Concordance

Query C04-1096 15 >
Shuffle 15 (699.3 per million)

other,15-1-C04-1096,bq	<term> binary relations </term> between <term>	objects	</term> . However , such an approach does	#5629 Past work of generating referring expressions mainly utilized attributes of objects and binary relations betweenobjects.
other,13-4-C04-1096,bq	</term> that are naturally recognized by <term>	humans	</term> . We conducted <term> psychological	#5684 The key is to identify groups of objects that are naturally recognized byhumans.
other,2-5-C04-1096,bq	by <term> humans </term> . We conducted <term>	psychological experiments	</term> with 42 subjects to collect <term>	#5688 We conductedpsychological experiments with 42 subjects to collect referring expressions in such situations, and built a generation algorithm based on the results.
other,9-5-C04-1096,bq	</term> with 42 subjects to collect <term>	referring expressions	</term> in such situations , and built a <term>	#5695 We conducted psychological experiments with 42 subjects to collectreferring expressions in such situations, and built a generation algorithm based on the results.
other,15-6-C04-1096,bq	could effectively generate proper <term>	referring expressions	</term> . <term> Machine transliteration/back-transliteration	#5726 The evaluation using another 23 subjects showed that the proposed method could effectively generate properreferring expressions.
other,14-2-C04-1096,bq	well when there is no distinctive <term>	attribute	</term> among <term> objects </term> . To overcome	#5645 However, such an approach does not work well when there is no distinctiveattribute among objects.
tech,18-5-C04-1096,bq	</term> in such situations , and built a <term>	generation algorithm	</term> based on the results . The evaluation	#5704 We conducted psychological experiments with 42 subjects to collect referring expressions in such situations, and built ageneration algorithm based on the results.
other,8-1-C04-1096,bq	expressions </term> mainly utilized <term>	attributes	</term> of <term> objects </term> and <term> binary	#5622 Past work of generating referring expressions mainly utilizedattributes of objects and binary relations between objects.
other,16-2-C04-1096,bq	distinctive <term> attribute </term> among <term>	objects	</term> . To overcome this limitation , this	#5647 However, such an approach does not work well when there is no distinctive attribute amongobjects.
other,7-4-C04-1096,bq	. The key is to identify groups of <term>	objects	</term> that are naturally recognized by <term>	#5678 The key is to identify groups ofobjects that are naturally recognized by humans.
other,12-1-C04-1096,bq	attributes </term> of <term> objects </term> and <term>	binary relations	</term> between <term> objects </term> . However	#5626 Past work of generating referring expressions mainly utilized attributes of objects andbinary relations between objects.
other,15-3-C04-1096,bq	utilizing the perceptual groups of <term>	objects	</term> and <term> n-ary relations </term> among	#5664 To overcome this limitation, this paper proposes a method utilizing the perceptual groups ofobjects and n-ary relations among them.
other,17-3-C04-1096,bq	perceptual groups of <term> objects </term> and <term>	n-ary relations	</term> among them . The key is to identify	#5666 To overcome this limitation, this paper proposes a method utilizing the perceptual groups of objects andn-ary relations among them.
other,10-1-C04-1096,bq	utilized <term> attributes </term> of <term>	objects	</term> and <term> binary relations </term> between	#5624 Past work of generating referring expressions mainly utilized attributes ofobjects and binary relations between objects.
tech,3-1-C04-1096,bq	intensive framework </term> . Past work of <term>	generating referring expressions	</term> mainly utilized <term> attributes </term>	#5617 Past work ofgenerating referring expressions mainly utilized attributes of objects and binary relations between objects.


	in Help