| questions </term> . Until now , the only way | to | assess the correctness of answers to such | #7546 Until now, the only way to assess the correctness of answers to such questions involves manual determination of whether an information nugget appears in a system's response. | |
| measure(ment),28-1-H05-1117,bq | for <term> automatically evaluating answers | to | definition questions </term> . Until now | #7536 Following recent developments in the automatic evaluation of machine translation and document summarization, we present a similar approach, implemented in a measure called POURPRE, for automatically evaluating answers to definition questions. |
| scoring system output </term> is an impediment | to | progress in the field , which we address | #7582 The lack of automatic methods for scoring system output is an impediment to progress in the field, which we address with this work. | |
| way to assess the correctness of answers | to | such questions involves manual determination | #7552 Until now, the only way to assess the correctness of answers to such questions involves manual determination of whether an information nugget appears in a system's response. |
