SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition
Selectional Preference (SP) is a commonly observed language phenomenon and proved to be useful in many natural language processing tasks. To provide a better evaluation method for SP models, we introduce SP-10K, a large-scale evaluation set that provides human ratings for the plausibility of 10,000 SP pairs over five SP relations, covering 2,500 most frequent verbs, nouns, and adjectives in American English. Three representative SP acquisition methods based on pseudo-disambiguation are evaluated with SP-10K. To demonstrate the importance of our dataset, we investigate the relationship between SP-10K and the commonsense knowledge in ConceptNet5 and show the potential of using SP to represent the commonsense knowledge. We also use the Winograd Schema Challenge to prove that the proposed new SP relations are essential for the hard pronoun coreference resolution problem.
Code (1)
Tasks
coreference-resolutionCoreference ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities
Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to collect commonsense knowledge. In this paper, we p…
Discourse ParsingA Neural Network Approach to Selectional Preference Acquisition
Improving Statistical Machine Translation with Selectional Preferences
Long-distance semantic dependencies are crucial for lexical choice in statistical machine translation. In this paper, we study semantic dependencies between verbs and their arguments by modeling selectional preferences i…
Machine TranslationSemantic Role LabelingTranslationWord Sense DisambiguationThematic fit evaluation: an aspect of selectional preferences
Multiplex Word Embeddings for Selectional Preference Acquisition
Conventional word embeddings represent words with fixed vectors, which are usually trained based on co-occurrence patterns among words. In doing so, however, the power of such representations is limited, where the same w…
Word EmbeddingsWord Similarity