| D11-1031 | optimise our parser towards a | task-based evaluation | . Our CCG parser is evaluated |
| A00-2024 | system . We are preparing the | task-based evaluation | of the overall system . We also |
| E03-1025 | comparison ( from Table 1 ) . In the | task-based evaluation | , the performance gap between |
| E14-1021 | judgments more strongly than BLEU on a | task-based evaluation | of paraphrase quality . 2 Related |
| E14-1066 | this section , we undertake a | task-based evaluation | of model output . We train on |
| D14-1073 | Abstract In this paper we present our | task-based evaluation | of query biased summarization |
| J09-2001 | granularities are contrasted in | task-based evaluation | . Prepositions are highly frequent |
| D14-1073 | methods and overall strategies in a | task-based evaluation | framework using relevance prediction |
| C00-2104 | * ~ re are planning to conduct | task-based evaluation | in question answering . * We |
| J09-4008 | the most common measure used in | task-based evaluations | in NLG , other measures can also |
| D14-1034 | syntactic parser , we turn to a | task-based evaluation | . We aim to predict the degree |
| J09-4008 | have been involved in a number of | task-based evaluations | of NLG systems and components |
| J08-1003 | The article also reports on a | task-based evaluation | experiment to rank the parsers |
| D14-1073 | <title> Finding Good Enough : A | Task-Based Evaluation | of Query Summarization for Cross |
| E14-1032 | evaluation . We opt therefore to use a | task-based evaluation | to compare our system directly |
| E03-1034 | evaluation are usually conducted : | task-based evaluation | and comparisons against human |
| C00-1012 | approach . Setting aside whether | task-based evaluation | is appropriate for testing strictly |
| E12-1048 | human-computer interaction , where running | task-based evaluations | is particularly expen sive , |
| C00-2104 | remain unclear until we conduct a | task-based evaluation | whether the smaller number of |
| E12-1064 | machine translation system for a | task-based evaluation | on the translation of direct |
