COLIEE-2022 CALL FOR TASK PARTICIPATION

Competition on Legal Information Extraction/Entailment (COLIEE)

COLIEE-2022 Workshop: June, 12-14 2022 (exact date to be confirmed)

Run in association with the International Workshop in Juris-Informatics (JURISIN 2022)

Venue: Kyoto International Conference Center, Kyoto, Japan (onsite/online/hybrid style is available)


COLIEE registration due: Mar 15, 2022


Those who wish to use previous COLIEE data for a trial, please contact rabelo(at)ualberta.ca

Results for all tasks now available!



Sponsored by
Alberta Machine Intelligence Institute (AMII)
University of Alberta
National Institute of Informatics (NII)
vLex Canada
Intellicon

Download Call for Participation

As an associated event of JURISIN 2022, we are happy to announce the 9th Competition on Legal Information Extraction and Entailment (COLIEE-2022).

Four tasks are included in the 2022 competition: Tasks 1 and 2 are about the case law competition, and tasks 3 and 4 are about the statute law competition. Task 1 is a legal case retrieval task, and it involves reading a new case Q, and extracting supporting cases S1, S2, ..., Sn from the provided case law corpus, to support the decision for Q. Task 2 is the legal case entailment task, which involves the identification of a paragraph from existing cases that entails the decision of a new case. As in previous COLIEE competitions, Task 3 is to consider a yes/no legal question Q and retrieve relevant statutes from a database of Japanese civil code statutes; Task 4 is to confirm entailment of a yes/no answer from the retrieved civil code statutes.

1. Tasks Description

1.1 (COLIEE Case Law Competition) Task 1:The Legal Case Retrieval Task

This legal case competition focuses on two aspects of legal information processing related to a database of predominantly Federal Court of Canada case laws, provided by Compass Law.

The legal case retrieval task involves reading a new case Q, and extracting supporting cases S1, S2, ... Sn for the decision of Q from the entire case law corpus. Through the document, we will call the supporting cases for the decision of a new case 'noticed cases'.

1.2 (COLIEE Case Law Competition) Task 2: The Legal Case Entailment task

This task involves the identification of a paragraph from existing cases that entails the decision of a new case.

Given a decision Q of a new case and a relevant case R, a specific paragraph that entails the decision Q needs to be identified. We confirmed that the answer paragraph can not be identified merely by information retrieval techniques using some examples. Because the case R is a relevant case to Q, many paragraphs in R can be relevant to Q regardless of entailment.

This task requires one to identify a paragraph which entails the decision of Q, so a specific entailment method is required which compares the meaning of each paragraph in R and Q in this task.

1.3 (COLIEE Statute Law Competition) Task 3: The Statute Law Retrieval Task

The COLIEE statute law competition focuses on two aspects of legal information processing related to answering yes/no questions from Japanese legal bar exams (the relevant data sets have been translated from Japanese to English).

Task 3 of the legal question answering task involves reading a legal bar exam question Q, and extracting a subset of Japanese Civil Code Articles S1, S2,..., Sn from the entire Civil Code which are those appropriate for answering the question such that

Entails(S1, S2, ..., Sn , Q) or Entails(S1, S2, ..., Sn , not Q).

Given a question Q and the entire Civil Code Articles, we have to retrieve the set of "S1, S2, ..., Sn" as the answer of this track.

1.4 (COLIEE Statute Law competition) Task 4: The Legal Textual Entailment Data Corpus

Task 4 of the legal textual entailment task involves the identification of an entailment relationship such that

Entails(S1, S2, ..., Sn , Q) or Entails(S1, S2, ..., Sn , not Q).

Given a question Q, we have to retrieve relevant articles S1, S2, ..., Sn through phase one, and then we have to determine if the relevant articles entail "Q" or "not Q". The answer of this track is binary: "YES"("Q") or "NO"("not Q").

