sentence. Our proposal showed an F score of 93.2% in negation and 80.9% in speculation. Additionally, the percentage of correct scopes (those with all their tokens correctly classified) was evaluated obtaining F scores of 90.9% in negation and 71.9% in speculation.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 1226) [ClassicSimilarity], result of:
          0.009567685 = score(doc=1226,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 1226, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1226)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The use of robo-readers to analyze news texts is an emerging technology trend in computational finance. Recent research has developed sophisticated financial polarity lexicons for investigating how financial sentiments relate to future company performance. However, based on experience from fields that commonly analyze sentiment, it is well known that the overall semantic orientation of a sentence may differ from that of individual words. This article investigates how semantic orientations can be better detected in financial and economic news by accommodating the overall phrase-structure information and domain-specific use of language. Our three main contributions are the following: (a) a human-annotated finance phrase bank that can be used for training and evaluating alternative models; (b) a technique to enhance financial lexicons with attributes that help to identify expected direction of events that affect sentiment; and (c) a linearized phrase-structure model for detecting contextual semantic orientations in economic texts. The relevance of the newly added lexicon features and the benefit of using the proposed learning algorithm are demonstrated in a comparative study against general sentiment models as well as the popular word frequency models used in recent financial studies. The proposed framework is parsimonious and avoids the explosion in feature space caused by the use of conventional n-gram features.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 3223) [ClassicSimilarity], result of:
          0.009567685 = score(doc=3223,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 3223, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3223)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The aim of the study was to test whether query expansion by approximate string matching methods is beneficial in retrieval from historical newspaper collections in a language rich with compounds and inflectional forms (Finnish). First, approximate string matching methods were used to generate lists of index words most similar to contemporary query terms in a digitized newspaper collection from the 1800s. Top index word variants were categorized to estimate the appropriate query expansion ranges in the retrieval test. Second, the effectiveness of approximate string matching methods, automatically generated inflectional forms, and their combinations were measured in a Cranfield-style test. Finally, a detailed topic-level analysis of test results was conducted. In the index of historical newspaper collection the occurrences of a word typically spread to many linguistic and historical variants along with optical character recognition (OCR) errors. All query expansion methods improved the baseline results. Extensive expansion of around 30 variants for each query word was required to achieve the highest performance improvement. Query expansion based on approximate string matching was superior to using the inflectional forms of the query words, showing that coverage of the different types of variation is more important than precision in handling one type of variation.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 3786) [ClassicSimilarity], result of:
          0.009567685 = score(doc=3786,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 3786, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3786)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Text simplification often relies on dated, unproven readability formulas. As an alternative and motivated by the success of term familiarity, we test a complementary measure: grammar familiarity. Grammar familiarity is measured as the frequency of the 3rd level sentence parse tree and is useful for evaluating individual sentences. We created a database of 140K unique 3rd level parse structures by parsing and binning all 5.4M sentences in English Wikipedia. We then calculated the grammar frequencies across the corpus and created 11 frequency bins. We evaluate the measure with a user study and corpus analysis. For the user study, we selected 20 sentences randomly from each bin, controlling for sentence length and term frequency, and recruited 30 readers per sentence (N = 6,600) on Amazon Mechanical Turk. We measured actual difficulty (comprehension) using a Cloze test, perceived difficulty using a 5-point Likert scale, and time taken. Sentences with more frequent grammatical structures, even with very different surface presentations, were easier to understand, perceived as easier, and took less time to read. Outcomes from readability formulas correlated with perceived but not with actual difficulty. Our corpus analysis shows how the metric can be used to understand grammar regularity in a broad range of corpora.

