News

• Two papers are accepted to the special issue of Semantic Web Journal (Q1) on Deep Learning for Knowledge Graphs (DL4KG). One is on taxonomy enrichment and the second one is a survey on neural entity linking.
• Alexander Panchenko is involved in the organization of the ESWC 2022 workshop on Language Interfaces for the Web of Data (NLIWoD) and the 10th Question Answering over Linked Data (QALD) Challenge. Web page.
• An invited talk at YaC/E: Yet Another Conference on Education in Yandex. Participation in a discussion on teaching data science courses and sharing my experience with teaching NLP course at Skoltech. Video
• Members of the NLP group obtain third place at the European hackathon Junction with text detoxification software. Press release, demo
• Alexander Panchenko delivers an invited talk at YaC/E: Yet Another Conference on Education in Yandex. Participation in a discussion on teaching data science courses and sharing my experience with teaching NLP course at Skoltech. Video.
• Alexander Panchenko delivers an invited talk at AI Technology In Search And Recommendation Workshop of Huawei on neural entity linking.
• Alexander Panchenko delivers an invited talk at AI Journey conference by Sberbank.
• David Dale speaks at the conference Conversations AI on dialogue systems winning an award for the best presentation.
• A new post at MTS blog about text detoxification research done with MTS-Skoltech lab.
• Daryna Dementieva presented at the 1st  workshop on NLP for Positive Impact co-located with the ACL-IJCAI 2021 conference.
• Members of the NLP group presented three talks at the Trustworthy AI conference on fake news and propaganda detection, inappropriate message detection, and text detoxification.
• An invited talk by Nikolay Babakov at the Crowd Science Seminar on detection of inappropriate messages. Video. A press release by Skoltech on the topic of this research is also available.
• An overview paper related to the CLEF laboratory on argument retrieval has been accepted to the 43rd European Conference on Information Retrieval (ECIR-2021).
• A paper has been accepted to the 8th workshop on Balto-Slavic Natural Language Processing (BSNLP) co-located with the EACL-2021 conference on detection of inappropriate messages on sensitive topics that could harm a company’s reputation (in collaboration with MTS).
• Three papers have been accepted to the 16th conference of the European Chapter of the Association for Computational Linguistics (EACL) on active learning with pre-trained language models for sequence tagging,  uncertainty estimation for transformer NLP models, and a demo on comparative question answering.
• A paper has been accepted to the 11th International Global Wordnet Conference (GWC2021) on graph-based representations for taxonomy enrichment (in collaboration with researchers from Moscow State University). Poster and video.
• Two papers have been accepted in the 9th International Conference on Analysis of Images, Social Networks, and Texts (AIST-2020) on RST parsing for the Russian language (in collaboration with Federal Research Center Computer Science and Control) and a semantic recommendation system of scientific texts (in collaboration with Higher School or Economics and University of Oslo).
• Two papers have been accepted to the 28th International Conference on Computational Linguistics (COLING-2020) on neural lexical substitution (in collaboration with researchers from Samsung) and taxonomy enrichment.
• A journal article has been accepted to the AI Magazine entitled “Conversational Intelligence Challenge: Accelerating Research with Crowd Science and Open Source” in collaboration with the MIPT.
• Two new Russian Science Foundation (RSF) grants were accepted: the first one entitled “Cross-lingual Knowledge Base Construction and Maintenance” is done in collaboration with NLP groups of Moscow State University and Higher School of Economics. The second one entitled “Uncertainty quantification of neural networks-based prediction for the design of experiments and optimization” is in collaboration with colleagues from Skoltech.
• Our group is involved in the organization of the 9th international conference on Analysis of Images, Social Networks, and Texts (AIST-2020).
• Our group is involved in the organization of the 14th workshop on graph-based natural language processing (TextGraphs-14) co-located with the 28th International Conference on Computational Linguistics (COLING’2020) in Barcelona, Spain.
• Our group is involved in the organization of the Knowledgeable NLP: the First Workshop on Integrating Structured Knowledge and Neural Networks for NLP co-located with the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 9th International Joint Conference on Natural Language Processing (AACL-IJCNLP-2020).
• Our group co-organized a shared task on Chinese-Russian machine translation co-located with the AINL-2020 conference (Turku, Finland). An overview is available here.
• A paper is accepted at the International Conference on Language Resources and Evaluation (LREC-2020) entitled “Word Sense Disambiguation for 158 Languages using Word Embeddings Only” Marseille, France
• A paper is accepted to the 26th International Conference on Computational Linguistics and Intellectual Technologies entitled “RUSSE-2020: Findings of the First Taxonomy Enrichment Task for the Russian Language” reporting results of the shared task organized by our group together with Moscow State University.
