TY - JOUR
T1 - A computational construction grammar approach to semantic frame extraction
AU - Beuls, Katrien
AU - Van Eecke, Paul
AU - Cangalovic, Vanja Sophie
N1 - Funding Information:
Funding: This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 732942 (funder id: http://dx.doi.org/10.13039/100010664), from the Flemish Government under the ‘Onderzoeksprogramma Artificiële Intelligentie (AI) Vlaanderen’ programme, and from a postdoctoral fellowship of the Research Foundation Flanders (FWO) awarded to PVE (grant No 75929, funder id: http://dx.doi.org/10.13039/501100003130).
Publisher Copyright:
© 2021 Walter de Gruyter GmbH. All rights reserved.
PY - 2021
Y1 - 2021
N2 - This paper introduces a novel methodology for extracting semantic frames from text corpora. Building on recent advances in computational construction grammar, the method captures expert knowledge of how semantic frames can be expressed in the form of conventionalised form-meaning pairings, called constructions. By combining these constructions in a semantic parsing process, the frame-semantic structure of a sentence is retrieved through the intermediary of its morpho-syntactic structure. The main advantage of this approach is that state-of-the-art results are achieved, without the need for annotated training data. We demonstrate the method in a case study where causation frames are extracted from English newspaper articles, and compare it to a commonly used approach based on Conditional Random Fields (CRFs). The computational construction grammar approach yields a word-level F 1 score of 78.5%, outperforming the CRF approach by 4.5 percentage points.
AB - This paper introduces a novel methodology for extracting semantic frames from text corpora. Building on recent advances in computational construction grammar, the method captures expert knowledge of how semantic frames can be expressed in the form of conventionalised form-meaning pairings, called constructions. By combining these constructions in a semantic parsing process, the frame-semantic structure of a sentence is retrieved through the intermediary of its morpho-syntactic structure. The main advantage of this approach is that state-of-the-art results are achieved, without the need for annotated training data. We demonstrate the method in a case study where causation frames are extracted from English newspaper articles, and compare it to a commonly used approach based on Conditional Random Fields (CRFs). The computational construction grammar approach yields a word-level F 1 score of 78.5%, outperforming the CRF approach by 4.5 percentage points.
KW - Computational construction grammar
KW - Fluid Construction Grammar
KW - FrameNet
KW - Semantic frames
UR - http://www.scopus.com/inward/record.url?scp=85101220963&partnerID=8YFLogxK
U2 - 10.1515/lingvan-2018-0015
DO - 10.1515/lingvan-2018-0015
M3 - Article
VL - 7
SP - 20180015
JO - Linguistics Vanguard
JF - Linguistics Vanguard
IS - 1
M1 - 20180015
ER -