Type

a

0.0023919214 = product of:
  0.0047838427 = sum of:
    0.0047838427 = product of:
      0.009567685 = sum of:
        0.009567685 = weight(_text_:a in 5043) [ClassicSimilarity], result of:
          0.009567685 = score(doc=5043,freq=16.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.18016359 = fieldWeight in 5043, product of:
              4.0 = tf(freq=16.0), with freq of:
                16.0 = termFreq=16.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=5043)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This paper is concerned with paraphrase detection, i.e., identifying sentences that are semantically identical. The ability to detect similar sentences written in natural language is crucial for several applications, such as text mining, text summarization, plagiarism detection, authorship authentication and question answering. Recognizing this importance, we study in particular how to address the challenges with detecting paraphrases in user generated short texts, such as Twitter, which often contain language irregularity and noise, and do not necessarily contain as much semantic information as longer clean texts. We propose a novel deep neural network-based approach that relies on coarse-grained sentence modelling using a convolutional neural network (CNN) and a recurrent neural network (RNN) model, combined with a specific fine-grained word-level similarity matching model. More specifically, we develop a new architecture, called DeepParaphrase, which enables to create an informative semantic representation of each sentence by (1) using CNN to extract the local region information in form of important n-grams from the sentence, and (2) applying RNN to capture the long-term dependency information. In addition, we perform a comparative study on state-of-the-art approaches within paraphrase detection. An important insight from this study is that existing paraphrase approaches perform well when applied on clean texts, but they do not necessarily deliver good performance against noisy texts, and vice versa. In contrast, our evaluation has shown that the proposed DeepParaphrase-based approach achieves good results in both types of texts, thus making it more robust and generic than the existing approaches.

Type

a

0.0023678814 = product of:
  0.0047357627 = sum of:
    0.0047357627 = product of:
      0.009471525 = sum of:
        0.009471525 = weight(_text_:a in 120) [ClassicSimilarity], result of:
          0.009471525 = score(doc=120,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.17835285 = fieldWeight in 120, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=120)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The noun compound - a sequence of nouns which functions as a single noun - is very common in English texts. No language processing system should ignore expressions like steel soup pot cover if it wants to be serious about such high-end applications of computational linguistics as question answering, information extraction, text summarization, machine translation - the list goes on. Processing noun compounds, however, is far from trouble-free. For one thing, they can be bracketed in various ways: is it steel soup, steel pot, or steel cover? Then there are relations inside a compound, annoyingly not signalled by any words: does pot contain soup or is it for cooking soup? These and many other research challenges are the subject of this special issue.

Type

a

0.0023678814 = product of:
  0.0047357627 = sum of:
    0.0047357627 = product of:
      0.009471525 = sum of:
        0.009471525 = weight(_text_:a in 2764) [ClassicSimilarity], result of:
          0.009471525 = score(doc=2764,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.17835285 = fieldWeight in 2764, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=2764)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The ACL Anthology is a large collection of research papers in computational linguistics. Citation data were obtained using text extraction from a collection of PDF files with significant manual postprocessing performed to clean up the results. Manual annotation of the references was then performed to complete the citation network. We analyzed the networks of paper citations, author citations, and author collaborations in an attempt to identify the most central papers and authors. The analysis includes general network statistics, PageRank, metrics across publication years and venues, the impact factor and h-index, as well as other measures.

Type

a

0.0023678814 = product of:
  0.0047357627 = sum of:
    0.0047357627 = product of:
      0.009471525 = sum of:
        0.009471525 = weight(_text_:a in 773) [ClassicSimilarity], result of:
          0.009471525 = score(doc=773,freq=8.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.17835285 = fieldWeight in 773, product of:
              2.828427 = tf(freq=8.0), with freq of:
                8.0 = termFreq=8.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0546875 = fieldNorm(doc=773)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

We show that generating English Wikipedia articles can be approached as a multi-document summarization of source documents. We use extractive summarization to coarsely identify salient information and a neural abstractive model to generate the article. For the abstractive model, we introduce a decoder-only architecture that can scalably attend to very long sequences, much longer than typical encoder- decoder architectures used in sequence transduction. We show that this model can generate fluent, coherent multi-sentence paragraphs and even whole Wikipedia articles. When given reference documents, we show it can extract relevant factual information as reflected in perplexity, ROUGE scores and human evaluations.

