| C92-3167 | and Speech Acts The unnatural | topic expansion | in Fig. 2 is related to speech |
| P98-2205 | describe a method of full-text | topic expansion | where the expansion passages |
| C92-3167 | in Fig. 1 . On the other hand , | topic expansion | is not natural in the dialogue |
| X96-1046 | also did well . Another factor in | topic expansion | is the number of terms being |
| C92-3167 | topic forwarding " . The unnatural | topic expansion | in Fig. 2 can be explained by |
| X96-1046 | created from the topic , but no | topic expansion | is done . There is minimal difference |
| C92-3167 | contradiction causes unnatural | topic expansion | . Utterance pairs such as " requesting |
| D08-1080 | the summaries produced with no | topic expansion | , WordNet ( WN ) and Wikipedia |
| X96-1046 | did not want to use more radical | topic expansion | methods . Additionally they used |
| X96-1046 | each group found the level of | topic expansion | appropriate for their retrieval |
| D08-1080 | . We analyze several types of | topic expansion | : no expansion , WordNet , Wikipedia |
| X96-1046 | retrieval ( sub - documents ) and | topic expansion | . This system used far fewer |
| X96-1046 | vector-space system . Both the | topic expansion | and the passage determination |
| D08-1080 | associations in the documents ' graph . 3 | Topic Expansion | with Encyclopedic Knowledge or |
| X93-1007 | types of automatic thesaurii for | topic expansion | have had unexpected success . |
| X96-1046 | document ranking , but only minimal | topic expansion | was used , with that expansion |
| X96-1046 | have for Passage Retrieval and | Topic Expansion | fewer relevant documents , but |
| T78-1014 | two levels in the same text . | Topic expansion | is illustrated in a story from |
| X96-1046 | local/global weighting schemes ( with no | topic expansion | ) . = cityal = INQ101 & CralEA |
| X96-1046 | runs . The westpl run did not use | topic expansion | , although a rrfixture of passages |
