Báo cáo khoa học: "Automatic Acquisition of Script Knowledge from a Text Collection" docx

... first explain what we mean by 'action', 'pair of actions', and 'sequence of actions' in this paper. In this work, an action is defined as a tuple of a transitive ... for au- tomatic acquisition of script knowledge from a Japanese text collection. Because script knowl- edge represents a typical sequence of actions formed in a partic...

Ngày tải lên: 31/03/2014, 20:20

... AUTOMATIC ACQUISITION OF SUBCATEGORIZATION FRAMES FROM UNTAGGED TEXT Michael R. Brent MIT AI Lab 545 Technology Square Cambridge, Massachusetts 02139 michael@ai.mit.edu ABSTRACT This ... immediately to the right of a main verb. Adverbs and adverbial phrases (including days and dates) are ignored for the pur- poses of case adjacency. A noun-phrase that sat- isfies th...

Ngày tải lên: 20/02/2014, 21:20

... practical, preferable, probable, ridiculous, unaware, uncertain and unclear. 617 et al., 1998) occur. In our pattern matching language a pattern is a disjunction of sets of partially instantiated ... recall rate. A new tool for linguistic annotation of SCFs in corpus data is also introduced which can considerably alleviate the pro- cess of obtaining training and test data for su...

Ngày tải lên: 08/03/2014, 04:22

... easier to validate existing qualia structures than to create them from scratch, which already corroborates the usefulness of our automatic approach. The qualia structure for each of the 10 randomly ... the principled idea of learning ranked qualia structures. In fact, a ranking of qualia elements is useful as it helps to determine a cut-off point and as a reliabil- ity indicat...

Ngày tải lên: 08/03/2014, 02:21

... Tagged Data Set, manually pro- duced by Rada Mihalcea and Li Yang (Mihalcea, 2003), from text drawn from the British National Corpus. We calculated a ‘supervised’ baseline from the annotated data by ... Topic signatures can be useful in a number of Natural Language Process- ing (NLP) applications, such as Word Sense Disambiguation (WSD) and Text Summarisation. Our method takes...

Ngày tải lên: 08/03/2014, 04:22

... learning approach, which is more attractive because it is trainable and adaptable, and subsequently the porting of a machine learning sys- tem to another domain is much easier than that of a rule-based ... procedures and NE instances are finally annotated with the appropriate NE categories. This automatically tagged corpus may have lower quality than the manually tagged ones but its si...

Ngày tải lên: 08/03/2014, 04:22

... which is a key part of many natural language applications such as speech recognition and statistical ma- chine translation. In this paper, we present a language modeling based on a kind of simple ... associate a priori prob- ability to a sentence. It is a key part of many natural language applications such as speech recognition and statistical machine translation. Pr...

Ngày tải lên: 08/03/2014, 05:21

... learning a foreign language. A subcategorization frame is a statement of what types of syntactic arguments a verb (or ad- jective) takes, such as objects, infinitives, that- clauses, participial ... manuals. 3. Hand-coded lists are expensive to make, and in- variably incomplete. 4. A subcategorization dictionary obtained auto- matically from corpora can be updated quic...

Ngày tải lên: 23/03/2014, 20:20

... an object, always takes an agent, always has a pa- tient, and always has the patient serving as ob- ject. The learner will also assume that em break never takes a location, a dative, etc. ... eral area of WIPE, CLEAR and SPRAY/LOAD, but the optional locative, and the fact that the theme can be marked with em with select for the class of SPRAY/LOAD, verbs of physical contac...

Ngày tải lên: 31/03/2014, 18:20

... Firstly, we pre- pared 482 location-name/and local-product pairs as seeds for the bootstrapping. These pairs were obtained automatically from a 'Web Japanese N- gram' database 3 provided ... 482 pairs. Then automatically create 200 tagged sentences, to which 'location' and 'product' tags are assigned. 2. Prepare another 200 sentences that contain only...

Ngày tải lên: 08/03/2014, 01:20