View on GitHub


Repository to track the progress in Natural Language Processing (NLP), including the datasets and the current state-of-the-art for the most common NLP tasks.

Sentiment Analysis

Sentiment analysis is the task of classifying the polarity of a given text.


The RuSentRel dataset consisted of analytical articles from Internet-portal These are translated into Russian texts in the domain of international politics obtained from foreign authoritative sources. The collected articles contain both the author’s opinion on the subject matter of the article and a large number of references mentioned between the participants of the described situations. The dataset contains 73 large analytical texts, labeled with about 2000 relations.

Sentiment Attitude Extraction task: Given a subset of documents, in which every document includes: (1) text, (2) a list of mentioned named entities. For each document it is required to complete a list of labeled entity pairs [(s1->o1, l1), … (sn->on, ln)], for which text conveys the presence of the sentiment relation expressed by the subject towards the object (si->oi) with sentiment li ∈ [neg, pos] (see the example below).

Task paper:

The public leaderboard is available at github repository

… Meanwhile Moscow has repeatedly emphasized that its activity in the Baltic Sea is a response precisely to actions of NATO and the escalation of the hostile approach to Russia near its eastern borders …
(NATO->Russia, neg), (Russia->NATO, neg)