2. Data Corpus

2.1 Case Law Competition Data Corpus(Task 1 and Task 2)

COLIEE-2022 data is drawn from an existing collection of predominantly Federal Court of Canada case law.

Participants can choose which phase they will apply for, amongst the two sub-tasks as follows:

1) Task 1: legal information retrieval task. Input is an unseen legal case Q, and output should be relevant cases in the given legal case corpus that support the decision of the input case, which are 'noticed cases'.

2) Task 2: Recognizing entailment between a new case and a relevant case. Input is a decision fragment from an unseen case and a relevant case (the full text from the unseen case, with a few pieces suppressed, is also given as input). Output should be a specific paragraph from the relevant case, which entails the given fragment of the unseen case.

2.2 Statute Law Competition Data Corpus(Task 3 and Task 4)

The corpus of legal questions is drawn from Japanese Legal Bar exams, and all the Japanese Civil Law articles are also provided (file format and access described below).

Participants can choose which phase they will apply for, amongst the three sub-tasks as follows:

1) Task 3: Legal Information Retrieval Task. Input is a bar exam 'Yes/No' question and output should be relevant civil law articles.

2) Task 4: Recognizing Entailment between Law Articles and Queries. Input is a bar exam 'Yes/No' question. After retrieving relevant articles using your method, you have to determine 'Yes' or 'No' as the output.

3. Measuring the Competition Results

3.1. Measuring the Case Law Competition Results (Tasks 1 and 2)

For Tasks one and two, evaluation measure will be precision, recall and F-measure:

Precision =    (the number of correctly retrieved cases(paragraphs) for all queries)
                               (the number of retrieved cases(paragraphs) for all queries) ,

Recall =       (the number of correctly retrieved cases(paragraphs) for all queries)
                                 (the number of relevant cases(paragraphs) for all queries) ,

F-measure =    (2 x Precision x Recall)
                  (Precision + Recall)



In the evaluation of Task 1 and Task 2, We simply use micro-average (evaluation measure is calculated using the results of all queries) rather than macro-average (evaluation measure is calculated for each query and then take average).

3.2. Measuring the Statute Law Competition Results (Tasks 3 and 4)

For Task 3, evaluation measure will be precision, recall and F2-measure (since IR process is pre-process to select candidate articles for providing candidates which will be used in the entailment process, we put emphasis on recall), and it is:

Precision =    average of (the number of correctly retrieved articles for each query)
                              (the number of retrieved articles for each query) ,

Recall =       average of (the number of correctly retrieved articles for each query)
                               (the number of relevant articles for each query) ,

F2-measure =    (5 x Precision x Recall)
                            (4 x Precision + Recall)



In addition to the above evaluation measures, ordinal information retrieval measures such as Mean Average Precision and R-precision can be used for discussing the characteristics of the submission results.

In COLIEE 2022, the method used to calculate the final evaluation score of all queries is macro-average (evaluation measure is calculated for each query and their average is used as the final evaluation measure) instead of micro-average (evaluation measure is calculated using results of all queries).

For Task 4, the evaluation measure will be accuracy, with respect to whether the yes/no question was correctly confirmed:

Accuracy = (the number of queries which were correctly confirmed as true or false)
(the number of all queries)

4. Submission details

Participants are required to submit a paper on their method and experimental results. At least one of the authors of an accepted paper has to present the paper at the COLIEE workshop of JURISIN 2022, which will be held online. We plan to publish a selection of the papers in the LNAI post-proceedings.

Papers should conform to the standards set out at the JURISIN 2022 webpage (section Submission).

5. Schedule


   15 Jan, 2022 Training data release.
   26 Jan, 2022 25 Feb, 2022 Test data release.
   15 Mar, 2022 Submission deadline of competition test runs for task 3.
   22 Mar, 2022 Announcements of rankings/ assessments for task 3 and announcements of answers (relevant article(s) for each question) for task 4.
   29 Mar, 2022strike> 02 Apr, 2022 Submission deadline of competition test runs for tasks 1, 2, 4.
   05 Apr, 2022 Announcements of rankings/ assessments for tasks 1, 2, 4.
   15 Apr, 2022 Paper submission deadline for the COLIEE workshop.
   30 Apr, 2022 Notification for the COLIEE workshop paper.
   15 May, 2022 Camera-ready copy deadline.
   12-14 Jun, 2022 JURISIN 2022 (one day for the COLIEE workshop - TBD).