Type

a

0.002269176 = product of:
  0.004538352 = sum of:
    0.004538352 = product of:
      0.009076704 = sum of:
        0.009076704 = weight(_text_:a in 3457) [ClassicSimilarity], result of:
          0.009076704 = score(doc=3457,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1709182 = fieldWeight in 3457, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=3457)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Arabic has a complex structure, which makes it difficult to apply natural language processing (NLP). Much research on Arabic NLP (ANLP) does exist; however, it is not as mature as that of other languages. Finding Arabic roots is an important step toward conducting effective research on most of ANLP applications. The authors have studied and compared six root-finding algorithms with success rates of over 90%. All algorithms of this study did not use the same testing corpus and/or benchmarking measures. They unified the testing process by implementing their own algorithm descriptions and building a corpus out of 3823 triliteral roots, applying 73 triliteral patterns, and with 18 affixes, producing around 27.6 million words. They tested the algorithms with the generated corpus and have obtained interesting results; they offer to share the corpus freely for benchmarking and ANLP research.

Type

a

0.002269176 = product of:
  0.004538352 = sum of:
    0.004538352 = product of:
      0.009076704 = sum of:
        0.009076704 = weight(_text_:a in 4967) [ClassicSimilarity], result of:
          0.009076704 = score(doc=4967,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1709182 = fieldWeight in 4967, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=4967)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Literature-based discovery (LBD) refers to a particular type of text mining that seeks to identify nontrivial assertions that are implicit, and not explicitly stated, and that are detected by juxtaposing (generally a large body of) documents. In this review, I will provide a brief overview of LBD, both past and present, and will propose some new directions for the next decade. The prevalent ABC model is not "wrong"; however, it is only one of several different types of models that can contribute to the development of the next generation of LBD tools. Perhaps the most urgent need is to develop a series of objective literature-based interestingness measures, which can customize the output of LBD systems for different types of scientific investigations.

Type

a

0.002269176 = product of:
  0.004538352 = sum of:
    0.004538352 = product of:
      0.009076704 = sum of:
        0.009076704 = weight(_text_:a in 682) [ClassicSimilarity], result of:
          0.009076704 = score(doc=682,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1709182 = fieldWeight in 682, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=682)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Specialized medical ontologies and terminologies, such as SNOMED CT and the Unified Medical Language System (UMLS), have been successfully leveraged in medical information systems to provide a standard web-accessible medium for interoperability, access, and reuse. However, these clinically oriented terminologies and ontologies cannot provide sufficient support when integrated into consumer-oriented applications, because these applications must "understand" both technical and lay vocabulary. The latter is not part of these specialized terminologies and ontologies. In this article, we propose a two-step approach for building consumer health terminologies from text: 1) automatic extraction of definitions from consumer-oriented articles and web documents, which reflects language in use, rather than relying solely on dictionaries, and 2) learning to map definitions expressed in natural language to terminological knowledge by inducing a syntactic-semantic grammar rather than using hand-written patterns or grammars. We present quantitative and qualitative evaluations of our two-step approach, which show that our framework could be used to induce consumer health terminologies from text.

Type

a

0.002269176 = product of:
  0.004538352 = sum of:
    0.004538352 = product of:
      0.009076704 = sum of:
        0.009076704 = weight(_text_:a in 1664) [ClassicSimilarity], result of:
          0.009076704 = score(doc=1664,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1709182 = fieldWeight in 1664, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=1664)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

This research creates an architecture for investigating the existence of probable lexical divergences between articles, categorized as Institute for Scientific Information (ISI) and non-ISI, and consequently, if such a difference is discovered, to propose the best available classification method. Based on a collection of ISI- and non-ISI-indexed articles in the areas of business and computer science, three classification models are trained. A sensitivity analysis is applied to demonstrate the impact of words in different syntactical forms on the classification decision. The results demonstrate that the lexical domains of ISI and non-ISI articles are distinguishable by machine learning techniques. Our findings indicate that the support vector machine identifies ISI-indexed articles in both disciplines with higher precision than do the Naïve Bayesian and K-Nearest Neighbors techniques.

Type

a