| M92-1005 | in The second prediction about | greedy merger | concerned incorrect slot fills |
| M92-1005 | then asked how lazy merger and | greedy merger | would affect the various scores |
| M92-1005 | problems relative to the NST set and | greedy merger | problems relative to the 1MT |
| M92-1005 | subject to both lazy merger and | greedy merger | problems . They should show lazy |
| M92-1005 | conclude that lazy merger and | greedy merger | are real problems in discourse |
| M92-1005 | least some of this may be due to | greedy merger | problems , supported by the somewhat |
| M92-1005 | multiple templates ( see Figure 2 ) . | Greedy merger | typically results in missing |
| M92-1005 | result in missing slot fills . | Greedy Merger | Two clauses describe two different |
| M92-1005 | 1.4 Measuring Lazy Merger and | Greedy Merger | Using these four message subsets |
| M92-1005 | 1ST vs. NST and 1MT vs. 2MT for | greedy merger | . Finally , we expect 1ST to |
| M92-1005 | corresponding decrease in recall . | Greedy merger | could also result in incorrect |
| M92-1005 | multi-template output , to test for | greedy merger | . The cross product of these |
| M92-1005 | problems caused by lazy merger and | greedy merger | , we defined two conditions : |
| M92-1005 | to those filled incorrectly . | Greedy merger | could result in lower recall |
| M92-1005 | followed by 1MT and finally 2MT . For | greedy merger | , we hypothesized that multi-template |