6. Details of Each Task

6.1 Task 1 Details

Our goal is to explore and evaluate legal document retrieval technologies that are both effective and reliable.

The task investigates the performance of systems that search a set of case laws that support the unseen case law. The goal of the task is to return 'noticed cases' in the given collection to a query. We call a case is 'noticed' to a query iff the case is referenced by the query case. In this task, the references are redacted from the query case contents, because our goal is to measure how accurately a machine can capture decision-supporting cases for a given case.

A corpus composed of Federal Court of Canada case laws will be provided. The process of executing the new query cases over the existing cases and generating the experimental runs should be entirely automatic. All query and noticed cases will be provided as a pool. In the training data, we will also disclose which are the noticed cases for each query case. In the test data, only the query cases will be given and the task is to predict which cases should be noticed with respect to each of the test query cases.

There should be no human intervention at any stage, including modifications to your retrieval system motivated by an inspection of the test queries. You won't have access to the test labels before you submit your runs.

At most three runs from each group will be assessed. The submission format and evaluation methods are described below.

6.2 Task 2 Details

Our goal is to predict the decision of a new case by entailment from previous relevant cases.

As a simpler version of predicting a decision, a decision of a new case and a noticed case will be given as a query. Then, your legal textual entailment system identifies which paragraph in the noticed case entails the decision, by comparing the meanings between queries and the paragraphs.

The task investigates the performance of systems that identifies a paragraph that entails the decision of an unseen case.

Training data consists of triples of a query, a noticed case, and a paragraph number of the noticed case by which the decision of the query is entailed. The process of executing the queries over the noticed cases and generating the experimental runs should be entirely automatic. Test data will include only queries and noticed cases, but no paragraph numbers.

There should be no human intervention at any stage, including modifications to your retrieval system motivated by an inspection of the test queries.

'Decision', in this context, does not mean the final decision of a case, but rather a conclusion expressed by the judge which is entailed by one or more particular paragraphs from the noticed case. In our dataset, this information is packaged in a file named 'entailed_fragment.txt'.

6.3 Task 3 Details

Our goal is to explore and evaluate legal document retrieval technologies that are both effective and reliable.

The task investigates the performance of systems that search a static set of civil law articles using previously unseen queries. The goal of the task is to return relevant articles in the collection to a query. We call an article as "Relevant" to a query iff the query sentence can be answered Yes/No, entailed from the meaning of the article. If combining the meanings of more than one article (e.g., "A", "B", and "C") can answer a query sentence, then all the articles ("A", "B", and "C") are considered "Relevant". If a query can be answered by an article "D", and it can be also answered by another article "E" independently, we also consider both of the articles "D" and "E" are "Relevant". This task requires the retrieval of all the articles that are relevant to answering a query.

Japanese civil law articles (English translation besides Japanese) will be provided, and training data consists of pairs of a query and relevant articles. The process of executing the queries over the articles and generating the experimental runs should be entirely automatic. Test data will include only queries but no relevant articles.

There should be no human intervention at any stage, including modifications to your retrieval system motivated by an inspection of the queries. You should not materially modify your retrieval system between the time you downloaded the queries and the time you submit your runs.

At most three runs from each group will be assessed. The submission format and evaluation methods are described below.

6.4 Task 4 Details

Our goal is to construct Yes/No question answering systems for legal queries, by entailment from the relevant articles.

