Computable Contracts by Extracting Obligation Logic Graphs

Sergio Servantez; Milan Aggarwal; Nedim Lipka; Balaji Krishnamurthy; Alexa Siu; Aparna Garimella; Kristian Hammond; Rajiv Jain

doi:10.1145/3594536.3595162

Computable Contracts by Extracting Obligation Logic Graphs

Sergio Servantez, Milan Aggarwal, Nedim Lipka, Balaji Krishnamurthy, Alexa Siu, Aparna Garimella, Kristian Hammond, Rajiv Jain

Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

The emergence of contract specific programming languages has struggled to translate into widespread adoption of computable contracts due largely to high conversion costs. In this work, we present the first system for converting natural language contracts into code through the extraction of key entities, relationships, and formulas into a graph representation called the Obligation Logic Graph (OLG). This approach allows the semantic meaning of contract obligations, including dependencies between obligations, to be captured through the OLG and mapped to code downstream. We also introduce OLG extraction as a new joint entity and relation prediction task for legal contracts, and present the Contract-OLG dataset, consisting of 1,876 contract provisions, 18,597 entities and 18,170 relationships. We perform detailed experiments to understand the capabilities of state-of-the-art Transformer and graph-based models at completing these tasks, and identify where there is currently a significant gap between human expert and machine performance, particularly for relation extraction.

Original language	English (US)
Title of host publication	19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference
Publisher	Association for Computing Machinery, Inc
Pages	267-276
Number of pages	10
ISBN (Electronic)	9798400701979
DOIs	https://doi.org/10.1145/3594536.3595162
State	Published - Jun 19 2023
Event	19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Braga, Portugal Duration: Jun 19 2023 → Jun 23 2023

Publication series

Name	19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference

Conference

Conference	19th International Conference on Artificial Intelligence and Law, ICAIL 2023
Country/Territory	Portugal
City	Braga
Period	6/19/23 → 6/23/23

Funding

This work was supported in part by Adobe Research. The authors thank Loraine Ferrer, Nissan Daquioag, and Amritanshu Tripathi for their contributions in annotating the Contract-OLG dataset.

Keywords

computable contracts
information extraction
natural language processing
obligation logic graph

ASJC Scopus subject areas

Artificial Intelligence
Software
Law

Access to Document

10.1145/3594536.3595162

Cite this

Servantez, S., Aggarwal, M., Lipka, N., Krishnamurthy, B., Siu, A., Garimella, A., Hammond, K., & Jain, R. (2023). Computable Contracts by Extracting Obligation Logic Graphs. In 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference (pp. 267-276). (19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference). Association for Computing Machinery, Inc. https://doi.org/10.1145/3594536.3595162

Servantez, Sergio ; Aggarwal, Milan ; Lipka, Nedim et al. / Computable Contracts by Extracting Obligation Logic Graphs. 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference. Association for Computing Machinery, Inc, 2023. pp. 267-276 (19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference).

@inproceedings{31404b0ccf8e40daade202913ae98239,

title = "Computable Contracts by Extracting Obligation Logic Graphs",

abstract = "The emergence of contract specific programming languages has struggled to translate into widespread adoption of computable contracts due largely to high conversion costs. In this work, we present the first system for converting natural language contracts into code through the extraction of key entities, relationships, and formulas into a graph representation called the Obligation Logic Graph (OLG). This approach allows the semantic meaning of contract obligations, including dependencies between obligations, to be captured through the OLG and mapped to code downstream. We also introduce OLG extraction as a new joint entity and relation prediction task for legal contracts, and present the Contract-OLG dataset, consisting of 1,876 contract provisions, 18,597 entities and 18,170 relationships. We perform detailed experiments to understand the capabilities of state-of-the-art Transformer and graph-based models at completing these tasks, and identify where there is currently a significant gap between human expert and machine performance, particularly for relation extraction.",

keywords = "computable contracts, information extraction, natural language processing, obligation logic graph",

author = "Sergio Servantez and Milan Aggarwal and Nedim Lipka and Balaji Krishnamurthy and Alexa Siu and Aparna Garimella and Kristian Hammond and Rajiv Jain",

