publications

2026

1. Large Language Models for Creation, Enrichment and Evaluation of Taxonomic Graphs

   Viktor Moskvoretskii, Irina Nikishina, Ekaterina Neminova, and 3 more authors

   Semantic Web, 2026

   Bib HTML

   @article{moskvoretskii2026taxonomic,
     title = {Large Language Models for Creation, Enrichment and Evaluation of Taxonomic Graphs},
     author = {Moskvoretskii, Viktor and Nikishina, Irina and Neminova, Ekaterina and Lobanova, Alina and Panchenko, Alexander and Biemann, Chris},
     year = {2026},
     journal = {Semantic Web},
     url = {https://doi.org/10.1177/22104968251404186},
     pages = {1--30},
     volume = {17},
     number = {1},
     doi = {10.1177/22104968251404186}
   }

2. Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages

   Saeed Almheiri, Bilal Elbouardi, Salsabila Zahirah Pranida, and 16 more authors

   In Proceedings of ACL 2026 (Volume 1: Long Papers), 2026

   Bib HTML

   @inproceedings{almheiri2026idioms,
     title = {Multilingual Idioms in Sentences and Conversations Across High-, Medium-, and Low-Resource Languages},
     author = {Almheiri, Saeed and Elbouardi, Bilal and Pranida, Salsabila Zahirah and Nikishina, Irina and B, Ashwath Rao and Krishnamurthy, Parameswari and Airlangga, Muhammad Cendekia and Genadi, Rifo Ahmad and Bao, Nguyen Phan Gia and Yari, Amir Hossein and Toyin, Hawau Olamide and Mukhituly, Nurdaulet and Attia, Mena and Hassan, Besher and Hidayatullah, Ahmad Fathan and Kuribayashi, Tatsuki and Li, Haonan and Bhat, Suma and Koto, Fajri},
     year = {2026},
     booktitle = {Proceedings of ACL 2026 (Volume 1: Long Papers)},
     url = {https://aclanthology.org/2026.acl-long.564/},
     pages = {12363--12389}
   }

3. Argument-Based Comparative Question Answering Evaluation Benchmark

   Irina Nikishina, Saba Anwar, Nikolay Dolgov, and 6 more authors

   In Proceedings of the 13th Workshop on Argument Mining and Reasoning, 2026

   Bib HTML

   @inproceedings{nikishina2026argument,
     title = {Argument-Based Comparative Question Answering Evaluation Benchmark},
     author = {Nikishina, Irina and Anwar, Saba and Dolgov, Nikolay and Manina, Maria and Ignatenko, Daria and Moskvoretskii, Viktor and Shelmanov, Artem and Baldwin, Tim and Biemann, Chris},
     year = {2026},
     booktitle = {Proceedings of the 13th Workshop on Argument Mining and Reasoning},
     url = {https://aclanthology.org/2026.argmining-1.6/},
     pages = {43--51}
   }

4. Do I look like a cat.n.01 to you? A Taxonomy Image Generation Benchmark

   Viktor Moskvoretskii, Alina Lobanova, Ekaterina Neminova, and 2 more authors

   In KONVENS 2026, 2026

   Bib HTML PDF

   @inproceedings{moskvoretskii2026cat,
     title = {Do I look like a cat.n.01 to you? A Taxonomy Image Generation Benchmark},
     author = {Moskvoretskii, Viktor and Lobanova, Alina and Neminova, Ekaterina and Panchenko, Alexander and Nikishina, Irina},
     year = {2026},
     booktitle = {KONVENS 2026},
     url = {https://konvens2026.uni-hamburg.de/index.php/dates-program/},
   }

5. Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval

   Artem Vazhentsev, Maria Marina, Daniil Moskovskiy, and 8 more authors

   arXiv preprint arXiv:2603.05471, 2026

   Bib HTML

   @article{vazhentsev2026parametric,
     title = {Leveraging LLM Parametric Knowledge for Fact Checking without Retrieval},
     author = {Vazhentsev, Artem and Marina, Maria and Moskovskiy, Daniil and Pletenev, Sergey and Seleznyov, Mikhail and Salnikov, Mikhail and Tutubalina, Elena and Konovalov, Vasily and Nikishina, Irina and Panchenko, Alexander and Moskvoretskii, Viktor},
     year = {2026},
     journal = {arXiv preprint arXiv:2603.05471},
   }

