Báo cáo khoa học: "Finding content-bearing terms using term similarities" pot

... capabilities as opposed to generational capabilities: the expansion of search terms to in- clude impossible strings is not a problem in terms of result. Looking at the immediate context overlaps re- turned ... the fact that when two terms are in a common entail- ment relation, it should be possible to sub- stitute one for the other in their most fre- quent surface contexts. Using the...

Ngày tải lên: 08/03/2014, 21:20

... inference method for determining cognate assignments under fixed parameters ϕ. We are given a set of languages and a list of words in each language, and our objec- tive is to determine which words ... in worst-case cubic time (using a generalization of the Floyd- Warshall algorithm). For acyclic or feed-forward transducers, this time can be improved dramati- cally by using a generalization...

Ngày tải lên: 17/03/2014, 00:20

... Consequently, we do not compare our performance with deterministic systems. Ponzetto (2010) extracts metadata from Wikipedia for supervised CoRe. Using such additional resources in our unsupervised ... entities that belong to the same named entity (NE) class. Determining common membership in an NE class like pers on is an easier task than determining coreference of two NEs. 3 System Archite...

Ngày tải lên: 07/03/2014, 22:20

... constants and t i is arbi- trary threshold. Using equation (1), we can estimate a similarity between the context of a target word and prototype context, and can determine the sense of a target word by ... in the training and test corpus of SENSEVAL-1, we make a parsing using Apple Pie Parser (Sekine, 1996) and additional vertices using some rules automati- cally. If the resulted parsing...

Ngày tải lên: 08/03/2014, 04:22

... example, in booking a flight in an automated travel agent system, the system state is described in terms of how close the agent is to being able to book the flight. Such systems suffer from a principal ... Institute Carnegie Mellon University Pittsburgh, PA 15213 Abstract Spoken dialogue managers have benefited from using stochastic planners such as Markov Decision Processes (MDPs). How- eve...

Ngày tải lên: 08/03/2014, 05:20

... Singapore, 4 August 2009. c 2009 ACL and AFNLP Finding Hedges by Chasing Weasels: Hedge Detection Using Wikipedia Tags and Shallow Linguistic Features Viola Ganter and Michael Strube EML Research ... us- ing corpus statistics and syntactic pat- terns. We take Wikipedia as an already annotated corpus using its tagged weasel words which mark sentences and phrases as non-factual. We evaluat...

Ngày tải lên: 20/02/2014, 09:20

... the two synonym extraction approaches based on dis- tributional similarity: one using syntactic context and one using translational context based on word alignment and the combination of both. ... that contains only nouns 3 We have determined the optimum in F-score for the alignment-based method, the syntax-based method and the combination independently by using a development set of 100...

Ngày tải lên: 20/02/2014, 12:20

... and method. • TRG: The models were trained using only the real-error corpus (baseline). • SRC: Trained using only the pseudo-error corpus. • ALL: Trained using the real-error and pseudo- error corpora ... task is hindered by the difficulty of collecting large error cor- pora. We tackle this problem by using pseudo- error sentences generated automatically. Fur- thermore, we apply domain...

Ngày tải lên: 19/02/2014, 19:20

... the shortest paths between any given word and the words ’good’ and ’bad’ to determine word polar- ity. They report that using shortest paths could be very noisy. For example. ’good’ and ’bad’ them- selves ... relat- edness graph. We used 10-fold cross validation for all tests. We evaluate our results in terms of accuracy. Statistical significance was tested us- ing a 2-tailed paired t-test...

Ngày tải lên: 20/02/2014, 04:20

... a system that creates a headline for an English news- paper story using linguistically-motivated heuris- tics to choose a potential headline. Jin and Hauptmann (2002) proposed a probabilistic ... “ and he wrote it ” is compared with the word “ﺐﺘﻛ” “ he wrote ” using the EWM method the resulting score will be 0, but when using the CCC method it will be 0.667. The CCC method comes f...

Ngày tải lên: 20/02/2014, 05:20