paper-with-me

Papers

Parsing Gapping Constructions Based on Grammatical and Semantic Roles

2020-11-01 · EMNLP 2020 11 · Yoshihide Kato, Shigeki Matsubara

A gapping construction consists of a coordinated structure where redundant elements are elided from all but one conjuncts. This paper proposes a method of parsing sentences with gapping to recover elided elements. The proposed method is based on constituent trees annotated with grammatical and semantic roles that are useful for identifying elided elements. Our method outperforms the previous method in terms of F-measure and recall.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Gapping Constructions in Universal Dependencies v2

2017-05-01 · WS 2017 5 · Sebastian Schuster, Matthew Lamm, Christopher D. Manning

Towards a QUD-Based Analysis of Gapping Constructions

2016-10-01 · PACLIC 2016 10 · Sang-Hee Park

Sentences with Gapping: Parsing and Reconstructing Elided Predicates

2018-04-18 · NAACL 2018 6 · Sebastian Schuster, Joakim Nivre, Christopher D. Manning

Sentences with gapping, such as Paul likes coffee and Mary tea, lack an overt predicate to indicate the relation between two or more arguments. Surface syntax representations of such sentences are often produced poorly b…

Natural Language UnderstandingRelationRelation Extraction

A Method for Studying Semantic Construal in Grammatical Constructions with Interpretable Contextual Embedding Spaces

2023-05-29 · Gabriella Chronis, Kyle Mahowald, Katrin Erk

We study semantic construal in grammatical constructions using large language models. First, we project contextual word embeddings into three interpretable semantic spaces, each defined by a different set of psycholingui…

ObjectPositionSentenceWord Embeddings

AGRR 2019: Corpus for Gapping Resolution in Russian

2019-08-01 · WS 2019 8 · Maria Ponomareva, Kira Droganova, Ivan Smurov, Tatiana Shavrina

This paper provides a comprehensive overview of the gapping dataset for Russian that consists of 7.5k sentences with gapping (as well as 15k relevant negative sentences) and comprises data from various genres: news, fict…