2025

1. ShortPathQA: A Dataset for Controllable Fusion of Large Language Models with Knowledge Graphs

   Mikhail Salnikov, Andrey Sakhovskiy, Irina Nikishina, and 11 more authors

   In NLDB 2025, 2025

   Bib HTML

   @inproceedings{salnikov2025shortpathqa,
     title = {ShortPathQA: A Dataset for Controllable Fusion of Large Language Models with Knowledge Graphs},
     author = {Salnikov, Mikhail and Sakhovskiy, Andrey and Nikishina, Irina and Usmanova, Aida and Kraft, Angelie and Möller, Cedric and Banerjee, Debayan and Huang, Junbo and Jiang, Longquan and Abdullah, Rana and Yan, Xi and Tutubalina, Elena and Usbeck, Ricardo and Panchenko, Alexander},
     year = {2025},
     booktitle = {NLDB 2025},
     url = {https://link.springer.com/chapter/10.1007/978-3-031-97141-9_7},
     pages = {95--110}
   }

2. ESG-Consultant: Developing of an ESG Compliance Consulting Tool for Companies Using RAG

   Angel Ontiveros, Irina Nikishina, Moritz Gomm, and 2 more authors

   In NLDB 2025 (Demo), 2025

   Bib HTML

   @inproceedings{ontiveros2025esg,
     title = {ESG-Consultant: Developing of an ESG Compliance Consulting Tool for Companies Using RAG},
     author = {Ontiveros, Angel and Nikishina, Irina and Gomm, Moritz and Schmitt, Christopher and Biemann, Chris},
     year = {2025},
     booktitle = {NLDB 2025 (Demo)},
     url = {https://link.springer.com/chapter/10.1007/978-3-031-97144-0_20},
     pages = {223--229}
   }

3. How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering

   Irina Nikishina, Saba Anwar, Nikolay Dolgov, and 4 more authors

   In Proceedings of ACL 2025 (Volume 1: Long Papers), 2025

   Bib HTML

   @inproceedings{nikishina2025compare,
     title = {How to Compare Things Properly? A Study of Argument Relevance in Comparative Question Answering},
     author = {Nikishina, Irina and Anwar, Saba and Dolgov, Nikolay and Manina, Maria and Ignatenko, Daria and Shelmanov, Artem and Biemann, Chris},
     year = {2025},
     booktitle = {Proceedings of ACL 2025 (Volume 1: Long Papers)},
     url = {https://aclanthology.org/2025.acl-long.765/},
     pages = {15702--15720}
   }

4. Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home

   Viktor Moskvoretskii, Maria Marina, Mikhail Salnikov, and 7 more authors

   In ACL 2025, 2025

   Bib HTML

   @inproceedings{moskvoretskii2025adaptive,
     title = {Adaptive Retrieval Without Self-Knowledge? Bringing Uncertainty Back Home},
     author = {Moskvoretskii, Viktor and Marina, Maria and Salnikov, Mikhail and Ivanov, Nikolay and Pletenev, Sergey and Galimzianova, Daria and Krayko, Nikita and Konovalov, Vasily and Nikishina, Irina and Panchenko, Alexander},
     year = {2025},
     booktitle = {ACL 2025},
   }

5. CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering

   Ahmad Shallouf, Irina Nikishina, and Chris Biemann

   In Proceedings of COLING 2025: System Demonstrations, 2025

   Bib HTML

   @inproceedings{shallouf2025compuge,
     title = {CompUGE-Bench: Comparative Understanding and Generation Evaluation Benchmark for Comparative Question Answering},
     author = {Shallouf, Ahmad and Nikishina, Irina and Biemann, Chris},
     year = {2025},
     booktitle = {Proceedings of COLING 2025: System Demonstrations},
     url = {https://aclanthology.org/2025.coling-demos.19/},
   }

6. Self-Taught Self-Correction for Small Language Models

   Viktor Moskvoretskii, Chris Biemann, and Irina Nikishina

   In ICLR 2025 SSI-FM Workshop, 2025

   Bib HTML

   @inproceedings{moskvoretskii2025self,
     title = {Self-Taught Self-Correction for Small Language Models},
     author = {Moskvoretskii, Viktor and Biemann, Chris and Nikishina, Irina},
     year = {2025},
     booktitle = {ICLR 2025 SSI-FM Workshop},
   }