If a 'Yes/No' legal bar exam question is given, your legal information retrieval system retrieves relevant Civil Law articles. Then, the task investigates the performance of systems that answer 'Yes' or 'No' to previously unseen queries by comparing the meanings between queries and your retrieved Civil Law articles. Training data consists of triples of a query, relevant article(s), a correct answer "Y" or "N". Test data will include only queries and relevant articles, but no 'Y/N' label.

There should be no human intervention at any stage, including modifications to your retrieval system motivated by an inspection of the queries. You should not materially modify your retrieval system between the time you downloaded the queries and the time you submit your runs.

At most three runs for each group should be assessed. The submission format and evaluation methods are described below.

7. Corpus Structure

The structure of the test corpora is derived from a general XML representation developed for use in RITEVAL, one of the tasks of the NII Testbeds and Community for Information access Research (NTCIR) project, as described at the following URL:

http://sites.google.com/site/ntcir11riteval/

The RITEVAL format was developed for the general sharing of information retrieval on a variety of domains.

7.1 Case Law Competition Corpus Structure - Task 1

The corpus is given as a flat list of files containing all query and noticed cases, for both the training and test datasets. The training dataset is described in a json file containing a mapping between the query case and a list of noticed cases, as in the example below:

{
   "000001.txt": ["000005.txt", "012101.txt"],
   "003423.txt": ["398421.txt", "012101.txt", "173651.txt"],
   "012831.txt": ["000001.txt"],
   ...
}
The above is an example of a golden labels file for Task 1 containing three query cases (or "base cases"). The first query case is the file "000001.txt", which has 2 noticed cases ("000005.txt" and "012101.txt"). The second query case is the file named "003423.txt", which has 3 noticed cases (whose file names are "021.txt" and "105.txt"). The third query case ("012831.txt") has only one noticed case: "000001.txt".

The test dataset json file contains only the list of query cases, and the task consists in populating the list of noticed cases for each query case.

7.2 Case Law Competition Corpus Structure - Task 2

The corpus structure for Task 2 is given below:
{
   "001": ["013.txt"],
   "002": ["003.txt", "045.txt"],
   ...
}
The above is an example of Task 2 training data containing 2 files. Each query case has a separate folder, which is named with the query case id. That folder contains a file named "base_case.txt", which contains the raw text of the query case (with a few fragments suppressed), a file named "entailed_fragment.txt", which contains a fragment from the query case that is entailed by one or more paragraphs of a referenced case, and a folder named "paragraphs". That folder contains the paragraphs of said referenced case, one paragraph per file, which are named 001.txt to [n].txt (n being the number of paragraphs in the referenced case). The expected answer for each case is given as a list of paragraphs in the mapping file.

Given the sample above, the file structure for the corpus would be:


task2_training_corpus
+--- 001
+------- base_case.txt
+------- entailed_fragment.txt
+------- paragraphs
+----------- 001.txt
+----------- 002.txt
+----------- ...
+----------- 046.txt
+--- 002
+------- base_case.txt
+------- entailed_fragment.txt
+------- paragraphs
+----------- 001.txt
+----------- 002.txt
+----------- ...
+----------- 211.txt
+--- train_labels.json


For the query case 001, there are 46 paragraphs in the referenced case (among which is the expected answer, 013.txt, as given in the golden labels JSON file shown before). For the query case 002, there are 211 paragraphs in the referenced case, among which are the two which entail the fragment of text for that case (003.txt and 045.txt, as given in the golden labels file). For the case whose id is "001", the expected answer is "013.txt", meaning the entailed fragment (ie, the decision) in that query can be entailed from the paragraph id 013 in the given noticed case. The decision in the query is not the final decision of the case. This is a decision for a part of the case, and a paragraph that supports this decision should be identified in the given noticed case. The test corpora will not include the JSON file mapping, and the task is to predict which paragraph(s) entail(s) the decision given by the entailed_fragment.txt file in each case.

