Prediction requirements - For questions related to calories, predictions must be given in kilocalories (kcal). - For all other nutrient parameters (protein, fat, carbohydrates, etc.) predictions must be given in grams (g). - Round predictions up to 2 decimal places.Constraints - You may use any models, but model size must not exceed 4B parameters and the weights must be open. - You may not use any additional data beyond what is already provided in the competition. - A full run of the solution should be fit within Colab or Kaggle resource limits. - You are allowed to use additional tools.Notes: use the Recipe API<a target="_blank" rel="noopener noreferrer" href="https://api-ninjas.com/"> https://api-ninjas.com/</a> and Nutrition API <a target="_blank" rel="noopener noreferrer" href="https://calorieninjas.com/api">https://calorieninjas.com/api</a> (you need to register and get the free key) together with the chosen open LLM (Hugging Face) and implement tool-calling to fetch recipe and nutrition data so you can compute accurate per‑serving values.&nbsp;You can start from starting_solution.ipynb

sample.csv

test.csv

starting_solution.ipynb

You need to develop a solution to answer questions about the composition of dishes (for example, calories and macronutrients or by recipes), using large language models (LLMs) with support for tool calling. Participants are required to use an open LLM from Hugging Face together with external APIs (a Recipe API and a Nutrition API) to accurately determine the nutritional value per serving for given dishes.

Public

Agreement

Регистрируясь на курс, я даю <a href="https://storage.yandexcloud.net/ds-ods/files/content/2025/09/10/4fe2e1a5db2a/2025_09_08_%D0%A1%D0%BE%D0%B3%D0%BB%D0%B0%D1%81%D0%B8%D0%B5_%D0%BC%D0%B5%D1%80%D0%BE%D0%BF%D1%80%D0%B8%D1%8F%D1%82%D0%B8%D1%8F_%D0%B8_%D0%BA%D1%83%D1%80%D1%81%D1%8B.pdf">согласие</a> на обработку персональных данных.

first_name

First name

last_name

Last name

email

Email

telegram

Telegram

study_place

Study place

study_specialty

Study specialty

work_place

Work place

work_position

Work position

expectations

Expectations

interests

Interests

preferred_language

Preferred language

about

About

where_from_course

Откуда узнали о курсе?

nlp_student

Если в вашей учебной программе в этом семестре есть курс NLP, выберите свой вуз:

Registration application for Course Season Autumn 2025

Practical Assignment 3: Agents

Predictions

Final Projects. NLP-course. Autumn 2025

Хакатон

Final Projects

Теория

1. Introduction to Natural Language Processing

Квест

Test 1

Course block deadline expired on 30.09.2025 20:59

Block deadline expired

Materials 1

2. Machine Learning Basics and Text Classification

Test 2

Course block deadline expired on 07.10.2025 20:59

Materials 2

3. Word Embeddings

Test 3

Course block deadline expired on 14.10.2025 20:59

Materials 3

Practice word2vec Lite

Course block deadline expired on 21.10.2025 20:59

Practice Word2Vec Hard

4. Convolutional Neural Networks

Test 4

Materials 4

5. Recurrent Neural Networks and Sequence Tagging

Test 5

Course block deadline expired on 28.10.2025 20:59

Materials 5

6. Machine Translation

Test 6

Course block deadline expired on 04.11.2025 20:59

Materials 6

Practical Assignment 2: Text multiclass classification: store's review rating

Your task is to classify the store's review rating into 5 classes. The metric is F1-score.

Соревнование

Practice 2

Course block deadline expired on 11.11.2025 20:59

7. Transformers

Test 7

Materials 7

8. Large Language Models

Test 8

Course block deadline expired on 25.11.2025 20:59

Materials 8

A. Hidden Markov Models and Tagging

Test A

Materials A

B. Topic Modeling

Test B

Materials B

C. Programming Language Processing

Course block deadline expired on 16.12.2025 15:41

Materials C

D. Conversational AI

Test D

Course block deadline expired on 16.12.2025 20:59

Materials D

E. LLM Compression

Materials E

F. Reinforcement Learning for NLP

Materials F

Practice 3

Course block deadline expired on 23.12.2025 20:59

Lecturers: 
Valentin Malykh (<a href="http://val.maly.hk/" rel="noopener noreferrer" target="_blank">personal page</a>)

Logistics: 
Lectures at 18:35&nbsp;MSK at Tuesdays online. First lecture will be at 16th of September.&nbsp;

Link to join lectures: <a href="https://my.mts-link.ru/j/MTC/nlp2025autumn" rel="noopener noreferrer" target="_blank">https://my.mts-link.ru/j/MTC/nlp2025autumn</a>&nbsp;

Seminars will be separate for universities and for ODS. Look info regarding schedule in the chat.

