| D08-1061 | The user was also presented with | Web search | link to verify the results against |
| D08-1040 | extracting of word associations using a | Web search | engine is fea - sible . The main |
| C04-1093 | term , as performed in existing | Web search | engines . The extraction module |
| C02-2017 | utterances in a multi-modal system for | web search | in newspaper databases . Users |
| A97-1033 | the amount of online full text , | Web search | that must be done . At this stage |
| A00-1003 | Typical queries are , as in most | Web search | applications , two to three words |
| C04-1066 | sets based on the hit number of a | web search | engine which is shown in Appendix |
| C02-1026 | ) , we used WordNet glosses or | web search | results to rerank the answers |
| C04-1066 | corpus . Then , we use hits on a | web search | engine as substitutes for frequencies |
| C02-1008 | information retrieval ( CLIR ) and | Web search | is the lack of appropriate translations |
| D08-1002 | , Wikipedia ar - ticles , and | Web search | engine results . In our data |
| C04-1195 | " M H " , as acquired using a | web search | engine . For instance , given |
| C04-1201 | we use in order to perform the | web search | . We begin by eliminating from |
| C04-1066 | word may be a stop word of the | web search | en - gine . When we reject the |
| D08-1029 | collected by selecting the top 100 | web search | results to queries about a name |
| C04-1170 | context , in a way similar to | web search | engine querying . 4 Lexicalisation |
| C02-1026 | using a dictionary ( WordNet ) and | web search | engines ( Altavista , MSN , and |
| D08-1061 | natural language understanding and | Web search | , as illustrated by their prominence |
| C02-1127 | in the search results of other | Web search | engines . This means they will |
| C00-2127 | ~ , V documcnts gathered by a | Web search | engine . supplies rnore specific |
