The Second "Mobile Cloud Cup" Computing Power Network Application Innovation Competition Has Been Launched
Do you still have a lot of question marks about the competition questions?
So, let's take a look at today's spoiler
University Track - Legal Science and Technology Innovation Sub-track
Track introduction :
This track is aimed at college students across the country. It is divided into the "Software Cup" direct push sub-track, the legal science and technology innovation sub-track, the computing network scheduling application sub-track and the nine-day application sub-track. For outstanding talents, adopt the method of algorithm plus application creativity competition to promote the innovation and cultivation of talents in colleges and universities, and help China Mobile's digital transformation and development.
Competition topic introduction :
University Track - Legal Science and Technology Innovation Sub-track
Title of the competition : Sensitive relationship identification in legal documents
Topic background :
Information extraction is one of the basic tasks of natural language processing. Information extraction can assist judicial case handlers to efficiently review files and quickly clarify case information. It can also provide a research basis for legal intelligence technologies such as knowledge graph construction, similar case recommendation, and automatic sentencing recommendations.
Competition task :
This task focuses on the extraction of sensitive person relationships in legal texts. The entity type is the person involved in the case. The participating teams need to identify the entity-relationship triples in the text and return the results in a prescribed format. For example, in the text "5. Testimony of witness Wang Mouyi (son of Wang Moujia)", the participating teams need to use models and algorithms to analyze the input text and identify the entities contained in it ("Wang Mouyi" and "Wang Moujia") , while judging the relationship category between name entities: parent-child.
Description of the competition :
In order to reduce the difficulty of the competition, the contestants of the name recognition function in the competition task can call the named entity recognition of mobile nine days or use open source implementation; the relationship recognition function needs to be implemented by themselves. The model submitted by the contestant should contain all functional modules, and it is not allowed to call other external services through the network, otherwise it will be considered a violation and the competition result will be cancelled.
Data description :
The data set used in this task comes from the judgment documents published by the Judgment Documents Network.
`label.txt` is a label file, each line is a relationship category
`train.txt` is the training set, which contains several pieces of data, and the field information of each piece of data is as follows:
`ID`: represents the ID of the piece of data
`sentence`: sentence content in the referee document
`relation`: the relationship between entity pairs in this data
`head`: the first entity in the sentence
`name`: entity content
`pos`: list, the index of the entity in the sentence
`tail`: the second entity in the sentence
`name`: entity content
`pos`: list, the index of the entity in the sentence
The fields `relation`, `head`, and `tail` are not included in the final test set, and the contestants predict entity pairs and relation fields corresponding to entities based on `sentence`
Data sample:
{
"sentence": "同事周某和蒋宗志将伍刚鼎重新控制后，才将其带离现场",
"head": {"name": "周某", "pos": [2, 4]},
"tail": {"name": "蒋宗志", "pos": [5, 8]},
"relation": "同事", "id": "9957b9fc-2481-4df4-ac47-0588eb6ddec5"
}Baseline description:
We provide a baseline model based on text-cnn, the code and usage are in the baseline folder
Schedule :
1. Registration, work preparation and submission from late May to mid-August 2023
2. Preliminary race on the track from mid-August to late August 2023
3. Submissions for the semi-finals will be from early September to mid-September 2023
4. The rematch on the track will be from mid-September to early October 2023
5. Submission of works for the track finals will be in mid-October 2023
6. Track finals in late October 2023
7. National finals and awards in November 2023
Note: The preliminary competition will be judged by the online expert system, the semi-finals will be an online roadshow, and the track finals and national finals will be carried out in the form of offline/online roadshows depending on the situation. If the competition schedule is adjusted, please pay attention to the official website of the competition, communication groups, emails and other notifications.
Registration requirements :
1. Registration method
Use your mobile cloud account to log in to the official website of the competition, click the "I want to participate" button on the competition page to register, and complete real-name authentication when submitting your work (click "upper right corner-account center-real-name authentication). (If you have any questions, please check: Download- Mobile Cloud Cup Competition Registration Process Manual)
2. Form a team
Each person can only participate in one team in each track, and entries are submitted in teams. Players are invited to form teams freely, and each team is limited to 2-5 people. After successful registration, players can create a team in "My Team" or join an existing team. The player who creates the team is the captain. The captain cannot create two or more teams across the track at the same time.
3. Resource acquisition method :
Use the Mobile Cloud Internet account to obtain resources through the Internet free trial policy.
If you have any questions during the competition, you can contact the competition assistant for consultation.