@inproceedings{borchmann-etal-2020-contract,
title = "Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines",
author = "Borchmann, {\L}ukasz and
Wisniewski, Dawid and
Gretkowski, Andrzej and
Kosmala, Izabela and
Jurkiewicz, Dawid and
Sza{\l}kiewicz, {\L}ukasz and
Pa{\l}ka, Gabriela and
Kaczmarek, Karol and
Kaliska, Agnieszka and
Grali{\'n}ski, Filip",
editor = "Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2020",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.findings-emnlp.380",
doi = "10.18653/v1/2020.findings-emnlp.380",
pages = "4254--4268",
abstract = "We propose a new shared task of semantic retrieval from legal texts, in which a so-called contract discovery is to be performed {--} where legal clauses are extracted from documents, given a few examples of similar clauses from other legal acts. The task differs substantially from conventional NLI and shared tasks on legal information extraction (e.g., one has to identify text span instead of a single document, page, or paragraph). The specification of the proposed task is followed by an evaluation of multiple solutions within the unified framework proposed for this branch of methods. It is shown that state-of-the-art pretrained encoders fail to provide satisfactory results on the task proposed. In contrast, Language Model-based solutions perform better, especially when unsupervised fine-tuning is applied. Besides the ablation studies, we addressed questions regarding detection accuracy for relevant text fragments depending on the number of examples available. In addition to the dataset and reference results, LMs specialized in the legal domain were made publicly available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="borchmann-etal-2020-contract">
<titleInfo>
<title>Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines</title>
</titleInfo>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Borchmann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Wisniewski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andrzej</namePart>
<namePart type="family">Gretkowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izabela</namePart>
<namePart type="family">Kosmala</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dawid</namePart>
<namePart type="family">Jurkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Łukasz</namePart>
<namePart type="family">Szałkiewicz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriela</namePart>
<namePart type="family">Pałka</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Karol</namePart>
<namePart type="family">Kaczmarek</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Agnieszka</namePart>
<namePart type="family">Kaliska</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Filip</namePart>
<namePart type="family">Graliński</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2020</title>
</titleInfo>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a new shared task of semantic retrieval from legal texts, in which a so-called contract discovery is to be performed – where legal clauses are extracted from documents, given a few examples of similar clauses from other legal acts. The task differs substantially from conventional NLI and shared tasks on legal information extraction (e.g., one has to identify text span instead of a single document, page, or paragraph). The specification of the proposed task is followed by an evaluation of multiple solutions within the unified framework proposed for this branch of methods. It is shown that state-of-the-art pretrained encoders fail to provide satisfactory results on the task proposed. In contrast, Language Model-based solutions perform better, especially when unsupervised fine-tuning is applied. Besides the ablation studies, we addressed questions regarding detection accuracy for relevant text fragments depending on the number of examples available. In addition to the dataset and reference results, LMs specialized in the legal domain were made publicly available.</abstract>
<identifier type="citekey">borchmann-etal-2020-contract</identifier>
<identifier type="doi">10.18653/v1/2020.findings-emnlp.380</identifier>
<location>
<url>https://aclanthology.org/2020.findings-emnlp.380</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>4254</start>
<end>4268</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines
%A Borchmann, Łukasz
%A Wisniewski, Dawid
%A Gretkowski, Andrzej
%A Kosmala, Izabela
%A Jurkiewicz, Dawid
%A Szałkiewicz, Łukasz
%A Pałka, Gabriela
%A Kaczmarek, Karol
%A Kaliska, Agnieszka
%A Graliński, Filip
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Findings of the Association for Computational Linguistics: EMNLP 2020
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F borchmann-etal-2020-contract
%X We propose a new shared task of semantic retrieval from legal texts, in which a so-called contract discovery is to be performed – where legal clauses are extracted from documents, given a few examples of similar clauses from other legal acts. The task differs substantially from conventional NLI and shared tasks on legal information extraction (e.g., one has to identify text span instead of a single document, page, or paragraph). The specification of the proposed task is followed by an evaluation of multiple solutions within the unified framework proposed for this branch of methods. It is shown that state-of-the-art pretrained encoders fail to provide satisfactory results on the task proposed. In contrast, Language Model-based solutions perform better, especially when unsupervised fine-tuning is applied. Besides the ablation studies, we addressed questions regarding detection accuracy for relevant text fragments depending on the number of examples available. In addition to the dataset and reference results, LMs specialized in the legal domain were made publicly available.
%R 10.18653/v1/2020.findings-emnlp.380
%U https://aclanthology.org/2020.findings-emnlp.380
%U https://doi.org/10.18653/v1/2020.findings-emnlp.380
%P 4254-4268
Markdown (Informal)
[Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines](https://aclanthology.org/2020.findings-emnlp.380) (Borchmann et al., Findings 2020)
ACL
- Łukasz Borchmann, Dawid Wisniewski, Andrzej Gretkowski, Izabela Kosmala, Dawid Jurkiewicz, Łukasz Szałkiewicz, Gabriela Pałka, Karol Kaczmarek, Agnieszka Kaliska, and Filip Graliński. 2020. Contract Discovery: Dataset and a Few-Shot Semantic Retrieval Challenge with Competitive Baselines. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 4254–4268, Online. Association for Computational Linguistics.