Báo cáo khoa học: "Learning High-Level Planning from Text" pot

... labeling of transcriptions. To this end, we selected potential boundary predictors based upon hypotheses derived from our own observa- tions and from previous theoretical and practi- cal studies ... by distance of poten- tial boundary site from end of utterance (at). The second split in the new tree does rely upon tem- poral distance this time, distance of boundary site from...

Ngày tải lên: 08/03/2014, 07:20

... approach human per- formance. This research is potentially very important in applications in which the time course of events is to be extracted from news. For example, whether two events overlap ... instances), from the TimeBank corpus annotated in TimeML (Pustejovky et al., 2003). The non- WSJ articles (mainly political and disaster news) include both print and broadcast news that...

Ngày tải lên: 20/02/2014, 12:20

... languages from non-parallel multilingual corpora in an unsupervised fashion. For this purpose, we assume a generative model for multilingual corpora, where each sentence is generated from a language ... borrowing from nearby languages, and 3) the innate abilities of humans (Chomsky, 1965). We assume hidden commonalities in syntax across languages, and try to extract a common grammar fr...

Ngày tải lên: 07/03/2014, 22:20

... null label is NO-REL. train/test split from Table 1 and the feature sets: Syntactic The syntactic features from Section 4. Semantic The semantic features from Section 4. All Both syntactic and ... relations and 77.8% on causal re- lations. We trained machine learning mod- els using features derived from WordNet and the Google N-gram corpus, and they out- performed a variety of baselin...

Ngày tải lên: 08/03/2014, 01:20

... both precision and recall. We cast semantic category acquisition from search logs as the task of learning labeled in- stances from few labeled seeds. To our knowledge this is the first study that ... different from ours. An- other line of new research is to combine various re- sources such as web documents with search query logs (Pas¸ca and Durme, 2008; Talukdar et al., 2008). We differ...

Ngày tải lên: 08/03/2014, 01:20

Ngày tải lên: 22/02/2014, 03:20

... reactions to major events. Bursty top- ics from microblogs reveal what events have attracted the most online attention. Although bursty event detection from text streams has been studied before, ... bursty topics from mi- croblogs therefore can help us identify the most pop- ular events that have drawn the public’s attention. In this paper, we study the problem of finding bursty topics...

Ngày tải lên: 07/03/2014, 18:20

... discourse cues such as register change, focus shift, and cue words. From a computa- tional viewpoint, deducing textual topic structure from lexical connectivity alone is appealing, both because it ... description of which he writes (pp 179-180): Our data , suggest that as a speaker moves from focus to focus (or from thought to thought) there are certain points at which there may...

Ngày tải lên: 08/03/2014, 07:20

... possible hypotheses of latent vectors for the definition of bank#n#1 2 Learning Latent Semantics of Definitions 2.1 Intuition Given only a few observed words in a definition, there are many hypotheses ... words. Therefore, missing words can be used to prune the hypotheses that are also highly related to the missing words. Consider the hypotheses of latent vectors in ta- ble 1 for bank#n#1. Assum...

Ngày tải lên: 19/02/2014, 19:20

... comparative sentences from text documents. This paper first investigates many comparative sentences referring to pre- vious studies and then defines a set of compar- ative keywords from them. A sentence ... to eliminate non- comparative sentences only from comparative sentence candidates with a CKL2 keyword. 4 Eliminating Non-comparative Sen- tences from the Candidates 3 A...

Ngày tải lên: 20/02/2014, 09:20