X hits on this document

PDF document

The split-fovea model of visual word - page 35 / 78

234 views

0 shares

0 downloads

0 comments

35 / 78

Total errors

139

136

Errors with frequency 0.1

129

116

Errors with higher frequency

10

20

Average Frequency

0.056

0.066

30

Chapter 2. The Simulations

Control Network Fixation Network

Table 2.4: Errors by frequency.

2.2.2

Frequency

Table 2.4 shows the network’s performance in relation to the frequency of the incorrect words. Not surprisingly, for both networks, most errors were made on low frequency words. The control network made 129 of its 139 errors on words with a frequency lower than 0.1 and he fixation network 116 of 136. The average frequency of the errors was 0.056 for the control and 0.066 for the fixation model. The error with the highest frequencies were ’coup’ at all positions for the control with a frequency of

    • 0.110

      and ’shed’ at position 1 for the fixation net with a frequency of 0.223 (see table

    • 2.5

      and 2.6. This result also means that the networks have correctly learned all the

higher frequency irregular words that were in the training corpus.

Tables of the errors with a frequency 0.1 have been included (2.5 for the control network and 2.6 for the fixation network). Note that a complete list of the errors made by each network can be found in appendix B and C respectively. As can be seen from the tables, most pronunciations computed by the networks, even though they are wrong, are nevertheless pretty close to the actual output. Thus, for example both networks pronounce the word ’dose’ as /d@Uz/ instead of /d@Us/ in most positions. Clearly this error is only a very slight error in the sharpness with which the coda of ’dose is pronounced. In fact, looking through the errors in the appendix, this error of the network substituting an /z/ instead of an /s/ is very common. Although this seems not to be a very big error, the pronunciation /d@Uz/ would correspond to the word

Document info
Document views234
Page views243
Page last viewedFri Dec 09 20:39:41 UTC 2016
Pages78
Paragraphs3087
Words17414

Comments