7.3 Statute Law Competition Corpus Structure (Tasks 3 and 4)

The format of the COLIEE competition corpora derived from an NTCIR representation of confirmed relationships between questions and the articles and cases relevant to answering the questions, as in the following example:

<pair label="Y" id="H18-1-2">
 <t1>
  (Seller's Warranty in cases of Superficies or Other Rights)Article 566
  (1)In cases where the subject matter of the sale is encumbered with for the purpose of a superficies, an emphyteusis, an easement, a right of retention or a pledge, if the buyer does not know the same and cannot achieve the purpose of the contract on account thereof, the buyer may cancel the contract. In such cases, if the contract cannot be cancelled, the buyer may only demand compensation for damages.
  (2)The provisions of the preceding paragraph shall apply mutatis mutandis in cases where an easement that was referred to as being in existence for the benefit of immovable property that is the subject matter of a sale, does not exist, and in cases where a leasehold is registered with respect to the immovable property.
  (3)In the cases set forth in the preceding two paragraphs, the cancellation of the contract or claim for damages must be made within one year from the time when the buyer comes to know the facts.
  (Seller's Warranty in cases of Mortgage or Other Rights) Article 567
  (1)If the buyer loses his/her ownership of immovable property that is the object of a sale because of the exercise of an existing statutory lien or mortgage, the buyer may cancel the contract.
  (2)If the buyer preserves his/her ownership by incurring expenditure for costs, he/she may claim reimbursement of those costs from the seller.
  (3)In the cases set forth in the preceding two paragraphs, the buyer may claim compensation if he/she suffered loss.
 </t1>
 <t2>
  There is a limitation period on pursuance of warranty if there is restriction due to superficies on the subject matter, but there is no restriction on pursuance of warranty if the seller's rights were revoked due to execution of the mortgage.
 </t2>
</pair>
The above is an example where query id "H18-1-2" is confirmed to be answerable from article numbers 566 and 567 (relevant to Task 3). The pair label "Y" in this example means the answer for this query is "Yes", which is entailed from the relevant articles (relevant to Task 4 and Task 5).

For the Tasks 3 and 4, the training data will be the same. The groups who participate only in the Task 3 can disregard the pair label.


8. Competition Results Submission Format

8.1. Task 1

For Task 1, a submission should consist of a single ASCII text file. Use a single space to separate columns, with three columns per line as follows:

000001 000018 univABC
000001 000045 univABC
000001 000130 univABC
000002 000433 univABC
.
.
.
where:

1. The first column is the query file name.
2. The second column is the official case number of the retrieved case.
3. The third column is called the "run tag" and should be a unique identifier for the submitting group, i.e., each run should have a different tag that identifies the group. Please restrict run tags to 12 or fewer letters and numbers, with no punctuation.
In this example of a submission, you can see that 000001 has multiple relevant articles (000018.txt, 000045.txt and 000130.txt).

8.2. Task 2

For Task 2, a submission should consist of a single ASCII text file. Use a single space to separate columns, with three columns per line as follows:

001 013 univABC
002 037 univABC
002 002 univABC
003 008 univABC
.
.
.
where:

1. The first column is the query id.
2. The second column is the paragraph number which entails the decision.
3. The third column is called the "run tag" and should be a unique identifier for the submitting group, i.e., each run should have a different tag that identifies the group. Please restrict run tags to 12 or fewer letters and numbers, with no punctuation.
A query can have multiple entailing paragraph numbers.

8.3. Task 3

Submission format in Task 3 is the TREC eval format used in trec_eval program. Use a single space to separate columns, with six columns per line as follows:

H21-5-3  Q0  	213	1   	0.8	univABC


Where

1. The first column is the query id.
2. The second column is "iter" for trec_eval and not used in the evaluation. Information of the column will be ignored. But please write Q0 in this column.
3. The third column is the official article number of the retrieved article.
3. The fourth column is the rank of the the retrieved articles.
3. The fifth column is similarity value (float value) of the retrieved articles.
6. The sixth column is called the "run tag" and should be a unique identifier for the submitting group, i.e., each run should have a different tag that identifies the group. Please restrict run tags to 12 or fewer letters and numbers, with no punctuation.

