### Table 4: Standard ML vs tw-constrained ML training

1994

"... In PAGE 16: ...ased on a similar reasoning. We call it t-constraint. tw-constraint The tw-constrained ML training is similar to the standard ML training, ex- cept that the probabilities p#28t=w#29 are not changed at the end of an iteration. The results in Table4 show the number of tagging errors when the model is trained with the standard or tw-constrained ML training. They show that the tw-constrained ML training still degrades the RF training, but not as... ..."

Cited by 163

### Table 5: Standard ML vs constrained ML training

1994

"... In PAGE 17: ...o a biclass model, i.e. a model where p#28t i =w 1 t 1 :::w i,1 t i,1 #29=h#28t i =t i,1 #29 The initial model is estimated by relative frequency on the whole training data and Viterbi tagging is used. As in the previous experiment, the results in Table5 show the number of tagging errors when the model is trained with the standard or t-constrained ML training. They show that the t-constrained ML training still degrades the RF training, but not as quickly as the standard ML.... ..."

Cited by 163

### Table 4 Standard ML vs. tw-constrained ML training.

### Table 1 shows the estimated standard deviation of the three considered ML estimators.

"... In PAGE 8: ... Table1 : Standard deviation of the Maximum Likelihood estimators. The Scale column contains the mean abs.... In PAGE 8: ... value of the estimated quantity, except for the camera orientation row, where error is given in degrees. Table1 shows that the standard deviation of the dual representation estimators is al- ways significantly lower than that of the ML estimator of independent point coordinates. One should also note that the estimation of all parameters, including the orientation of cameras, their positions and focal length, is improved.... ..."

Cited by 2

### Table 1 shows the estimated standard deviation of the three considered ML estimators.

"... In PAGE 8: ... Table1 : Standard deviation of the Maximum Likelihood estimators. The Scale column contains the mean abs.... In PAGE 8: ... value of the estimated quantity, except for the camera orientation row, where error is given in degrees. Table1 shows that the standard deviation of the dual representation estimators is al- ways significantly lower than that of the ML estimator of independent point coordinates. One should also note that the estimation of all parameters, including the orientation of cameras, their positions and focal length, is improved.... ..."

### Table 2: Thread topic coherences and thread com- ponent coherences.

2004

"... In PAGE 7: ... The di erence between Hlogo value and that of random assignment is more than 3 times the standard deviation, showing that the topic assignment by the proposed method is statistically signi - cantly better than random topic assignment. Table2 reports the average thread topic coherence of all 335 threads we collected from the CNN set. In the table, we also show the thread component coherence (denoted as Hthread), which is the coherence value of the shots in a thread component.... ..."

Cited by 5

### Table 5: ML mod raw expressions

"... In PAGE 9: ... As a result, if e is a term of type , then the application ( x: set(Fst(A [int; 5])):x) e is type-correct, whereas in the absence of the non-standard equations this would not be so (assuming 3 6 = 5 : int). The raw syntax of ML mod is an extension of that of ML; the extensions are given in Table5 . The judgement forms are the same as for ML str , and are axiomatized by the structure rules of Appendix B together with the rules of Appendix C.... ..."

### Table 6: GARCH ML Estimation Results Model 1 Model 2 Model 3 Model 4

1998

"... In PAGE 19: ... We scale the news count variables by a factor of 0:01 as is indicated in table 6. Table6 presents Quasi-Maximum Likelihood Estimates for four different versions of our augmented GARCH(1,1) model. Standard errors from the estimated Hessian are reported in parentheses and robust standard errors (Bollerslev and Wooldridge 1992) are shown in square brackets.... In PAGE 19: ... Finally, in addition to the interest rate differential, we include currency-specific news-count variables in the variance (Model 4). Table 7 summarizes some analyses of the standardized residuals from the models re- ported in Table6 . In particular, we report descriptive statistics for the first four moments of the standardized residuals.... ..."

Cited by 5