| an <term> expert human translation </term> | or | a <term> machine translation </term> . Additionally | #734 The subjects were given three minutes per extract to determine whether they believed the sample output to be an expert human translationor a machine translation. | |
| their logistics system to place a supply | or | information request . The request is passed | #843 Using LCS-Marine, tactical personnel can converse with their logistics system to place a supply or information request. | |
| the status of a <term> request </term> changes | or | when a <term> request </term> is complete . | #880 Requestors can also instruct the system to notify them when the status of a request changes or when a request is complete. | |
| measure(ment),19-3-H01-1058,bq | performance </term> ( typically , <term> word | or | semantic error rate </term> ) from a list | #1090 The oracle knows the reference word string and selects the word string with the best performance (typically, word or semantic error rate) from a list of word strings, where each word string has been obtained by using a different LM. |
| </term> using a <term> neural network </term> | or | a <term> decision tree </term> . The method | #1167 We suggest a method that mimics the behavior of the oracle using a neural networkor a decision tree. | |
| decision of how to combine them into one | or | more <term> sentences </term> . In this paper | #1331 Sentence planning is a set of inter-related but distinct tasks, one of which is sentence scoping, i.e. the choice of syntactic structure for elementary speech acts and the decision of how to combine them into one or more sentences. | |
| language </term> , current systems use manual | or | semi-automatic methods to collect <term> | #1770 While paraphrasing is critical both for interpretation and generation of natural language, current systems use manual or semi-automatic methods to collect paraphrases. | |
| tech,32-1-P01-1056,bq | compete with <term> hand-crafted template-based | or | rule-based approaches </term> . In this paper | #2046 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. |
| 2.284 <term> SRHs </term> as either coherent | or | incoherent ( given a <term> baseline </term> | #2528 An evaluation of our system against the annotated data shows that, it successfully classifies 73.2% in a German corpus of 2.284 SRHs as either coherent or incoherent (given a baseline of 54.55%). | |
| only requires a few <term> common noun </term> | or | <term> pronoun </term><term> seeds </term> that | #3313 This approach only requires a few common nounor pronoun seeds that correspond to the concept for the targeted NE, e.g. he/she/man/woman for PERSON NE. | |
| <term> user </term> 's <term> knowledge </term> | or | typical kinds of <term> users </term> , the | #4307 Unlike previous studies that focus on user's knowledgeor typical kinds of users, the user model we propose is more comprehensive. | |
| to adapt to a desired <term> domain </term> | or | <term> genre </term> . Examples and results | #4507 Monolingual, unannotated text can be used to further improve the stemmer by allowing it to adapt to a desired domainor genre. | |
| * - stem-suffix * </term> ( * denotes zero | or | more occurrences of a <term> morpheme </term> | #4630 We approximate Arabic's rich morphology by a model that a word consists of a sequence of morphemes in the pattern prefix*-stem-suffix* (* denotes zero or more occurrences of a morpheme). | |
| been comparable across <term> corpora </term> | or | <term> lexicons </term> . Observing that the | #5555 Along the way, we present the first comprehensive comparison of unsupervised methods for part-of-speech tagging, noting that published results to date have not been comparable across corporaor lexicons. | |
| similarity </term> between <term> words </term> | or | use <term> lexical affinity </term> to create | #6366 In comparison with previous models, which either use arbitrary windows to compute similarity between wordsor use lexical affinity to create sequential models, in this paper we focus on models intended to capture the co-occurrence patterns of any pair of words or phrases at any distance in the corpus. | |
| patterns </term> of any pair of <term> words </term> | or | <term> phrases </term> at any distance in the | #6393 In comparison with previous models, which either use arbitrary windows to compute similarity between words or use lexical affinity to create sequential models, in this paper we focus on models intended to capture the co-occurrence patterns of any pair of wordsor phrases at any distance in the corpus. | |
| sources </term> , such as the <term> Web </term> | or | <term> newswire documents </term> . Despite | #6770 Information extraction techniques automatically create structured databases from unstructured data sources, such as the Webor newswire documents. | |
| Given a particular <term> concept </term> , | or | <term> word sense </term> , a <term> topic signature | #6910 Given a particular concept, or word sense, a topic signature is a set of words that tend to co-occur with it. | |
| systems </term> , such as <term> BLEU </term> | or | <term> NIST </term> , are now well established | #7692 Automatic evaluation metrics for Machine Translation (MT) systems, such as BLEUor NIST, are now well established. | |
| pairs </term> like <term> English-Chinese </term> | or | <term> English-Japanese </term> , because of | #7714 Yet, they are scarcely used for the assessment of language pairs like English-Chineseor English-Japanese, because of the word segmentation problem. |
