### Table 3. Residual errors for corrections performed with computer-assisted technique.

"... In PAGE 6: ... Table 2 gives the angular and translational residuals for fluo- roscopic guidance. Table3 gives the angular and translational residuals for computer- assisted guidance. For both techniques, the mean and standard deviations of the residu- als is shown.... ..."

### Table 2. Algorithm Framework for GA-DFALS Algorithm: Learning Deterministic Finite-state Automaton Based on Genetic Algorithm (A Basis)

2006

"... In PAGE 8: ...dure [7], and it is so called standard genetic algorithm 4. The core of our learning system (Deterministic Finite-state Automaton Learning System Based on Genetic Algorithm, GA-DFALS) is based on this framework (see Table2 ). The genetic operators we used are fitness proportionate selection operator, uniform crossover operator, and point mutation operator.... ..."

### TABLE VIII THE NUMBER OF STATES FOR FINITE-STATE CODES BY ALGORITHM A

### TABLE I. A Finite-State Automaton for Recognizing Tokens Old

### Table 1: Our computed-assisted bound for the rate of approach to equilibrium compared to known theoretical bounds

"... In PAGE 4: ... instead. A comparison of our computed estimates with known theoretical estimates is made in Table1 . The map ~ T has a graph almost identical to that displayed in Figure 2.... ..."

### TABLE 1. Result of the transformation of the finite-state graph into a transition table.

2006

### Table 6. Sample rules from the Chou-Fasman finite-state automaton.

1992

"... In PAGE 13: ... Each transition is actually a set of rules dependent on the input window and the current state. Table6 displays some samples of different types of rules derived from the FSA (the full set of rules appear in the Appendix). Not all of the rules involve state information; some of the rules are used to prove propositions that are used in other rules.... ..."

Cited by 13

### Table 6. Sample rules from the Chou-Fasman finite-state automaton.

"... In PAGE 13: ... Each transition is actually a set of rules dependent on the input window and the current state. Table6 displays some samples of different types of rules derived from the FSA (the full set of rules appear in the Appendix). Not all of the rules involve state information; some of the rules are used to prove propositions that are used in other rules.... ..."

### Table 1. Sentence translation rates (SA) and word accuracies (WA) obtained using Connectionist Mod- els and di erent Finite-State Models trained on two incremental corpora from the Spanish-to-English Descriptive MLA-MT task.

"... In PAGE 6: ... Both connectionist and nite-state models were trained on the two preceding corpora and tested on the same test corpus. The translation accuracies achieved (see Table1 ) again show that NNs outperformed FSMs. It should be noted that a SST inferred with DR constraints only provides complete sen- tence and, consequently, the word accuracy translations can be decreased as it can be observed in Table 1.... In PAGE 6: ... The translation accuracies achieved (see Table 1) again show that NNs outperformed FSMs. It should be noted that a SST inferred with DR constraints only provides complete sen- tence and, consequently, the word accuracy translations can be decreased as it can be observed in Table1 . The inferred SSTs had less than 1,000 states and 2,000 edges1.... ..."

### Table 2. Sentence translation rates (SA) and word accuracies (WA) obtained using Connectionist Mod- els and di erent Finite-State Models trained on two incremental corpora from the Spanish-to-English Extended MLA-MT task.

"... In PAGE 6: ... The learned neural and nite-state mod- els were later evaluated on the test corpus. Table2 shows the translation rates, which clearly indicates that NNs outperformed FSMs. 1 However, SSTs with less than 100 states and a few hundred edges were inferred using 50,000 training... ..."