Linguistic Interpretation of Effect of Words on Neural Network Operation

Student: Arshinov Grigorii

Supervisor: Oleg Durandin

Faculty: Faculty of Humanities (Nizhny Novgorod)

Educational Programme: Fundamental and Applied Linguistics (Bachelor)

Year of Graduation: 2018

The paper addresses the problem of interpretability of neural networks in NLP problems. We propose a linguistic evaluation of words that can cause a recurrent neural model to change it's descision while preforming sentiment classification task. We use a metric that was proposed by Li et al. on russian texts. We cluster words using word2vec and analyse linguistic semantics of words that affect classification quality.

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses