| measure(ment),21-7-H01-1058,ak | The method amounts to tagging <term> LMs </term> with <term> confidence measures </term> and picking the best <term> hypothesis </term> corresponding to the <term> LM </term> with the best <term> confidence </term> . | #1193 The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to the LM with the bestconfidence. | |
| measure(ment),7-7-H01-1058,ak | The method amounts to tagging <term> LMs </term> with <term> confidence measures </term> and picking the best <term> hypothesis </term> corresponding to the <term> LM </term> with the best <term> confidence </term> . | #1179 The method amounts to tagging LMs withconfidence measures and picking the best hypothesis corresponding to the LM with the best confidence. | |
| tech,17-6-H01-1058,ak | We suggest a method that mimics the behavior of the <term> oracle </term> using a <term> neural network </term> or a <term> decision tree </term> . | #1169 We suggest a method that mimics the behavior of the oracle using a neural network or adecision tree. | |
| tech,7-4-H01-1058,ak | Actually , the <term> oracle </term> acts like a <term> dynamic combiner </term> with hard decisions using the <term> reference </term> . | #1122 Actually, the oracle acts like adynamic combiner with hard decisions using the reference. | |
| tech,11-5-H01-1058,ak | We provide experimental results that clearly show the need for a <term> dynamic language model combination </term> to improve the <term> performance </term> further . | #1142 We provide experimental results that clearly show the need for adynamic language model combination to improve the performance further. | |
| other,13-7-H01-1058,ak | The method amounts to tagging <term> LMs </term> with <term> confidence measures </term> and picking the best <term> hypothesis </term> corresponding to the <term> LM </term> with the best <term> confidence </term> . | #1185 The method amounts to tagging LMs with confidence measures and picking the besthypothesis corresponding to the LM with the best confidence. | |
| tech,4-2-H01-1058,ak | We find that simple <term> interpolation methods </term> , like <term> log-linear and linear interpolation </term> , improve the <term> performance </term> but fall short of the <term> performance </term> of an <term> oracle </term> . | #1048 We find that simpleinterpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of an oracle. | |
| model,11-1-H01-1058,ak | In this paper , we address the problem of combining several <term> language models ( LMs ) </term> . | #1038 In this paper, we address the problem of combining severallanguage models ( LMs ). | |
| model,43-3-H01-1058,ak | The <term> oracle </term> knows the <term> reference word string </term> and selects the <term> word string </term> with the best <term> performance </term> ( typically , <term> word or semantic error rate </term> ) from a list of <term> word strings </term> , where each <term> word string </term> has been obtained by using a different <term> LM </term> . | #1113 The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a differentLM. | |
| model,17-7-H01-1058,ak | The method amounts to tagging <term> LMs </term> with <term> confidence measures </term> and picking the best <term> hypothesis </term> corresponding to the <term> LM </term> with the best <term> confidence </term> . | #1189 The method amounts to tagging LMs with confidence measures and picking the best hypothesis corresponding to theLM with the best confidence. | |
| model,5-7-H01-1058,ak | The method amounts to tagging <term> LMs </term> with <term> confidence measures </term> and picking the best <term> hypothesis </term> corresponding to the <term> LM </term> with the best <term> confidence </term> . | #1177 The method amounts to taggingLMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. | |
| tech,8-2-H01-1058,ak | We find that simple <term> interpolation methods </term> , like <term> log-linear and linear interpolation </term> , improve the <term> performance </term> but fall short of the <term> performance </term> of an <term> oracle </term> . | #1052 We find that simple interpolation methods, likelog-linear and linear interpolation, improve the performance but fall short of the performance of an oracle. | |
| tech,13-6-H01-1058,ak | We suggest a method that mimics the behavior of the <term> oracle </term> using a <term> neural network </term> or a <term> decision tree </term> . | #1165 We suggest a method that mimics the behavior of the oracle using aneural network or a decision tree. | |
| tech,24-2-H01-1058,ak | We find that simple <term> interpolation methods </term> , like <term> log-linear and linear interpolation </term> , improve the <term> performance </term> but fall short of the <term> performance </term> of an <term> oracle </term> . | #1068 We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of the performance of anoracle. | |
| tech,1-3-H01-1058,ak | The <term> oracle </term> knows the <term> reference word string </term> and selects the <term> word string </term> with the best <term> performance </term> ( typically , <term> word or semantic error rate </term> ) from a list of <term> word strings </term> , where each <term> word string </term> has been obtained by using a different <term> LM </term> . | #1071 Theoracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. | |
| tech,3-4-H01-1058,ak | Actually , the <term> oracle </term> acts like a <term> dynamic combiner </term> with hard decisions using the <term> reference </term> . | #1118 Actually, theoracle acts like a dynamic combiner with hard decisions using the reference. | |
| tech,10-6-H01-1058,ak | We suggest a method that mimics the behavior of the <term> oracle </term> using a <term> neural network </term> or a <term> decision tree </term> . | #1162 We suggest a method that mimics the behavior of theoracle using a neural network or a decision tree. | |
| measure(ment),15-2-H01-1058,ak | We find that simple <term> interpolation methods </term> , like <term> log-linear and linear interpolation </term> , improve the <term> performance </term> but fall short of the <term> performance </term> of an <term> oracle </term> . | #1059 We find that simple interpolation methods, like log-linear and linear interpolation, improve theperformance but fall short of the performance of an oracle. | |
| measure(ment),21-2-H01-1058,ak | We find that simple <term> interpolation methods </term> , like <term> log-linear and linear interpolation </term> , improve the <term> performance </term> but fall short of the <term> performance </term> of an <term> oracle </term> . | #1065 We find that simple interpolation methods, like log-linear and linear interpolation, improve the performance but fall short of theperformance of an oracle. | |
| measure(ment),15-3-H01-1058,ak | The <term> oracle </term> knows the <term> reference word string </term> and selects the <term> word string </term> with the best <term> performance </term> ( typically , <term> word or semantic error rate </term> ) from a list of <term> word strings </term> , where each <term> word string </term> has been obtained by using a different <term> LM </term> . | #1085 The oracle knows the reference word string and selects the word string with the bestperformance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
