Báo cáo khoa học: "Automatic Construction of Frame Representations for Spont aneous Speech in Unrestricted Domains" docx

... Automatic Construction of Frame Representations for Spontaneous Speech in Unrestricted Domains Klaus Zechner Language Technologies Institute Carnegie Mellon University 5000 Forbes Avenue ... able to build shallow semantic representations for spontaneous speech in unrestricted domains, without the neces- sity of extensive knowledge engineering. Initial experi...

Ngày tải lên: 23/03/2014, 19:20

... method consists of the following three steps: 1. Preprocessing Before extracting opinion sentences, HTML documents are preprocessed. This process involves separating texts form HTML tags, recognizing sentence ... called indicators. Indicators for positive sentences are called positive indicators. ’Pros’ is an example of positive indi- cator. Similarly, indicators for negative sentence...

Ngày tải lên: 20/02/2014, 12:20

... not included in the final tree. In practice, we cannot follow exactly that algorithm, because maintaining a list of the cosines between every pair of nodes requires a tremendous amount of ... "product" and containing words for things, the other labeled "analyst" and con- taining names of people. We would like to instead label this node something like &q...

Ngày tải lên: 08/03/2014, 06:20

... occur during parsing or mapping, are solved by selecting the patterns that minimize the semantic distance between the input sentence and the source examples (real examples in the training corpus). 3.3 ... mean number of word-link com- binations in which word sequences of the source and the target contain word links only between their constituents (cross-links are allowed). If a biling...

Ngày tải lên: 08/03/2014, 21:20

... replacement since their affixing of words (inflection of words) can include both pre- fixing, infixing and suffixing. Therefore we cre- ated a trainable lemmatizer that handles pre- and infixes in addition ... the full form. The training process terminates when the full forms in all pairs in the training set are trans- formed to their corresponding lemmas. After training, the d...

Ngày tải lên: 23/03/2014, 16:21

... hierarchical index of type {topic→information} based on this automat- ically generated model for each topic in the topic taxonomy. An entry of this index contains topic specific information viz. ... questions, etc. The {topic→information} index requires iden- tification of the topic for each call to make use of information available in the model. Below we show examples of the...

Ngày tải lên: 31/03/2014, 01:20

... distinguishing be- tween convention of means and convention of forms for indirect speech acts; the former covers Searle's analysis in terms of felicity conditions and reasons for performing ... application areas for NLIs. Indirect speech acts Indirect speech acts (Searle, 1975) have been one of the active areas of research in computa- tional linguistics....

Ngày tải lên: 18/03/2014, 02:20

... enumerating an in nite number of models is of course infeasible. For this reason, we will now transfer the concept of solved forms from dominance constraints to RMRS. An RMRS in solved form is ... phrase ques- tions of practical grammar engineering in well- defined formal terms. For instance, one crucial is- sue in developing a hybrid system that combines or compares the out...

Ngày tải lên: 31/03/2014, 20:20

... USA tomuro@cs.depaul.edu Dina Demner-Fushman National Library of Medicine Bethesda, MD USA ddemner@mail.nih.gov Abstract Detecting the linguistic scope of negated and speculated information in text is an impor- tant Information ... and corpora. 1 Motivation Information Extraction (IE) systems often face the problem of distinguishing between affirmed, negated, and speculative informatio...

Ngày tải lên: 20/02/2014, 04:20

... level of a single pair (T, H) (Sec. 4.1). The anchoring process gives the direct possibility of 403 implementing an inter-pair similarity that can be used as a baseline approach or in combination ... correct marking of tree nodes with placeholders; and, (3) the pruning of irrelevant information in large syntactic trees. 5.1 Controlling the computational cost The computational cost...

Ngày tải lên: 20/02/2014, 12:20