Please refer to the README file of the trec_eval.8.1.tar.gz for detailed explanation. Most significant difference between the previous submission format and new one is that it is necessary to provide ranked lists instead of simple answer sets. Maximum numbers of the documents for each query is limited to 100. It is also encouraged to submit ranked list results with 100 candidates for each query. Since such submissions have smaller precision values due to the large numbers of candidates, it may be inappropriate to compare ones with small numbers of candidates. In order to clarify these different types of submissions, please add suffix "-L" for the submission result file (e.g., When univABC is the results for the submission with limited numbers of candidates, please use univABC-L for the submission with large numbers of submission).

8.4. Task 4

For Task 4, again a submission should consist of a single ASCII text file. Use as single space to separate columns as follows, with three columns per line as follows:

H18-1-2 Y univABC
H18-5-A N univABC
H19-19-I Y univABC
H21-5-3 N univABC
.
.
.
where:

1. and 3 as for Phase One,
2. "Y" or "N" indicating whether the Y/N question was confirmed to be true ("Y") by the relevant articles, or confirmed to be false ("N").


Participants are also required to submit answers and evaluation results of past three years' formal run settings, i.e. using each of the past three years' datasets (H30,H31,R01) as test datasets, older years' datasets (-H29, -H30,-H31) as training datasets.
If this is not realistic due to e.g. the training time, please consult the task organizers.

In your submission, please add the dataset name as a prefix to the original file name:

R03.task4.YOURID Final submission for TestData_{jp,en}.xml

R02.task4.YOURID for riteval_R02_{jp,en}.xml
R01.task4.YOURID for riteval_R01_{jp,en}.xml
H30.task4.YOURID for riteval_H30_{jp,en}.xml

9. Presentation Schedule


TBD

10. Task Winners

The list of winners for the COLIEE 2022 edition is:
  • Task 1: UA - University of Alberta
  • Task 2: NM - NeuralMind
  • Task 3: HUKB - Knowledge Base Laboratory, Hokkaido University
  • Task 4: KIS - Kano Laboratory
Detailed list of all submissions received available here.

11. Application Details

Potential participants to COLIEE-2022 should respond to this call for participation by submitting an application. To apply, submit the application and memorandums of the following URLs to rabelo(at)ualberta.ca:

Questions and Further Information

rabelo(at)ualberta.ca

We will send an acknowledgement to the email address supplied in the form once we have processed the form.

Previous COLIEE editions

COLIEE 2021. A summary paper on the 2021 edition is available, as well as the complete proceedings.
COLIEE 2020. A summary paper on the 2020 edition is available.
COLIEE 2019. A summary paper on the 2019 edition is available.
COLIEE 2018. Summary papers on the case law tasks and statute law tasks available.
COLIEE 2017
COLIEE 2016
COLIEE 2015
COLIEE 2014


Program Committee

Randy Goebel, University of Alberta, Canada
Yoshinobu Kano, Shizuoka University, Japan
Mi-Young Kim, University of Alberta, Canada
Maria Navas Loro, Technical University of Madrid, Spain
Nguyen Le Minh, JAIST, Japan
Juliano Rabelo, University of Alberta, Canada
Julien Rossi, University of Amsterdam, The Netherlands
Ken Satoh, NII, Japan
Jaromir Savelka, University of Pittsburgh, USA
Yunqiu Shao, Tsinghua University, China
Akira Shimazu, JAIST, Japan
Satoshi Tojo, JAIST, Japan
Vu Tran, JAIST, Japan
Josef Valvoda, Cambridge University, UK
Hannes Westermann, University of Montreal, Canada
Hiroaki Yamada, Tokyo Institute of Technology, Japan
Masaharu Yoshioka, Hokkaido University, Japan
Sabine Wehnert, Otto-von-Guericke-Universität Magdeburg, Germany

Last updated: Apr, 2022