... make a difference in the adequacy of the parsings of natural- language sentences will be alterations of the format itself in terms of in- creasing the degree of context-sensitivity. This in effect ... pertinent in the case of a grammar having sufficient context-sensitivity to serve the needs of syn- tactic recognition adequate for the machine translation of natural languages. a) Since the ... times of the neces- sary location information, such as sentence boundaries, word positions in the sentence, search distances, etc. Received July 15, 1965 AUTOMATIC PARSING OFNATURAL LANGUAGES...
... EVALUATIONOFNATURALLANGUAGE INTERFACES TO DATABASE SYSTEMS: A PANEL DISCUSSION Norman K. Sondheimer, Chair Sperry Univac Blue Bell, PA For a naturallanguage access to ... occasionally were even informal evaluations of systems conducted. Recently, this has begun to change. In the last several years, many of the current generation ofnaturallanguage access to database ... IIl. On the basis of these evaluations, what should the future look like for natural language access to database? Under this point, what niches look most promising for natural language interfaces?...
... chal-lenge is the evaluation: manual evaluation is adifficult, time-consuming process and not ap-plicable within efficient development of sys-tems. Automaticevaluation requires a cor-pus of questions ... Y are known enemies.The problem of several possible answers and, inconsequence, automaticevaluation has been tackledfor years within another field of study: automatic summarisation (Hori et ... slow a rate of data acquisition. Therefore it is of- ten necessary to raise the reward and rely on efficient automatic validation of the data.We have looked into the answer agreement of the workers...
... evaluating the output oflanguage tech-nology applications—MT, natural language generation, summarisation automatic eval-uation techniques generally conflate mea-surement of faithfulness to source ... grammar, rhythm and flow,appropriateness of tone, and several other specificcharacteristics of good text.In terms ofautomatic evaluation, we are not aware of any technique that measures only fluency ... generator.In Proceedings of the International NaturalLanguage Genera-tion Conference (INLG) 2002, pages 17–24.Shimei Pan and James Shaw. 2004. Segue: A hybrid case-based surface naturallanguage generator....
... present the evaluations of ROUGE-L, ROUGE-S, and compare their per-formance with other automaticevaluation meas-ures. 5 Evaluations One of the goals of developing automatic evalua-tion ... for MT Research. In Proceedings of the 2nd International Conference on Language Resources and Evaluation, Athens, Greece. NIST. 2002. AutomaticEvaluationof Machine Translation Quality using ... Proceedings of COLING-92, Nantes, France. Thompson, H. S. 1991. AutomaticEvaluationof Translation Quality: Outline of Methodology and Report on Pilot Experiment. In Proceedings of the Evaluator’s...
... Commercialization ofNaturalLanguage Processing Technology. Communications of the ACM, in press. Grishman R., Macleod C. and Wolf S. (1993) The Comlex syntax project. Proceedings of the ARPA Human Language ... problems in a multi-user environment. The task of a developer of a particular naturallanguage application is greatly simplified by the presence of these resources. In the future we plan to ... and/or run time. We discuss issues of achieving compatibility between these disparate resources. 1 NL Engine Natural language processing in the Unisys natural language understanding (NLU) system...
... depiction of the first kind of accommodation accommodation A A A l 2 1 ¢g Figure 2: Schematic depiction of the second kind of accommodation Ex. 11 Go into the other room to get the urn of coffee. ... complex facets of the problem of mapping NaturalLanguage in- structions onto an agent's behavior. However, an aspect that no one has really considered is computing the ob- jects of the intentions ... UNDERSTANDING NATURAL LANGUAGE INSTRUCTIONS: THE CASE OF PURPOSE CLAUSES Barbara Di Eugenio * Department of Computer and Information Science University of Pennsylvania Philadelphia,...
... Rrlba ,,m Press, Hlllsdale, NJ. 57 The Use of Ooject-Specl flc Knowledge in Natural Language Processing Mark H. Bursteln Department of Computer Science, Yale University 1. INTRODUCTION ... research has been on the development of processes which utillze Information provided by Object Primitives to facilitate the "comprehension" ofnaturallanguage texts by computer. That ... introduction of stereotyplc knowledge of objects into the conceptual analysis of text. By encoding information in OP descriptions, we were able to increase the interpretive power of the analyzer...
... " ;natural language& quot; is the result of a compromise be- tween these two opposing extremes. If we had same better understanding of the cognitive dynamics that shape and evolve natural language, ... ideal. Naturallanguage is wordy (redun- dant) and imprecise. Most b,*m,m groups who have a need to communicate quickly and accurately tend to develop a rather well specified subset ofnaturallanguage ... NATURALLANGUAGE AND COMPUTER INTEBFACE DESIGN MURRAY TUROFF DEPARTMENT OF COMPU%'z~ AND IiVFORMATION SCIENCE IIEW JERSEY INSTITUTE OF TECHNOLOGY SOME ICONOCLASTIC...
... corpus analysis of cue phrases. 1 Introduction Researchers ofnaturallanguage have repeatedly ac- knowledged that texts are not just a sequence of words nor even a sequence of clauses and ... derive automatically have on the accuracy of other natural language processing tasks, such as anaphora res- olution, intention recognition, or text summarization. In this paper, we describe evaluations ... rhetorical parsing, sum- marization, and generation ofnaturallanguage texts. Ph.D. thesis, Department of Computer Science, Uni- versity of Toronto, Forthcoming. Martin, James R. 1992. English...
... Because of the high-dimensional nature ofnatural language, it is often easy to generate an extremely large number of features. The challenge of parameter estimation is to find a combination of ... Performance of the application is measured in terms of character error 2 The result of ME/L2 is better than that reported in Andrew and Gao (2007) due to the use of the variant of L2-regularized ... pre-vious work (Ratnaparkhi, 1996), we assume that the tag of a word is independent of the tags of all pre-ceding words given the tags of the previous two words (i.e., =2 in the equation above)....
... comparesa number of statistical and machinelearning techniques for ordering se-quences of adjectives in the context of a naturallanguage generation system.1 The problemThe question of robustness ... order of prenominal adjectives in English.2 Word bigram modelThe problem of generating ordered sequences of adjectives is an instance of the more general prob-lem of selecting among a number of ... whichtakes values V as the weighted sum of the entropy of each of the values V:H(Df) =∑vi∈VH(Df=vi)|Df=vi||D|Here H(Df=vi) is the entropy of subset of the in-stance base which has...
... and Strzalkowski, T Evaluat- ing Syntax Performance of Parser/Grammars of English. Proceedings ofNaturalLanguage Processing Systems Evaluation Workshop, Berkeley, California, 1991. 5. Hopcraft, ... consists of the following 4 elements: • Selection of application domain. • Development of a manually-bracketed corpus (tree- bank) of the domain. • Creation of a grammar with a large coverage of ... broad but not unrestricted range of sentence types and the availability of large corpora of computer manuals. We amassed a corpus of 40 million words, consisting of several hundred computer manuals....
... Proceedings, Speech and NaturalLanguage Workshop, pp. 230-236, June 1990 3. Chitrao, and R. Grishman, "Statistical Parsing of Messages," Proceedings, Speech and Natural Language Workshop, ... states of each of the two models are unseen and must be inferred from the words. The problem oflanguage understanding, then, is to recover the most likely meaning structure given a sequence of ... techniques. Empirical results, including the results of an ARPA 31 HIDDEN UNDERSTANDING MODELS OF NATURALLANGUAGE Scott Miller College of Computer Science Northeastern University Boston,...