| measure(ment),21-2-H01-1058,bq | performance </term> but fall short of the <term> | performance | </term> of an <term> oracle </term> . The <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),19-3-H01-1058,bq | <term> performance </term> ( typically , <term> | word or semantic error rate | </term> ) from a list of <term> word strings | #1089 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 different LM. |
| other,29-3-H01-1058,bq | error rate </term> ) from a list of <term> | word strings | </term> , where each <term> word string </term> | #1099 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 ofword strings, where each word string has been obtained by using a different LM. |
| tech,7-4-H01-1058,bq | the <term> oracle </term> acts like a <term> | dynamic combiner | </term> with <term> hard decisions </term> using | #1122 Actually, the oracle acts like adynamic combiner with hard decisions using the reference. |
| measure(ment),7-7-H01-1058,bq | amounts to tagging <term> LMs </term> with <term> | confidence measures | </term> and picking the best <term> hypothesis | #1179 The method amounts to tagging LMs withconfidence measures and picking the best hypothesis corresponding to the LM with the best confidence. |
| other,10-4-H01-1058,bq | a <term> dynamic combiner </term> with <term> | hard decisions | </term> using the <term> reference </term> . | #1125 Actually, the oracle acts like a dynamic combiner withhard decisions using the reference. |
| other,14-4-H01-1058,bq | <term> hard decisions </term> using the <term> | reference | </term> . We provide experimental results | #1129 Actually, the oracle acts like a dynamic combiner with hard decisions using thereference. |
| tech,4-2-H01-1058,bq | LMs ) </term> . We find that simple <term> | interpolation methods | </term> , like <term> log-linear and linear | #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,17-7-H01-1058,bq | 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. |
| measure(ment),15-3-H01-1058,bq | <term> word string </term> with the best <term> | performance | </term> ( typically , <term> word or semantic | #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. |
| measure(ment),15-2-H01-1058,bq | interpolation </term> , improve the <term> | performance | </term> but fall short of the <term> performance | #1059 We find that simple interpolation methods, like log-linear and linear interpolation, improve theperformance but fall short of the performance of an oracle. |
| tech,17-6-H01-1058,bq | using a <term> neural network </term> or a <term> | decision tree | </term> . The method amounts to tagging <term> | #1169 We suggest a method that mimics the behavior of the oracle using a neural network or adecision tree. |
| measure(ment),18-5-H01-1058,bq | model combination </term> to improve the <term> | performance | </term> further . We suggest a method that | #1149 We provide experimental results that clearly show the need for a dynamic language model combination to improve theperformance further. |
| tech,8-2-H01-1058,bq | interpolation methods </term> , like <term> | log-linear and linear interpolation | </term> , improve the <term> performance </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. |
| model,11-1-H01-1058,bq | address the problem of combining several <term> | language models ( LMs ) | </term> . We find that simple <term> interpolation | #1038 In this paper, we address the problem of combining severallanguage models ( LMs ). |
| model,5-7-H01-1058,bq | </term> . The method amounts to tagging <term> | LMs | </term> with <term> confidence measures </term> | #1177 The method amounts to taggingLMs with confidence measures and picking the best hypothesis corresponding to the LM with the best confidence. |
| other,13-7-H01-1058,bq | measures </term> and picking the best <term> | hypothesis | </term> corresponding to the <term> LM </term> | #1185 The method amounts to tagging LMs with confidence measures and picking the besthypothesis corresponding to the LM with the best confidence. |
| tech,11-5-H01-1058,bq | results that clearly show the need for a <term> | dynamic language model combination | </term> to improve the <term> performance </term> | #1142 We provide experimental results that clearly show the need for adynamic language model combination to improve the performance further. |
| model,43-3-H01-1058,bq | been obtained by using a different <term> | LM | </term> . Actually , the <term> oracle </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. |
| other,10-3-H01-1058,bq | word string </term> and selects the <term> | word string | </term> with the best <term> performance </term> | #1080 The oracle knows the reference word string and selects theword 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. |
