Automatic syntactic analysis of a sentence is an important computational linguistics task. At present, there are no syntactic structure parsers for Russian that are publicly available and suitable for practical applications. Ground-up creation of such parsers requires building of a treebank annotated according to a given formal grammar, which is quite a cumbersome task. However, since there are several syntactic dependency parsers for Russian, it seems reasonable to employ dependency parsing results for syntactic structure analysis. The article introduces an algorithm that allows to construct the constituency tree of a Russian sentence by a syntactic dependency tree. The formal grammar used by the algorithm is based on the D.E. Rosenthal’s classic reference. The algorithm was evaluated on 300 Russian-language sentences. 200 of them were selected from the aforementioned reference, and 100 from OpenCorpora, an open corpus of sentences extracted from Russian news and periodicals. During the evaluation, the sentences were passed to syntactic dependency parsers from Stanza, SpaCy, and Natasha packages, then the resulted dependency trees were processed by the proposed algorithm. The obtained constituency trees were compared with the trees manually annotated by experts in linguistics. The best performance was achieved using the Stanza parser: the constituency parsing F1–score was 0.85, and the sentence parts tagging accuracy was 0.93, that would be sufficient for many practical applications, such as event extraction, information retrieval and sentiment analysis.
In recent years the interest in automatic depression detection has grown within medical and scientific-technical communities. Depression is one of the most widespread mental illnesses that affects human life. In this review we present and analyze the latest researches devoted to depression detection. Basic notions related to the definition of depression were specified, the review includes both unimodal and multimodal corpora containing records of informants diagnosed with depression and control groups of non-depressed people. Theoretical and practical researches which present automated systems for depression detection were reviewed. The last ones include unimodal as well as multimodal systems. A part of reviewed systems addresses the challenge of regressive classification predicting the degree of depression severity (non-depressed, mild, moderate and severe), and another part solves a problem of binary classification predicting the presence of depression (if a person is depressed or not). An original classification of methods for computing of informative features for three communicative modalities (audio, video, text information) is presented. New methods for depression detection in every modality and all modalities in total are defined. The most popular methods for depression detection in reviewed studies are neural networks. The survey has shown that the main features of depression are psychomotor retardation that affects all communicative modalities and strong correlation with affective values of valency, activation and domination, also there has been observed an inverse correlation between depression and aggression. Discovered correlations confirm interrelation of affective disorders and human emotional states. The trend observed in many reviewed papers is that combining modalities improves the results of depression detection systems.
Recently, Speech Emotion Recognition (SER) has become an important research topic of affective computing. It is a difficult problem, where some of the greatest challenges lie in the feature selection and representation tasks. A good feature representation should be able to reflect global trends as well as temporal structure of the signal, since emotions naturally evolve in time; it has become possible with the advent of Recurrent Neural Networks (RNN), which are actively used today for various sequence modeling tasks. This paper proposes a hybrid approach to feature representation, which combines traditionally engineered statistical features with Long Short-Term Memory (LSTM) sequence representation in order to take advantage of both short-term and long-term acoustic characteristics of the signal, therefore capturing not only the general trends but also temporal structure of the signal. The evaluation of the proposed method is done on three publicly available acted emotional speech corpora in three different languages, namely RUSLANA (Russian speech), BUEMODB (Turkish speech) and EMODB (German speech). Compared to the traditional approach, the results of our experiments show an absolute improvement of 2.3% and 2.8% for two out of three databases, and a comparative performance on the third. Therefore, provided enough training data, the proposed method proves effective in modelling emotional content of speech utterances.
1 - 3 of 3 items