Using Verb Frames for Text Difficulty Assessment

John Lee; Meichun Liu; Tianyuan Cai

Using Verb Frames for Text Difficulty Assessment

Department of Linguistics and Translation

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

159 Downloads (CityUHK Scholars)

Abstract

This paper presents the first investigation on using semantic frames to assess text difficulty. Based on Mandarin VerbNet, a verbal semantic database that adopts a frame-based approach, we examine usage patterns of ten verbs in a corpus of graded Chinese texts. We identify a number of characteristics in texts at advanced grades: more frequent use of non-core frame elements; more frequent omission of some core frame elements; increased preference for noun phrases rather than clauses as verb arguments; and more frequent metaphoric usage. These characteristics can potentially be useful for automatic prediction of text readability

Original language	English
Title of host publication	Proceedings of the LREC International FrameNet Workshop 2020
Subtitle of host publication	Towards a Global, Multilingual FrameNet
Publisher	ELDA/ELRA
Pages	56-62
ISBN (Electronic)	9791095546580
Publication status	Published - May 2020
Event	International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet - Marseille, France Duration: 11 May 2020 → 16 May 2020

Conference

Conference	International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet
Country/Territory	France
City	Marseille
Period	11/05/20 → 16/05/20

Research Keywords

Mandarin VerbNet
verb frames
frame elements
readability

Publisher's Copyright Statement

European Language Resources Association (ELRA), licensed under CC-BY-NC.

Access Output

48400561.pdfFinal Published version, 277 KBLicence: CC BY-NC

http://www.lrec-conf.org/proceedings/lrec2020/workshops/framenet2020/pdf/2020.framenet-1.8.pdf

Other Access Options

Check CityUHK Library

Permanent Link

Right click to copy link

Cite this

@inproceedings{058cc940c8f448d79507cef36b7cd404,

title = "Using Verb Frames for Text Difficulty Assessment",

abstract = "This paper presents the first investigation on using semantic frames to assess text difficulty. Based on Mandarin VerbNet, a verbal semantic database that adopts a frame-based approach, we examine usage patterns of ten verbs in a corpus of graded Chinese texts. We identify a number of characteristics in texts at advanced grades: more frequent use of non-core frame elements; more frequent omission of some core frame elements; increased preference for noun phrases rather than clauses as verb arguments; and more frequent metaphoric usage. These characteristics can potentially be useful for automatic prediction of text readability",

keywords = "Mandarin VerbNet, verb frames, frame elements, readability",

author = "John Lee and Meichun Liu and Tianyuan Cai",

year = "2020",

month = may,

language = "English",

pages = "56--62",

booktitle = "Proceedings of the LREC International FrameNet Workshop 2020",

publisher = "ELDA/ELRA",

note = "International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet ; Conference date: 11-05-2020 Through 16-05-2020",

}

Lee, J , Liu, M & Cai, T 2020, Using Verb Frames for Text Difficulty Assessment. in Proceedings of the LREC International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet. ELDA/ELRA, pp. 56-62, International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet, Marseille, France, 11/05/20. <http://www.lrec-conf.org/proceedings/lrec2020/workshops/framenet2020/pdf/2020.framenet-1.8.pdf>

Using Verb Frames for Text Difficulty Assessment. / Lee, John ; Liu, Meichun ; Cai, Tianyuan.
Proceedings of the LREC International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet. ELDA/ELRA, 2020. p. 56-62.

Research output: Chapters, Conference Papers, Creative and Literary Works › RGC 32 - Refereed conference paper (with host publication) › peer-review

TY - GEN

T1 - Using Verb Frames for Text Difficulty Assessment

AU - Lee, John

AU - Liu, Meichun

AU - Cai, Tianyuan

PY - 2020/5

Y1 - 2020/5

N2 - This paper presents the first investigation on using semantic frames to assess text difficulty. Based on Mandarin VerbNet, a verbal semantic database that adopts a frame-based approach, we examine usage patterns of ten verbs in a corpus of graded Chinese texts. We identify a number of characteristics in texts at advanced grades: more frequent use of non-core frame elements; more frequent omission of some core frame elements; increased preference for noun phrases rather than clauses as verb arguments; and more frequent metaphoric usage. These characteristics can potentially be useful for automatic prediction of text readability

AB - This paper presents the first investigation on using semantic frames to assess text difficulty. Based on Mandarin VerbNet, a verbal semantic database that adopts a frame-based approach, we examine usage patterns of ten verbs in a corpus of graded Chinese texts. We identify a number of characteristics in texts at advanced grades: more frequent use of non-core frame elements; more frequent omission of some core frame elements; increased preference for noun phrases rather than clauses as verb arguments; and more frequent metaphoric usage. These characteristics can potentially be useful for automatic prediction of text readability

KW - Mandarin VerbNet

KW - verb frames

KW - frame elements

KW - readability

UR - http://www.lrec-conf.org/proceedings/lrec2020/workshops/framenet2020/index.html

M3 - RGC 32 - Refereed conference paper (with host publication)

SP - 56

EP - 62

BT - Proceedings of the LREC International FrameNet Workshop 2020

PB - ELDA/ELRA

T2 - International FrameNet Workshop 2020: Towards a Global, Multilingual FrameNet

Y2 - 11 May 2020 through 16 May 2020

ER -

Using Verb Frames for Text Difficulty Assessment

Abstract

Conference

Research Keywords

Publisher's Copyright Statement

Access Output

Other Access Options

Permanent Link

Other Files and Links

Fingerprint

Cite this