<p>We present you 4 baseline solutions based on logistic regression, catboost, LSTM and Transformers.&nbsp;<br />
You can find them in their respective folders:&nbsp;<code>./baseline_tfidf_logreg</code>,&nbsp;<code>./&lt;catboost_baseline&gt;</code>,&nbsp;<code>./baseline_rnn</code>&nbsp;and&nbsp;<code>./&lt;transformer_baseline&gt;</code> (<a href="https://github.com/e0xextazy/nlp_huawei_new2_task" rel="noopener noreferrer" target="_blank">github repo</a> with baselines).&nbsp;</p>

<p>Each of these folders contains a file&nbsp;<code>requirements.txt</code>&nbsp;that will help you with the installation of the dependencies. To see the score and how many points you get if you can beat him, look at the table below:</p>

<figure class="table">
<table>
<thead>
<tr>
<th>baseline</th>
<th>Accuracy</th>
</tr>
</thead>
<tbody>
<tr>
<td>LogReg</td>
<td>0.43687</td>
</tr>
<tr>
<td>CatBoost</td>
<td>0.23240</td>
</tr>
<tr>
<td>LSTM</td>
<td>0.34413</td>
</tr>
<tr>
<td>Transformer</td>
<td>0.61340</td>
</tr>
</tbody>
</table>
</figure>

<p>You should beat the leaderboard baselines:&nbsp;</p>

<ul>
<li>The easy baseline has quality 0.65. If you beat it you get 12 points.</li>
<li>The hard baseline is 0.75. If you beat this baseline you get 25 point for the task. Good luck!</li>
<li>If you will be the first in your group, you&#39;ll get 3 bonus points.</li>
</ul>

Your task is to classify film descriptions into 6 classes. The metric is Accuracy.

Public

User Agreement

<p>Я прочитал(-а) и согласен(-на) с <a href="https://storage.yandexcloud.net/datasouls-ods/CourseFest_1/Docs/UserAgreement.pdf" rel="noopener noreferrer" target="_blank">Пользовательским соглашением и Политикой конфиденциальности</a></p>

Privacy Policy

<p>Я даю свое <a href="http://storage.yandexcloud.net/ds-ods/files/data/docs/events/Spring23/soglasieru.pdf">согласие</a> ООО &ldquo;Соревнования Анализа Данных&rdquo; на обработку и передачу моих персональных данных партнерам мероприятия для информационного взаимодействия&nbsp;</p>

Consent

<p>Я согласен(а) получать информационные рассылки от ООО &ldquo;Соревнования Анализа Данных&rdquo; про активности ODS</p>

<p>Мне интересно получать предложения о работе</p>

first_name

First name

last_name

Last name

country

Country (lat)

city

City (lat)

email

Email

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

Registration application for Course Season Spring 2023

Practical Assignment 2: Text multiclass classification: movie's genre

Predictions

Ruslan Sirazhetdinov

alexey-zhavoronkin

Fedor Dobryanski

Nikita Chukhrov

Vladimir_Netrepkin

Dmitrii Poliakov

Denis Tsybrick

Mikhail Shutov

Maksim Maklygin

Vladislav Shimanskii

Alexandr Migunov

Dmitrii Sudakov

Samuil Burovin

Fedor Pavlov

Rinat Mahmutov

Yuriy Kim

Leonid Dzyatko

19d1ffdb45a6

Nikita Girman

ivan tsvetkov

Andrey Popov

Daniil Avtushko

Nikita Venediktov

Rheamer

Vsevolod Vlasov

Vladimir Lazarev

Eugene Krylov

Konstantin Mitrofanov

Kirill Dubovik

Shkut Maxim

Grigorii Fetisov

Vladislav Mostovik

Alexandr Maximenko

Dmitry Kosmachev

KONSTANTIN LIKHOTA

Fomberg Vladislav

Irina Prokofieva

Eugene Astafurov

Dmitry Vedenichev

Orkhan Makhmudov

Konstantin Templin

Sergey Nichiporchik

Mikhail Lazukov

Dmitry Stepakov

Vadim Sorokin

Tatiana Zakharova

Arina Gritsai

Nikita Odinets

Yulian Gilyazev

David Moiseev

Accuracy

#	Teams (139)	Accuracy	Last	Entries
1	Ruslan Sirazhetdinov	1	18m	27
2	alexey-zhavoronkin	1	18m	7
3	Fedor Dobryanski	1	18m	8
4	Nikita Chukhrov	1	18m	5
5	Vladimir_Netrepkin	1	18m	2
6	Dmitrii Poliakov	0.9988826816	18m	3
7	Denis Tsybrick	0.9988826816	18m	15
8	Mikhail Shutov	0.9988826816	18m	5
9	Maksim Maklygin	0.9988826816	18m	4
10	Vladislav Shimanskii	0.9988826816	18m	3
11	Alexandr Migunov	0.9977653631	18m	34
12	Dmitrii Sudakov	0.9977653631	18m	10
13	Samuil Burovin	0.9966480447	18m	9
14	Fedor Pavlov	0.9966480447	18m	1
15	Rinat Mahmutov	0.9921787709	18m	26
16	Yuriy Kim	0.9921787709	18m	8
17	Leonid Dzyatko	0.9921787709	18m	8
18	19d1ffdb45a6	0.9910614525	18m	6
19	Nikita Girman	0.9251396648	18m	6
20	ivan tsvetkov	0.9162011173	18m	1
21	Andrey Popov	0.912849162	18m	11
22	Daniil Avtushko	0.9039106145	18m	6
23	Nikita Venediktov	0.9027932961	18m	4
24	Rheamer	0.8938547486	18m	3
25	Vsevolod Vlasov	0.8927374302	18m	16
26	Vladimir Lazarev	0.8748603352	18m	3
27	Eugene Krylov	0.8737430168	18m	10
28	Konstantin Mitrofanov	0.8715083799	18m	33
29	Kirill Dubovik	0.869273743	18m	23
30	Shkut Maxim	0.8636871508	18m	7
31	Grigorii Fetisov	0.8625698324	18m	9
32	Vladislav Mostovik	0.8581005587	18m	22
33	Alexandr Maximenko	0.851396648	18m	20
34	Dmitry Kosmachev	0.8469273743	18m	14
35	KONSTANTIN LIKHOTA	0.8458100559	18m	4
36	Fomberg Vladislav	0.8446927374	18m	3
37	Irina Prokofieva	0.8402234637	18m	17
38	Eugene Astafurov	0.8379888268	18m	3
39	Dmitry Vedenichev	0.8357541899	18m	4
40	Orkhan Makhmudov	0.8346368715	18m	2
41	Konstantin Templin	0.8245810056	18m	16
42	Sergey Nichiporchik	0.8223463687	18m	7
43	Mikhail Lazukov	0.8145251397	18m	9
44	Dmitry Stepakov	0.8089385475	18m	7
45	Vadim Sorokin	0.8089385475	18m	3
46	Tatiana Zakharova	0.8067039106	18m	6
47	Arina Gritsai	0.8067039106	18m	10
48	Nikita Odinets	0.8044692737	18m	3
49	Yulian Gilyazev	0.7988826816	18m	7
50	David Moiseev	0.7988826816	18m	3