59 research outputs found
Findings of the LoResMT 2020 Shared Task on Zero-Shot for Low-Resource languages
No full textThis paper presents the findings of the LoResMT 2020 Shared Task on zero-shot translation for low resource languages. This task was organised as part of the 3rd Workshop on Technologies for MT of Low Resource Languages (LoResMT) at AACL-IJCNLP 2020. The focus was on the zero-shot approach as a notable development in Neural Machine Translation to build MT systems for language pairs where parallel corpora are small or even non-existent. The shared task experience suggests that back-translation and domain adaptation methods result in better accuracy for small-size datasets. We further noted that, although translation between similar languages is no cakewalk, linguistically distinct languages require more data to give better results
Symbolic-numeric implementation of the four potential method for calculating normal modes of square electromagnetic waveguide with rectangular insert
No full textIn this paper, the Maple computer algebra system is used to construct a symbolic-numeric implementation of the method for calculating normal modes of square closed waveguides in a vector formulation. The method earlier proposed by Malykh et al. [M.D. Malykh, L.A. Sevastianov, A.A. Tiutiunnik, N.E. Nikolaev. On the representation of electromagnetic fields in closed waveguides using four scalar potentials // Journal of Electromagnetic Waves and Applications, 32 (7), 886-898 (2018)] will be referred to as the method of four potentials. The Maple system is used at all stages of treating the system of differential equations for four potentials: the generation of the Galerkin basis, the substitution of approximate solution into the system under study, the formulation of a computational problem, and its approximate solution. The paper presents the results of the verification method. © 2019 Author(s)
A System for answering simple questions in multiple languages
No full textOur research focuses on the most prevalent type of queries-simple questions-exemplified by questions like "What is the capital of France-". These questions reference an entity such as "France", which is directly connected (one hop) to the answer entity "Paris" in the underlying knowledge graph (KG). We propose a multilingual Knowledge Graph Question Answering (KGQA) technique that orders potential responses based on the distance between the question s text embeddings and the answer s graph embeddings. A system incorporating this novel method is also described in our work. Through comprehensive experimentation using various English and multilingual datasets and two KGs-Freebase andWikidata-we illustrate the comparative advantage of the proposed method across diverse KG embeddings and languages. This edge is apparent even against robust baseline systems, including seq2seq QA models, search-based solutions and intricate rule-based pipelines. Interestingly, our research underscores that even advanced AI systems like ChatGPT encounter difficulties when tasked with answering simple questions. This finding emphasizes the relevance and effectiveness of our approach, which consistently outperforms such systems. We are making the source code and trained models from our study publicly accessible to promote further advancements in multilingual KGQA.Analytical Center for the Government of the Russian Federation, (000000D730321P5Q0002); Analytical Center for the Government of the Russian Federation; Russian Academy of Sciences, РАН, (70-2021-00142); Russian Academy of Sciences, РАН; Ministry of Education and Science of the Russian Federation, Minobrnauka, (075-02-2023-935); Ministry of Education and Science of the Russian Federation, MinobrnaukaPavel Braslavski’s work was supported in part by the Ministry of Science and Higher Education of the Russian Federation (project 075-02-2023-935). The work of Valentin Malykh was supported by a grant for research centers in the field of artificial intelligence, provided by the Analytical Center for the Government of the Russian Federation in accordance with the subsidy agreement (agreement identifier 000000D730321P5Q0002) and the agreement with the Ivannikov Institute for System Programming of the Russian Academy of Sciences dated November 2, 2021 No. 70-2021-00142
- …
