Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings

Daniel Braun

Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings

Industrial Engineering & Business Information Systems

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Language and its usage change over time. While legal language is arguably more stable than everyday language, it is still subject to change. Sometimes it changes gradually and slowly, sometimes almost instantaneously, for example through legislative changes. This paper presents an application of diachronic word embeddings to track changes in the usage of language by German courts triggered by changing legislation, based on a corpus of more than 200,000 documents. The results show the swift and lasting effect that changes in legislation can have on the usage of language by courts and suggest that using time-restricted word embedding models could be beneficial for downstream NLP tasks.

Original language	English
Title of host publication	Proceedings of the Natural Legal Language Processing Workshop 2022
Publisher	Association for Computational Linguistics (ACL)
Pages	218-227
Number of pages	10
Publication status	Published - Dec 2022
Event	Natural Legal Language Processing Workshop, NLLP 2022 - Abu Dhabi, United Arab Emirates Duration: 8 Dec 2022 → 8 Dec 2022

Workshop

Workshop	Natural Legal Language Processing Workshop, NLLP 2022
Abbreviated title	NLLP Workshop 2022
Country/Territory	United Arab Emirates
City	Abu Dhabi
Period	8/12/22 → 8/12/22

Access to Document

https://aclanthology.org/2022.nllp-1.19.pdfLicence: CC BY

Cite this

@inproceedings{a3a35cc0bd214c7c8ec7a7c80f1820b3,

title = "Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings",

abstract = "Language and its usage change over time. While legal language is arguably more stable than everyday language, it is still subject to change. Sometimes it changes gradually and slowly, sometimes almost instantaneously, for example through legislative changes. This paper presents an application of diachronic word embeddings to track changes in the usage of language by German courts triggered by changing legislation, based on a corpus of more than 200,000 documents. The results show the swift and lasting effect that changes in legislation can have on the usage of language by courts and suggest that using time-restricted word embedding models could be beneficial for downstream NLP tasks.",

author = "Daniel Braun",

year = "2022",

month = dec,

language = "English",

pages = "218--227",

booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2022",

publisher = "Association for Computational Linguistics (ACL)",

address = "United States",

note = "Natural Legal Language Processing Workshop, NLLP 2022, NLLP Workshop 2022 ; Conference date: 08-12-2022 Through 08-12-2022",

}

Braun, D 2022, Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings. in Proceedings of the Natural Legal Language Processing Workshop 2022. Association for Computational Linguistics (ACL), pp. 218-227, Natural Legal Language Processing Workshop, NLLP 2022, Abu Dhabi, United Arab Emirates, 8/12/22. <https://aclanthology.org/2022.nllp-1.19.pdf>

TY - GEN

T1 - Tracking Semantic Shifts in German Court Decisions with Diachronic Word Embeddings

AU - Braun, Daniel

PY - 2022/12

Y1 - 2022/12

N2 - Language and its usage change over time. While legal language is arguably more stable than everyday language, it is still subject to change. Sometimes it changes gradually and slowly, sometimes almost instantaneously, for example through legislative changes. This paper presents an application of diachronic word embeddings to track changes in the usage of language by German courts triggered by changing legislation, based on a corpus of more than 200,000 documents. The results show the swift and lasting effect that changes in legislation can have on the usage of language by courts and suggest that using time-restricted word embedding models could be beneficial for downstream NLP tasks.

AB - Language and its usage change over time. While legal language is arguably more stable than everyday language, it is still subject to change. Sometimes it changes gradually and slowly, sometimes almost instantaneously, for example through legislative changes. This paper presents an application of diachronic word embeddings to track changes in the usage of language by German courts triggered by changing legislation, based on a corpus of more than 200,000 documents. The results show the swift and lasting effect that changes in legislation can have on the usage of language by courts and suggest that using time-restricted word embedding models could be beneficial for downstream NLP tasks.

M3 - Conference contribution

SP - 218

EP - 227

BT - Proceedings of the Natural Legal Language Processing Workshop 2022

PB - Association for Computational Linguistics (ACL)

T2 - Natural Legal Language Processing Workshop, NLLP 2022

Y2 - 8 December 2022 through 8 December 2022

ER -