• Publications
  • Influence
SemEval-2014 Task 4: Aspect Based Sentiment Analysis
TLDR
Sentiment analysis is increasingly viewed as a vital task both from an academic and a commercial standpoint. Expand
  • 699
  • 107
  • PDF
SemEval-2010 Task 14: Word Sense Induction &Disambiguation
TLDR
This paper presents the description and evaluation framework of SemEval-2010 Word Sense Induction & Disambiguation task, as well as the evaluation results of 26 participating systems. Expand
  • 154
  • 42
  • PDF
An Empirical Study on Compositionality in Compound Nouns
TLDR
A multiword is compositional if its meaning can be expressed in terms of the meaning of its constituents. Expand
  • 118
  • 39
  • PDF
Exploiting Syntactic and Shallow Semantic Kernels for Question Answer Classification
TLDR
We study the impact of syntactic and shallow semantic information in automatic classification of questions and answers and answer re-ranking. Expand
  • 219
  • 20
  • PDF
SemEval-2015 Task 12: Aspect Based Sentiment Analysis
TLDR
SemEval-2015 Task 12, a continuation of Sem Eval-2014 Task 4, aimed to foster research beyond sentenceor text-level sentiment classification towards Aspect Based Sentiment Analysis. Expand
  • 172
  • 20
  • PDF
Stochastic Constraint Programming: A Scenario-Based Approach
TLDR
We introduce scenario based stochastic constraint programming for decision making under uncertainty in a language called Stochastic OPL. Expand
  • 105
  • 16
  • PDF
Extending a Lexical Ontology by a Combination of Distributional Semantics Signatures
TLDR
We describe here a procedure to automatically extend an ontology such as WordNet with domain-specific knowledge. Expand
  • 118
  • 13
  • PDF
An Unsupervised Method for General Named Entity Recognition and Automated Concept Discovery
TLDR
This paper presents an approach to enriching ontologies with domain-dependent information in a fully unsupervised way. Expand
  • 169
  • 11
  • PDF
Tag-based expert recommendation in community question answering
TLDR
We study the user expertise under tags rather than topics in CQA and show that our method can achieve better performance than the state-of-the-art model. Expand
  • 33
  • 7
Priority Union and Generalization in Discourse Grammars
TLDR
We describe an implementation in Carpenter's typed feature formalism, ALE, of a discourse grammar of the kind proposed by Scha, Polanyi, et al. which uses the operations of priority union and generalization to resolve parallelism-dependent anaphora. Expand
  • 35
  • 7
  • PDF