paper-with-me

Papers

SP-10K: A Large-scale Evaluation Set for Selectional Preference Acquisition

2019-05-14 · ACL 2019 7 · Hongming Zhang, Hantian Ding, Yangqiu Song

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.

📄 PDF Abstract BibTeX arXiv:1906.02123

Code (1)

HKUST-KnowComp/SP-10K 공식 구현

Tasks

coreference-resolutionCoreference Resolution

Methods 이 논문이 사용한 방법론

American 설명 없음

Similar Papers 제목 키워드 기반

ASER: Towards Large-scale Commonsense Knowledge Acquisition via Higher-order Selectional Preference over Eventualities

2021-04-05 · Hongming Zhang, Xin Liu, Haojie Pan, Haowen Ke 외

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 Parsing

A Neural Network Approach to Selectional Preference Acquisition

2014-10-01 · EMNLP 2014 10 · Tim Van de Cruys
Semantic Role LabelingSemantic Textual SimilarityWord Sense Disambiguation

Improving Statistical Machine Translation with Selectional Preferences

2016-12-01 · COLING 2016 12 · Haiqing Tang, Deyi Xiong, Min Zhang, ZhengXian Gong

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 Disambiguation

Thematic fit evaluation: an aspect of selectional preferences

2016-08-01 · WS 2016 8 · Asad Sayeed, Clayton Greenberg, Vera Demberg
Decision Making

Multiplex Word Embeddings for Selectional Preference Acquisition

2020-01-09 · IJCNLP 2019 11 · Hongming Zhang, Jiaxin Bai, Yan Song, Kun Xu 외

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