Báo cáo khoa học: "Generating Entailment Rules from FrameNet" pot

... ‘sell ⇒ get’. 3.3 Generating Entailment Rules The final step in the FRED algorithm generates lexical syntactic entailment rules from the ex- tracted templates and lexical entailment relations. For ... gen- erating entailment rules from FrameNet, called FRED (FrameNet Entailment- rule Derivation), which operates in three steps: a) extracting tem- plates for each LU; b) detect...

Ngày tải lên: 17/03/2014, 00:20

... 4 Acquiring Transfer Rules This section describes the procedure for deriving transfer rules from aligned parse trees. First, the best-scoring alignment is recovered from the Children-Pairing ... scoring alignment, we acquire transfer rules from that alignment. When more than one pair of trees tie for the highest score, we acquire transfer rules from the set of pairs of a...

Ngày tải lên: 23/03/2014, 19:20

... perfection of the trained rules; rather, we require that rules reach a certain level of success. For rules that disambiguate the first element (except the default disambiguation rules) , we require ... parser rules can refer only to limited aspects of the current parser state. Rules can mention the grammatical category of the constituents in the buffer and the current incomp...

Ngày tải lên: 31/03/2014, 18:20

... <object,action,scene> triples predicted from the visual characteristics of the image to find potential captions. Ordonez et al. (2011) use global image matching with local re- ordering from a much larger set of ... natural- sounding descriptions from computer vision de- tections. This commonality is our starting point: We aim to design a system capable of producing natural-sounding...

Ngày tải lên: 31/03/2014, 21:20

... 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

... 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 ... sets of continuous and discrete variables by using set of splitting rules, stopping rules, and prediction rules. These rules affect the internal nodes, subtree height, and terminal...

Ngày tải lên: 08/03/2014, 07:20

... 2004) to extract key- words from tweets to tag users. Topic discovery from Twitter is also related to our work (Ramage et al., 2010), but we further extract keyphrases from each topic for summarizing ... applicable to Twitter because it does not make sense to ex- tract keyphrases from a single tweet, and if we ex- tract keyphrases from a whole tweet collection we will mix a diverse...

Ngày tải lên: 17/03/2014, 00:20

... of the objects the speaker is referring to. From the generation perspective, this means that, starting from the set of objects to be described and from the properties known to hold of these objects by ... fol- lowing example from (Stone and Webber, 1998) il- lustrates, the information used to uniquely identify some object need not be localised to a definite de- scription. (2) Remove th...

Ngày tải lên: 17/03/2014, 08:20

... also identify related songs from the internet, including: other songs from the same al- bum, popular songs of the artist and popular songs of related artists, as obtained from Yahoo Music. c) The ... base form from the original verb or noun, so that YAG can generate grammatical sentences. Figure 5 shows the regenerated review from Fig- ure 1. YAG regenerates as many f-sentences fro...

Ngày tải lên: 20/02/2014, 04:20

... our general corpora to produce three different models: GSLCLM from the GSLC corpus, NewsLM from the newspaper corpus and DomNewsLM from the domain adapted newspaper Corpus. 3.1 Interpolating the ... speech recognition grammar compiled from the same GF interpretation grammar. The results show a relative Word Error Rate (WER) reduction of 37% for the SLM derived from the interpretatio...

Ngày tải lên: 22/02/2014, 02:20