• A journal article is accepted to the Datenbank-Spektrum journal entitled “Answering Comparative Questions with Arguments” in collaboration with the University of Hamburg, Germany.
• A paper is accepted at the Probability and Meaning (PaM) conference in Gothenburg, Sweden entitled “Generating Lexical Representations of Frames using Lexical Substitution” in collaboration with the University of Hamburg, Germany.
• MTS (Mobile TeleSystems), one of the largest telecommunication companies in Russia, is provided fundings for two NLP projects in a form of a joint laboratory. We are excited to this opportunity.
• Our group co-organizes the first shared task on taxonomy enrichment for the Russian language at the Dialogue Evaluation campaign together with a researcher from Moscow State University. You are welcome to participate: the Codalab page and detailed description are available here.
• A paper is accepted at the European Conference on Information Retrieval (ECIR’2020) conference in Lisbon, Portugal entitled “Touché: The First Shared Task on Argument Retrieval” which describes the shared task organized together with German colleagues.
• Our group is involved in the organization of the 14th workshop on graph-based natural language processing (TextGraphs-14) co-located with the 28th International Conference on Computational Linguistics (COLING’2020) in Barcelona, Spain. Consider submitting a paper about some innovative applications of graph theory to NLP tasks!
• A paper was accepted at the Web Search and Data Mining (WSDM’2020) conference in Houston, the USA entitled “Comparative Web Search Questions” in collaboration with several German researchers.
• Our group is involved in the organization of a CLEF 2020 lab on Argument Mining. Technologies for argument mining and argumentation processing are maturing continuously, giving rise to the idea of retrieving arguments in search scenarios. Our CLEF lab features two subtasks (i) the retrieval of arguments from a focused debate collection to support argumentative conversations, and (ii) the retrieval of arguments from a generic web crawl to answer comparative questions with argumentative results. The goal of this lab is to perform an evaluation of various strategies to retrieve argumentative information from the web content. In this paper, we describe the setting of each subtask: the motivation, the data, and the evaluation methodology. Please consider participation in this shared task!
• A paper is accepted at the conference on Recent Advances in Natural Language Processing (RANLP’2019) in Varna, Bulgaria entitled “Combining Lexical Substitutes in Neural Word Sense Induction” in collaboration with researchers from a Samsung research center.
• A paper is accepted at the conference on Analysis of Images, Social networks and Texts (AIST’2019) in Kazan, Russia entitled “Noun Compositionality Detection using Distributional Semantics for the Russian Language”.
• Seven papers were accepted at the Association for Computational Linguistics (ACL’2019) conference and associated workshops: three papers accepted to the main conference, one demo paper, a paper at the student research workshop (main conference) and two papers at regular workshops. This presentation provides summaries of all these seven papers:
  1. Jana, A., Puzyrev, D., Panchenko, A., Goyal, P., Biemann, C., Mukherjee, A. (2019): On the Compositionality Prediction of Noun Phrases using Poincaré Embeddings.
  2. Kutuzov, A., Dorgham, M, Oliynyk, O., Biemann, C., Panchenko, A. (2019): Making Fast Graph-based Algorithms with Graph Metric Embeddings.
  3. Aly, R., Acharya, S., Ossa, A., Köhn, A., Biemann, C., Panchenko, A. (2019): Every child should have parents: a taxonomy refinement algorithm based on hyperbolic term embeddings.
  4. Chernodub, A., Oliynyk, O., Heidenreich, P., Bondarenko, A., Hagen, M., Biemann, C., Panchenko, A. (2019): TARGER: Neural Argument Mining at Your Fingertips.
  5. Sevgili, Ö., Panchenko, A., Biemann, C. (2019): Improving Neural Entity Disambiguation with Graph Embeddings.
  6. Panchenko, A., Bondarenko, A., Franzek, M., Hagen, M., Biemann, C. (2019): Categorizing Comparative Sentences.
  7. Puzyrev, D., Shelmanov, A., Panchenko, A., and Artemova, E., 2019, August. A Dataset for Noun Compositionality Detection for a Slavic Language.
• Two papers are accepted at SemEval-2019 on unsupervised semantic frame induction in collaboration with the Universities of Hamburg and Mannheim and in collaboration with Samsung research. In these two papers, ELMo and BERT contextualized word embedding models were probed in the task of semantic frame induction.
• A paper is accepted at the 8th Joint Conference on Lexical and Computational Semantics (*SEM) in Minneapolis, USA on learning graph embeddings based on graph similarity metrics.