Báo cáo khoa học: "TOWARDS A SELF-EXTENDING PARSER" docx

... interesting Ideas and techniques, these techniques do not fully extend to • domain as complex as natural language analysis. Rather than attempting the formidable task of creating a language learning ... of each exemplar. Learning by near-miss analysis. Winston [2] takes full advantage of this technique, it may be usefully applied to a natural language system that can Interactlvei...

Ngày tải lên: 31/03/2014, 17:20

... su- perlatives have mainly focused on particular se- mantic properties that may only rarely occur in natural language (Szabolcsi, 1986; Heim, 1999). My goal is a comprehensive computational treatment ... IS -A relation that holds between target and comparison set (cf. Relation 2 in Section 3). They 68 are a good initial focus for a computational ap- proach because both their targe...

Ngày tải lên: 20/02/2014, 12:20

... representation languages as FRL, KLONE and KIIL. Frames have played dual functions. They have been used as a way to organize the inferences, and also as a structural representation of what is ... ACCOUNTS. FOR EACH ACCOUNT THE BANK WANTS A LIST SHOWING THE BALANCE AT THE BEGINNING OF THE PERIOD, THE NUMBER OF DEPOSITS AND WITHDRAWALS, AND THE FINAL BALANCE. THE ACCOUNTS AND TRAN...

Ngày tải lên: 21/02/2014, 20:20

... syntactic analysis of substantial fragments of natural language. These developments also demonstrate that if natural language processing systems are to be able to handle the grammatical and ... to domain knowledge already encoded in the knowledge base of a limited domain natural language application such as a database query system. Given a hand-coded hierarchical organization of...

Ngày tải lên: 22/02/2014, 09:20

... (;ci'many lhnaih !,1'~!! at I)! ll)iBM I.BITNI'71' ABSTRACT The desire to construct robust and portable na- tural language systems has led to research on how a core vocabulary ... here allows for a balanced extension of this very smaU core. The list//3 was chosen as the statistical core vocabulary serving as a base for applying se- mantic criteria, becat, s...

Ngày tải lên: 22/02/2014, 10:20

... best classification tasks in terms of the Silhou- ette measure are the 3-way and 15-way classifica- tions. The baseline is calculated, for each task, as the average value of the Adjusted Rand measure ... attachment or grammatical function of the constituents, we have to take into account that the extraction is an approximation. There are various phenomena that can lead us to an erroneous extrac...

Ngày tải lên: 08/03/2014, 04:22

... word-ending, ambiguous among nomi- native and accusative singular masculine- -inanimate, and nominative singular masculine-animate, thus representing the adjectival "normal form,'), ... natural language understanding, namely the project of man-machine communication called TIBAQ (Text-and-Inference Based Answering of Questions, cf. (Haji~ov@ and Sgall, 1981)) with no pre-arr...

Ngày tải lên: 09/03/2014, 01:20

... project treat anno- tation data in XML from any source as separate annotation layers, provided the text nodes in each layer contain the same base data. The base data is extracted and kept in a text ... annotated text corpora. While the XML standard specifies a data model and serialization format for XML, a semantics is largely left to be defined for a particular ap- plication. Many data...

Ngày tải lên: 17/03/2014, 04:20

... Towards a Resource for Lexical Semantics: A Large German Corpus with Extensive Semantic Annotation Katrin Erk and Andrea Kowalski and Sebastian Pad ´ o and Manfred Pinkal Department of Computational ... implemented that will pro- vide a graphical interface for the annotation. It will display the syntactic structure and allow for a graph- ical manipulation of semantic frame trees, in...

Ngày tải lên: 17/03/2014, 06:20

... trans- lation memory and a statistical-based translation model. Our results show that an automatically derived transla- tion memory can be used within a sta- tistical framework to often find trans- lations ... phrases; new trans- lations are produced by optimally partitioning the input into phrases that match examples from the TMEM (Maruyana and Watanabe, 1992), or by finding all partial ma...

Ngày tải lên: 17/03/2014, 07:20