Official support chat: <a href="https://mm.ods.ai/ods/channels/nlp_course" rel="noopener noreferrer" target="_blank">https://mm.ods.ai/ods/channels/nlp_course</a>&nbsp;

Syllabus:

<ul>
	<li>Introduction to Natural Language Processing</li>
	<li>Machine Learning Basics and Text Classification</li>
	<li>Word Embeddings
	<ul>
		<li>1st Assignment</li>
	</ul>
	</li>
	<li>Convolutional Neural Networks
	<ul>
		<li>2nd Assignment</li>
	</ul>
	</li>
	<li>Recurrent Neural Networks</li>
	<li>Statistical Machine Translation</li>
	<li>Transformers</li>
	<li>LLMs</li>
	<li>Project Consultation
	<ul>
		<li>3rd Assignment</li>
	</ul>
	</li>
</ul>

&nbsp;

Prerequisites:

<ul>
	<li>Basic Python Programming</li>
	<li>College Calculus, Linear Algebra</li>
	<li>Basic Probability and Statistics</li>
	<li>Foundations of Machine Learning</li>
</ul>

Assignments:

&nbsp; There will be two assignments on the course.

Projects: 
The participants will be suggested to work on a project during the course. The successful project development is crucial to pass the course. 
The projects from previous runs are available<a href="https://ods.ai/projects" rel="noopener noreferrer" target="_blank"> here</a>.

Natural Language Processing (NLP) is a domain of research whose objective is to analyze and understand human languages and develop technologies to enable human machine interactions with natural languages. NLP is an interdisciplinary field involving linguistics, computer sciences and artificial intelligence. The goal of this course is to provide students with comprehensive knowledge of NLP. Students will be equiped with the principles and theories of NLP, as well as various NLP technologies, including rule-based, statistical and neural network ones. After this course, students will be able to conduct NLP research and develop state-of-the-art NLP systems.

Таблица лидеров

Natural Language Processing course (stream 9, autumn 2025)

Artem Kamentsev

Максим Коновалов

Sergei

Андрей Дойников

Vladislav Golovchenko

Andrei Chupeev

Алексей Чернышев

Boris Tolstokulakov

Igor Romaykin

Kate Zinyakova

Anastasiia Gapeeva

Вадим Коробковский

Vladimir Zenin

Дмитрий Беркутов

Daniel Mokhort

Amir Diyanov

Борис Сажин

Vladislav Kiniakin

anna smekalova

Daniil Zaichenko

Maksim Kirdiashkin

Скобей Илья

Vladislav Shkarovskii

Dmitrii Osin

Vladislav Poletaev

x6a549430158f

Nastia Koneva

Аня Конева

fe19f9c3ba15f

Mark Filatov

g7acb339dcaed

София Баранецкая

Elena Data Souls

Rizvan Iskaliev

Dmitriy Gorbunov

b247ac5e66961

Nikita Studenikin

Алексей Шевченко

Daria Vegera

Анна Шумилова

p097c88304c63

t7bddffe60e0f

baseline

Anna Yurishcheva

Zakirov Timur

Александр Хамицаев

uc4e205855519

Anpilov Kirill

p5c75693a9e4f

Konstantin K

Accuracy Score

#	Teams (74)	Accuracy Score	Last	Entries
1	Artem Kamentsev	0.9	5d	34
2	Максим Коновалов	0.9	10d	12
3	Sergei	0.88	5d	16
4	Андрей Дойников	0.88	5d	4
5	Vladislav Golovchenko	0.88	3d	9
6	Andrei Chupeev	0.86	5d	5
7	Алексей Чернышев	0.86	7d	11
8	Boris Tolstokulakov	0.86	3d	15
9	Igor Romaykin	0.86	5d	6
10	Kate Zinyakova	0.86	5d	2
11	Anastasiia Gapeeva	0.86	3d	12
12	Вадим Коробковский	0.86	3d	6
13	Vladimir Zenin	0.86	4d	3
14	Дмитрий Беркутов	0.84	5d	6
15	Daniel Mokhort	0.84	3d	1
16	Amir Diyanov	0.82	5d	11
17	Борис Сажин	0.82	3d	12
18	Vladislav Kiniakin	0.82	6d	2
19	anna smekalova	0.82	4d	3
20	Daniil Zaichenko	0.82	3d	7
21	Maksim Kirdiashkin	0.82	3d	4
22	Скобей Илья	0.82	3d	2
23	Vladislav Shkarovskii	0.8	3d	11
24	Dmitrii Osin	0.8	3d	9
25	Vladislav Poletaev	0.8	8d	27
26	x6a549430158f	0.8	4d	18
27	Nastia Koneva	0.8	4d	6
28	Аня Конева	0.8	4d	3
29	fe19f9c3ba15f	0.8	3d	10
30	Mark Filatov	0.8	3d	5
31	g7acb339dcaed	0.8	3d	5
32	София Баранецкая	0.8	3d	1
33	Elena Data Souls	0.78	23d	6
34	Rizvan Iskaliev	0.78	8d	16
35	Dmitriy Gorbunov	0.78	5d	7
36	b247ac5e66961	0.78	8d	15
37	Nikita Studenikin	0.78	7d	26
38	Алексей Шевченко	0.78	4d	7
39	Daria Vegera	0.78	3d	15
40	Анна Шумилова	0.78	3d	9
41	p097c88304c63	0.78	3d	8
42	t7bddffe60e0f	0.78	3d	5
baseline strong		0.78
43	Anna Yurishcheva	0.74	3d	6
44	Zakirov Timur	0.74	3d	10
45	Александр Хамицаев	0.7	9d	7
46	uc4e205855519	0.68	3d	7
47	Anpilov Kirill	0.68	3d	10
48	p5c75693a9e4f	0.66	3d	8
49	Konstantin K	0.62	3d	25