Abstract | ||
---|---|---|
We introduce ConnotationWordNet, a connotation lexicon over the network of words in conjunction with senses. We formulate the lexicon induction problem as collective inference over pairwise-Markov Random Fields, and present a loopy belief propagation algorithm for inference. The key aspect of our method is that it is the first unified approach that assigns the polarity of both word- and sense-level connotations, exploiting the innate bipartite graph structure encoded in WordNet. We present comprehensive evaluation to demonstrate the quality and utility of the resulting lexicon in comparison to existing connotation and sentiment lexicons. |
Year | Venue | Field |
---|---|---|
2014 | PROCEEDINGS OF THE 52ND ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, VOL 1 | Problem of induction,Random field,Inference,Computer science,Connotation,Bipartite graph,Lexicon,Artificial intelligence,Natural language processing,WordNet,Belief propagation |
DocType | Volume | Citations |
Conference | P14-1 | 10 |
PageRank | References | Authors |
0.49 | 26 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jun Seok Kang | 1 | 67 | 3.81 |
Song Feng | 2 | 280 | 19.55 |
Leman Akoglu | 3 | 1498 | 71.55 |
Yejin Choi | 4 | 2239 | 153.18 |