| resources </term> are <term> monolingual </term> . We | also | refer to an <term> evaluation method </term> | #9812 We also refer to an evaluation method and plan to compare our system's output with a benchmark system. | |
| approximations </term> for these computations . We | also | discuss some practical ways of dealing | #10077 We also discuss some practical ways of dealing with complexity. | |
| given biased <term> gold standard </term> it | also | enables <term> automatic parameter optimization | #10225 Offering advantages like reproducability and independency of a given biased gold standard it also enables automatic parameter optimization of the WSI algorithm. | |
| indicators for the top-level prediction task . We | also | find that the <term> transcription errors | #10609 We also find that the transcription errors inevitable in ASR output have a negative impact on models that combine lexical-cohesion and conversational features, but do not change the general preference of approach for the two tasks. | |
| evaluate their relative performances . We | also | introduce a new strategy , called <term> | #10841 We also introduce a new strategy, called Begin/After tagging or BIA, and show that it is competitive to the best other strategies. | |
| 96 % and a <term> recall </term> of 98 % . It | also | gets a <term> precision </term> of 70 % and | #11262 It also gets a precision of 70% and a recall of 49% in the task of placing commas. | |
| </term> of <term> abstract moves </term> . We | also | present a prototype <term> concordancer </term> | #11760 We also present a prototype concordancer, CARE, which exploits the move-tagged abstracts for digital learning. | |
| different <term> inference types </term> . The paper | also | discusses how <term> memory </term> is structured | #12020 The paper also discusses how memory is structured in multiple ways to support the different inference types, and how the information found in memory determines which inference types are triggered. | |
| can make a fair copy of not only texts but | also | graphs and tables indispensable to our | #12256 In this paper, we report a system FROFF which can make a fair copy of not only texts but also graphs and tables indispensable to our papers. | |
| and the <term> typing location </term> can be | also | changed in lateral or longitudinal directions | #12284 Its selection of fonts, specification of character size are dynamically changeable, and the typing location can be also changed in lateral or longitudinal directions. | |
| aspects of <term> language learning </term> are | also | discussed . Current <term> natural language | #12524 Implications towards automating certain aspects of language learning are also discussed. | |
| appear cooperative or graceful unless they | also | incorporate numerous <term> non-literal aspects | #12569 While such decoding is an essential underpinning, much recent work suggests that natural language interfaces will never appear cooperative or graceful unless they also incorporate numerous non-literal aspects of communication, such as robust communication procedures. | |
| vital to <term> machine translation </term> are | also | discussed together with various interesting | #13314 Some examples of the difference between Japanese sentence structure and English sentence structure, which is vital to machine translation are also discussed together with various interesting ambiguities. | |
| view of <term> language definition </term> are | also | noted . Representative samples from an <term> | #13401 Several advantages from the point of view of language definition are also noted. | |
| conversational vehicle to deliver it . The paper | also | promotes a new view for <term> extensional | #14571 The paper also promotes a new view for extensional reference. | |
| way . This <term> generation system </term> | also | uses <term> disjunctive feature structures | #16249 This generation systemalso uses disjunctive feature structures to reduce the number of copies of the derivation tree. | |
| interface </term> for browsing and editing was | also | designed and implemented . The principle | #17330 A customized interface for browsing and editing was also designed and implemented. | |
| training corpus </term> and the real tasks are | also | taken into consideration by enlarging the | #17899 To make the proposed algorithm robust, the possible variations between the training corpus and the real tasks are also taken into consideration by enlarging the separation margin between the correct candidate and its competing members. | |
| <term> sentence </term> again . This method is | also | capable of handling <term> unknown words </term> | #18228 This method is also capable of handling unknown words, which is important in practical systems. | |
| field of <term> speech processing </term> , but | also | in the related areas of <term> Human-Machine | #18636 The paper provides an overview of the research conducted at LIMSI in the field of speech processing, but also in the related areas of Human-Machine Communication, including Natural Language Processing, Non Verbal and Multimodal Communication. |
