| tech,1-4-H01-1001,ak | . Traditional <term> information retrieval | techniques | </term> use a <term> histogram </term> of <term> | #58 Traditional information retrieval techniques use a histogram of keywords as the document representation but oral communication may offer additional indices such as the time and place of the rejoinder and the attendance. | |
| tech,12-1-H01-1042,ak | efficacy of applying <term> automated evaluation | techniques | </term> , originally devised for the <term> | #558 The purpose of this research is to test the efficacy of applying automated evaluation techniques, originally devised for the evaluation of human language learners, to the output of machine translation (MT) systems. | |
| tech,4-2-H01-1042,ak | </term> . We believe that these <term> evaluation | techniques | </term> will provide information about both | #586 We believe that these evaluation techniques will provide information about both the human language learning process, the translation process and the development of machine translation systems. | |
| tech,28-4-H01-1055,ak | overcome by employing <term> machine learning | techniques | </term> . In this paper , we address the | #1025 We show how research in generation can be adapted to dialog systems, and how the high cost of hand-crafting knowledge-based generation systems can be overcome by employing machine learning techniques. | |
| tech,7-4-P01-1007,ak | In this paper , we study a <term> parsing | technique | </term> whose purpose is to improve the practical | #1687 In this paper, we study a parsing technique whose purpose is to improve the practical efficiency of RCL parsers. | |
| formal computation of the logical form . | Techniques | for automatically training modules of a | #2013 Here we emphasize the connection to Montague semantics which can be viewed as a formal computation of the logical form. Techniques for automatically training modules of a natural language generator have recently been proposed, but a fundamental concern is whether the quality of utterances produced with trainable components can compete with hand-crafted template-based or rule-based approaches. | ||
| mechanisms and the other adopting statistical | techniques | . We present our <term> multi-level answer | #2371 The answering agents adopt fundamentally different strategies, one utilizing primarily knowledge-based mechanisms and the other adopting statistical techniques. | ||
| tech,5-1-N03-1026,ak | ambiguity packing and stochastic disambiguation | techniques | </term> for <term> Lexical-Functional Grammars | #2795 We present an application of ambiguity packing and stochastic disambiguation techniques for Lexical-Functional Grammars (LFG) to the domain of sentence condensation. | |
| tech,4-1-N03-2015,ak | . We describe a simple <term> unsupervised | technique | </term> for learning <term> morphology </term> | #3159 We describe a simple unsupervised technique for learning morphology by identifying hubs in an automaton. | |
| performance to more complex mixtures of | techniques | . We present a <term> syntax-based constraint | #3227 Those hubs mark the boundary between root and suffix, achieving similar performance to more complex mixtures of techniques. | ||
| introduce a number of new performance enhancing | techniques | including <term> part of speech tagging </term> | #4106 Motivated by these arguments, we introduce a number of new performance enhancing techniques including part of speech tagging, new similarity measures and expanded stop lists. | ||
| tech,4-1-P03-2036,ak | empirical comparison of <term> CFG filtering | techniques | </term> for <term> LTAG </term> and <term> HPSG | #5116 An empirical comparison of CFG filtering techniques for LTAG and HPSG is presented. | |
| tech,3-4-H05-1012,ak | improvement over <term> traditional word alignment | techniques | </term> is shown as well as improvement on | #5339 Significant improvement over traditional word alignment techniques is shown as well as improvement on several machine translation tests. | |
| are focused on <term> parsing </term> , the | techniques | described generalize naturally to NLP structures | #5569 Although our experiments are focused on parsing, the techniques described generalize naturally to NLP structures other than parse trees. | ||
| </term> . Basic methodology and practical | techniques | are reported in detail . The resultant <term> | #7296 Basic methodology and practical techniques are reported in detail. | ||
| tech,4-4-I05-5003,ak | Our results show that <term> MT evaluation | techniques | </term> are able to produce useful features | #7453 Our results show that MT evaluation techniques are able to produce useful features for paraphrase classification and to a lesser extent entailment. | |
| lesser extent <term> entailment </term> . Our | technique | gives a substantial improvement in <term> | #7471 Our technique gives a substantial improvement in paraphrase classification accuracy over all of the other models used in the experiments. | ||
| tech,5-1-P05-1046,ak | many current <term> information extraction | techniques | </term> is severely limited by the need for | #9023 The applicability of many current information extraction techniques is severely limited by the need for supervised training data. | |
| tech,1-3-P05-1074,ak | available resource . Using <term> alignment | techniques | </term> from <term> phrase-based statistical | #10178 Using alignment techniques from phrase-based statistical machine translation, we show how paraphrases in one language can be identified using a phrase in another language as a pivot. | |
| tech,1-2-P05-2008,ak | negative . Traditional <term> machine learning | techniques | </term> have been applied to this problem | #10421 Traditional machine learning techniques have been applied to this problem with reasonable success, but they have been shown to work well only when there is a good match between the training and test data with respect to topic. |
