scholarly journals Efficient Word Retrieval by Means of SOM Clustering and PCA

Author(s):  
Simone Marinai ◽  
Stefano Faini ◽  
Emanuele Marino ◽  
Giovanni Soda
2020 ◽  
Vol 29 (3) ◽  
pp. 1574-1595
Author(s):  
Chaleece W. Sandberg ◽  
Teresa Gray

Purpose We report on a study that replicates previous treatment studies using Abstract Semantic Associative Network Training (AbSANT), which was developed to help persons with aphasia improve their ability to retrieve abstract words, as well as thematically related concrete words. We hypothesized that previous results would be replicated; that is, when abstract words are trained using this protocol, improvement would be observed for both abstract and concrete words in the same context-category, but when concrete words are trained, no improvement for abstract words would be observed. We then frame the results of this study with the results of previous studies that used AbSANT to provide better evidence for the utility of this therapeutic technique. We also discuss proposed mechanisms of AbSANT. Method Four persons with aphasia completed one phase of concrete word training and one phase of abstract word training using the AbSANT protocol. Effect sizes were calculated for each word type for each phase. Effect sizes for this study are compared with the effect sizes from previous studies. Results As predicted, training abstract words resulted in both direct training and generalization effects, whereas training concrete words resulted in only direct training effects. The reported results are consistent across studies. Furthermore, when the data are compared across studies, there is a distinct pattern of the added benefit of training abstract words using AbSANT. Conclusion Treatment for word retrieval in aphasia is most often aimed at concrete words, despite the usefulness and pervasiveness of abstract words in everyday conversation. We show the utility of AbSANT as a means of improving not only abstract word retrieval but also concrete word retrieval and hope this evidence will help foster its application in clinical practice.


Medicina ◽  
2021 ◽  
Vol 57 (3) ◽  
pp. 235
Author(s):  
Diego Galvan ◽  
Luciane Effting ◽  
Hágata Cremasco ◽  
Carlos Adam Conte-Junior

Background and objective: In the current pandemic scenario, data mining tools are fundamental to evaluate the measures adopted to contain the spread of COVID-19. In this study, unsupervised neural networks of the Self-Organizing Maps (SOM) type were used to assess the spatial and temporal spread of COVID-19 in Brazil, according to the number of cases and deaths in regions, states, and cities. Materials and methods: The SOM applied in this context does not evaluate which measures applied have helped contain the spread of the disease, but these datasets represent the repercussions of the country’s measures, which were implemented to contain the virus’ spread. Results: This approach demonstrated that the spread of the disease in Brazil does not have a standard behavior, changing according to the region, state, or city. The analyses showed that cities and states in the north and northeast regions of the country were the most affected by the disease, with the highest number of cases and deaths registered per 100,000 inhabitants. Conclusions: The SOM clustering was able to spatially group cities, states, and regions according to their coronavirus cases, with similar behavior. Thus, it is possible to benefit from the use of similar strategies to deal with the virus’ spread in these cities, states, and regions.


2021 ◽  
Author(s):  
Endang Sri Rahayu ◽  
Eko Mulyanto Yuniarno ◽  
I Ketut Edhy Purnama ◽  
Mauridhi Hery Purnomo

2002 ◽  
Vol 14 (1) ◽  
pp. 104-115 ◽  
Author(s):  
Kimihiro Nakamura ◽  
Manabu Honda ◽  
Shigeru Hirano ◽  
Tatsuhide Oga ◽  
Nobukatsu Sawamoto ◽  
...  

We used functional magnetic resonance imaging (fMRI) to examine whether the act of writing involves different neuro-psychological mechanisms between the two script systems of the Japanese language: kanji (ideogram) and kana (phonogram). The main experiments employed a 2 × 2 factorial design that comprised writing-to-dictation and visual mental recall for kanji and kana. For both scripts, the actual writing produced a widespread fronto-parietal activation in the left hemisphere. Especially, writing of kanji activated the left posteroinferior temporal cortex (lPITC), whereas that of kana also yielded a trend of activation in the same area. Mental recall for both scripts activated similarly the left parieto-temporal regions including the lPITC. The writing versus mental recall comparison revealed greater activations in the left sensorimotor areas and right cerebellum. The kanji versus kana comparison showed increased responses in the left prefrontal and anterior cingulate areas. Especially, the lPITC showed a significant task-by-script interaction. Two additional control tasks, repetition (REP) and semantic judgment (SJ), activated the bilateral perisylvian areas, but enhanced the lPITC response only weakly. These results suggest that writing of the ideographic and phonographic scripts, although using the largely same cortical regions, each modulates the visual word-retrieval system according to their graphic features. Furthermore, comparisons with two additional tasks indicate that the activity of the lPITC increases especially in expressive language operations regardless of sensory modalities of the input stimulus.


Author(s):  
Ton Dijkstra ◽  
Walter J. B. van Heuven

This chapter on the reading of words by multilinguals considers how retrieving words in two or more languages is affected by the lexical properties of the words, the sentence context in which they occur, and the language to which they belong. Reaction time and event-related potential (ERP) studies are discussed that investigate the processing of cognates, interlingual homographs, and words with different numbers of neighbors, both in isolation and in sentence context. After reviewing different models for multilingual word retrieval, it is concluded that multilingual word recognition involves a language-independent, context-sensitive, and interactive pattern recognition routine, with temporal properties that can be determined not only by “classical” reaction time techniques, but even better by up-to-date research techniques such as eye-tracking and ERP recordings.


2018 ◽  
Vol In Press (In Press) ◽  
Author(s):  
Salime Jafari ◽  
Ahmad Reza Khatoonabadi ◽  
Maryam Noroozian ◽  
Azar Mehri ◽  
Hassan Ashayeri ◽  
...  

2013 ◽  
Vol 2 (1) ◽  
Author(s):  
Radina Mohamad Deli

Barcroft (2007) found opportunities for word retrieval to be advantageous during second language vocabulary learning. This study extended such a finding and investigated the effect of increased time in target-word retrieval for learning new vocabulary in the L2, as well as the effect of presentation orders of different time conditions on word retrieval. The data were obtained from 17 native Arab speakers who attempted to learn 24 new English words by viewing 24 word-picture pairs. Each picture and its corresponding word were viewed with different time lags of 0, 6 and 12 seconds between them in different presentation orders. The results showed that, although the increased time does not positively affect word retrieval, the overall findings correspond to Barcroft’s (2007) view, at least in the case of 6 seconds lag. The results also showed that the production of target words in both the control and retrieval-oriented conditions depend on and vary according to the order of presentation, particularly in the case of 6 seconds lag in which word gain is found to be highest when the lag is presented first and second.


Sign in / Sign up

Export Citation Format

Share Document