ContractNLI: A Dataset for Document-level Natural Language Inference for Contracts

10/05/2021
by   Yuta Koreeda, et al.
0

Reviewing contracts is a time-consuming procedure that incurs large expenses to companies and social inequality to those who cannot afford it. In this work, we propose "document-level natural language inference (NLI) for contracts", a novel, real-world application of NLI that addresses such problems. In this task, a system is given a set of hypotheses (such as "Some obligations of Agreement may survive termination.") and a contract, and it is asked to classify whether each hypothesis is "entailed by", "contradicting to" or "not mentioned by" (neutral to) the contract as well as identifying "evidence" for the decision as spans in the contract. We annotated and release the largest corpus to date consisting of 607 annotated contracts. We then show that existing models fail badly on our task and introduce a strong baseline, which (1) models evidence identification as multi-label classification over spans instead of trying to predict start and end tokens, and (2) employs more sophisticated context segmentation for dealing with long documents. We also show that linguistic characteristics of contracts, such as negations by exceptions, are contributing to the difficulty of this task and that there is much room for improvement.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
03/02/2023

Developing a Compiler for EROP – A Language for the Specification of Smart Contracts, An Experience Report

A smart contract is a translation of a standard paper-based contract tha...
research
11/02/2021

Detecting Logical Relation In Contract Clauses

Contracts underlie most modern commercial transactions defining define t...
research
05/31/2021

A Bytecode-based Approach for Smart Contract Classification

With the development of blockchain technologies, the number of smart con...
research
10/26/2021

CLAUSEREC: A Clause Recommendation Framework for AI-aided Contract Authoring

Contracts are a common type of legal document that frequent in several d...
research
04/09/2023

RISC: Generating Realistic Synthetic Bilingual Insurance Contract

This paper presents RISC, an open-source Python package data generator (...
research
08/14/2023

Generative Interpretation

We introduce generative interpretation, a new approach to estimating con...
research
08/04/2021

Practices of public procurement and the risk of corrupt behavior before and after the government transition in México

Corruption has a huge impact on economic growth, democracy, inequality, ...

Please sign up or login with your details

Forgot password? Click here to reset