This paper proposes how to automatically identify Korean comparative sentences from text documents. This paper first investigates many comparative sentences referring to previous studies and then defines a set of comparative keywords from them. A sentence which contains one or more elements of the keyword set is called a comparative-sentence candidate. Finally, we use machine learning techniques to eliminate non-comparative sentences from the candidates. As a result, we achieved significant performance, an F1-score of 88.54%, in our experiments using various web documents. ...
Th=s report describes Paul, a computer text generation system desig~ed LO create cohesive text through the use o| lexlcal substitutions. Specihcally, Ihas system is designed Io determmistically choose between provluminahzat0on, superordinate suhstntut0on, and dehmte noun phrase reiterabon. The system identities a strength el antecedence recovery for each of the lex~cal subshtutions, and matches them against the strength el potenfml antecedence of each element m the text to select the proper substitutions for these elements. ...
Albert Einstein once said everything should be made as simple as possible, but not simpler.
Einstein could have been talking about programming languages, as the landscape is strewn
with “simple” languages that, several versions later, have 500-page reference manuals!
The truth is that we expect a lot of our programming languages.We demand support for en-
capsulation and abstraction, type checking and exception handling, polymorphism and more.
The ultrasonic transducer behaves as a ‘speaker’ in send mode (from 40 to 50
kHz). The electronics of the ultrasonic transducer produces electrical pulses
to set the piezoceramic element in motion (conversion of electrical energy to
mechanical energy). The piezoceramic element is located on the inside of the
outer diaphragm. The outer diaphragm vibrates in line with the resonance
frequency and produces ultrasonic waves.
The short pulse sequences hit an obstacle and are bounced back (reflected).
A robust dictionary of semantic frames is an essential element of natural language understanding systems that use ontologies. However, creating lexical resources that accurately capture semantic representations en masse is a persistent problem. Where the sheer amount of content makes hand creation inefficient, computerized approaches often suffer from over generality and difficulty with sense disambiguation.
Semantic relations between text concepts denote the core elements of lexical semantics. This paper presents a model for the automatic detection of INTENTION semantic relation. Our approach ﬁrst identiﬁes the syntactic patterns that encode intentions, then we select syntactic and semantic features for a SVM learning classiﬁer. In conclusion, we discuss the application of INTENTION relations to Q&A.
DTG are designed to share some of the advantages of TAG while overcoming some of its limitations. DTG involve two composition operations called subsertion and sister-adjunction. The most distinctive feature of DTG is that, unlike TAG, there is complete uniformity in the way that the two DTG operations relate lexical items: subsertion always corresponds to complementation and sister-adjunction to modification.
We exploit the resources in the Arabic Treebank (ATB) and Arabic Gigaword (AG) to determine the best features for the novel task of automatically creating lexical semantic verb classes for Modern Standard Arabic (MSA). The verbs are classiﬁed into groups that share semantic elements of meaning as they exhibit similar syntactic behavior. The results of the clustering experiments are compared with a gold standard set of classes, which is approximated by using the noisy English translations provided in the ATB to create Levin-like classes for MSA.
This study employs a knowledge intensive corpus analysis to identify the elements of the communicative context which can be used to determine the appropriate lexical and grammatical form of instructional texts. IMAGENE, an instructional text generation system based on this analysis: is presented, particularly with reference to its expression of precondition relations. INTRODUCTION Technical writers routinely employ a range of forms of expression for precondition expressions in instructional text.
This paper investigates two elements of Maximum Entropy tagging: the use of a correction feature in the Generalised Iterative Scaling (Gis) estimation algorithm, and techniques for model smoothing. We show analytically and empirically that the correction feature, assumed to be required for the correctness of GIS, is unnecessary. We also explore the use of a Gaussian prior and a simple cutoff for smoothing. The experiments are performed with two tagsets: the standard Penn Treebank POS tagset and the larger set of lexical types from Combinatory Categorial Grammar. ...