Source PaperYearLineSentence
P10-1123 2010 38
(Li et al, 2009; Dali et al, 2009)
P10-1139 2010 208
Usually the convergence of the iteration algorithm is achieved when the difference between the scores computed at two successive iterations for any nodes falls below a given threshold (Wan et al, 2008; Li et al, 2009; Erkan and Radev, 2004)
P10-1125 2010 71
A graph based algorithm is presented to answeropinion questions (Li et al, 2009)
C10-1087 2010 31
Yet, such applications typicallyonly handle a narrow aspect of discourse, address ing coreference by term substitution (Dali et al, 2009; Li et al, 2009)
D12-1013 2012 8
Sentiment classification is the task of identifying the sentiment polarity (e.g., positive or negative) of *1 Corresponding author a natural language text towards a given topic (Pang et al2002; Turney, 2002) and has become the core component of many important applications in opinion analysis (Cui et al2006; Li et al2009; Lloret et al2009; Zhang and Ye, 2008)
D12-1034 2012 318
Sentimentanalysis has been used before on the slightly un usual task of opinion question answering, where thesystem is asked to answer subjective opinion ques tions (Stoyanov et al2005; Dang, 2008; Li et al2009)
D12-1036 2012 292
For the topic of answer generation in opinion-QA, Li et al2009) formulated it as a sentence rankingtask
D12-1036 2012 261
4.3.1 Comparisons to the State-of-the-ArtsWe compared our multi-criteria optimization ap proach against two state-of-the-arts methods: a) the 398 method presented in Li et al2009), which selects some retrieved sentences to generate the answers based on a graph-based algorithm; b) the methodproposed by Lloret et al2011) that forms the an swers by re-ranking the retrieved sentences
P14-1049 2014 77
Graph models have been proven successful in many NLP applications, especially in representing the link relationships between words or sen tences (Wan and Yang, 2008; Li et al, 2009)