note = "Publisher Copyright: {\textcopyright} ICAIL 2023. All rights reserved.; 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 ; Conference date: 19-06-2023 Through 23-06-2023",

year = "2023",

month = jun,

day = "19",

doi = "10.1145/3594536.3595162",

language = "English (US)",

series = "19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference",

publisher = "Association for Computing Machinery, Inc",

pages = "267--276",

booktitle = "19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference",

}

Servantez, S, Aggarwal, M, Lipka, N, Krishnamurthy, B, Siu, A, Garimella, A, Hammond, K & Jain, R 2023, Computable Contracts by Extracting Obligation Logic Graphs. in 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference. 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference, Association for Computing Machinery, Inc, pp. 267-276, 19th International Conference on Artificial Intelligence and Law, ICAIL 2023, Braga, Portugal, 6/19/23. https://doi.org/10.1145/3594536.3595162

Computable Contracts by Extracting Obligation Logic Graphs. / Servantez, Sergio; Aggarwal, Milan; Lipka, Nedim et al.
19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference. Association for Computing Machinery, Inc, 2023. p. 267-276 (19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Computable Contracts by Extracting Obligation Logic Graphs

AU - Servantez, Sergio

AU - Aggarwal, Milan

AU - Lipka, Nedim

AU - Krishnamurthy, Balaji

AU - Siu, Alexa

AU - Garimella, Aparna

AU - Hammond, Kristian

AU - Jain, Rajiv

PY - 2023/6/19

Y1 - 2023/6/19

N2 - The emergence of contract specific programming languages has struggled to translate into widespread adoption of computable contracts due largely to high conversion costs. In this work, we present the first system for converting natural language contracts into code through the extraction of key entities, relationships, and formulas into a graph representation called the Obligation Logic Graph (OLG). This approach allows the semantic meaning of contract obligations, including dependencies between obligations, to be captured through the OLG and mapped to code downstream. We also introduce OLG extraction as a new joint entity and relation prediction task for legal contracts, and present the Contract-OLG dataset, consisting of 1,876 contract provisions, 18,597 entities and 18,170 relationships. We perform detailed experiments to understand the capabilities of state-of-the-art Transformer and graph-based models at completing these tasks, and identify where there is currently a significant gap between human expert and machine performance, particularly for relation extraction.

AB - The emergence of contract specific programming languages has struggled to translate into widespread adoption of computable contracts due largely to high conversion costs. In this work, we present the first system for converting natural language contracts into code through the extraction of key entities, relationships, and formulas into a graph representation called the Obligation Logic Graph (OLG). This approach allows the semantic meaning of contract obligations, including dependencies between obligations, to be captured through the OLG and mapped to code downstream. We also introduce OLG extraction as a new joint entity and relation prediction task for legal contracts, and present the Contract-OLG dataset, consisting of 1,876 contract provisions, 18,597 entities and 18,170 relationships. We perform detailed experiments to understand the capabilities of state-of-the-art Transformer and graph-based models at completing these tasks, and identify where there is currently a significant gap between human expert and machine performance, particularly for relation extraction.

KW - computable contracts

KW - information extraction

KW - natural language processing

KW - obligation logic graph

UR - http://www.scopus.com/inward/record.url?scp=85176553347&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85176553347&partnerID=8YFLogxK

U2 - 10.1145/3594536.3595162

DO - 10.1145/3594536.3595162

M3 - Conference contribution

AN - SCOPUS:85176553347

T3 - 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference

SP - 267

EP - 276

BT - 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference

PB - Association for Computing Machinery, Inc

T2 - 19th International Conference on Artificial Intelligence and Law, ICAIL 2023

Y2 - 19 June 2023 through 23 June 2023

ER -

Servantez S, Aggarwal M, Lipka N, Krishnamurthy B, Siu A, Garimella A et al. Computable Contracts by Extracting Obligation Logic Graphs. In 19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference. Association for Computing Machinery, Inc. 2023. p. 267-276. (19th International Conference on Artificial Intelligence and Law, ICAIL 2023 - Proceedings of the Conference). doi: 10.1145/3594536.3595162

Computable Contracts by Extracting Obligation Logic Graphs

Abstract

Publication series

Conference

Funding

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this