2024

1. Creating a Taxonomy for Retrieval Augmented Generation Applications

   Irina Nikishina, Özge Sevgili, Mahei Manhai Li, and 2 more authors

   arXiv preprint arXiv:2408.02854, 2024

   Bib HTML

   @article{nikishina2024ragtaxonomy,
     title = {Creating a Taxonomy for Retrieval Augmented Generation Applications},
     author = {Nikishina, Irina and Sevgili, Özge and Li, Mahei Manhai and Biemann, Chris and Semmann, Martin},
     year = {2024},
     journal = {arXiv preprint arXiv:2408.02854},
   }

2. UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims

   Özge Sevgili, Irina Nikishina, Seid Muhie Yimam, and 2 more authors

   In Proceedings of the Seventh Fact Extraction and VERification Workshop, 2024

   Bib HTML

   @inproceedings{sevgili2024averitec,
     title = {UHH at AVeriTeC: RAG for Fact-Checking with Real-World Claims},
     author = {Sevgili, Özge and Nikishina, Irina and Yimam, Seid Muhie and Semmann, Martin and Biemann, Chris},
     year = {2024},
     booktitle = {Proceedings of the Seventh Fact Extraction and VERification Workshop},
     url = {https://aclanthology.org/2024.fever-1.5/},
   }

3. TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks

   Viktor Moskvoretskii, Ekaterina Neminova, Alina Lobanova, and 2 more authors

   In Proceedings of the 62nd Conference of the Association for Computational Linguistics, Aug 2024

   Bib

   @inproceedings{moskvoretskii-etal-2024-taxollama,
     title = {TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks},
     author = {Moskvoretskii, Viktor and Neminova, Ekaterina and Lobanova, Alina and Panchenko, Alexander and Nikishina, Irina},
     booktitle = {Proceedings of the 62nd Conference of the Association for Computational Linguistics},
     month = aug,
     year = {2024},
     address = {Bangkok, Tailand},
     publisher = {Association for Computational Linguistics},
     dimensions = {false},
   }

4. Low-Resource Machine Translation through the Lens of Personalized Federated Learning

   Viktor Moskvoretskii, Nazarii Tupitsa, Chris Biemann, and 3 more authors

   In Proceedings of the The 2024 Conference on Empirical Methods in Natural Language Processing, Nov 2024

   Abs Bib

   We present a new approach based on the Personalized Federated Learning algorithm MeritFed that can be applied to Natural Language Tasks with heterogeneous data. We evaluate it on the Low-Resource Machine Translation task, using the dataset from the Large-Scale Multilingual Machine Translation Shared Task (Small Track #2) and the subset of Sami languages from the multilingual benchmark for Finno-Ugric languages. In addition to its effectiveness, MeritFed is also highly interpretable, as it can be applied to track the impact of each language used for training. Our analysis reveals that target dataset size affects weight distribution across auxiliary languages, that unrelated languages do not interfere with the training, and auxiliary optimizer parameters have minimal impact. Our approach is easy to apply with a few lines of code, and we provide scripts for reproducing the experiments at thishttps://github.com/VityaVitalich/MeritFed

   @inproceedings{moskvoretskii2024low,
     title = {Low-Resource Machine Translation through the Lens of Personalized Federated Learning},
     author = {Moskvoretskii, Viktor and Tupitsa, Nazarii and Biemann, Chris and Horvath, Samuel and Gorbunov, Eduard and Nikishina, Irina},
     journal = {arXiv preprint arXiv:2406.12564},
     booktitle = {Proceedings of the The 2024 Conference on Empirical Methods in Natural Language Processing},
     month = nov,
     year = {2024},
     address = {Miami, USA},
     publisher = {Association for Computational Linguistics},
     dimensions = {false},
   }

5. Industry vs Academia: Running a Course on Transformers in Two Setups

   Irina Nikishina, Maria Tikhonova, Viktoria Chekalina, and 3 more authors

   In Proceedings of the Sixth Workshop on Teaching NLP, Aug 2024

   Bib

   @inproceedings{nikishina-et-al-2024-industry,
     title = {Industry vs Academia: Running a Course on Transformers in Two Setups},
     author = {Nikishina, Irina and Tikhonova, Maria and Chekalina, Viktoria and Zaytsev, Alexey and Vazhentsev, Artem and Panchenko, Alexander},
     booktitle = {Proceedings of the Sixth Workshop on Teaching NLP},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
   }

6. Soevereign at PerpectiveArg2024: Using LLMs with Argument Mining

   Robert Guenzler, Oezge Sevgili, Steffen Remus, and 2 more authors

   In Proceedings of the 11th Workshop on Argument Mining, Aug 2024

   Bib

   @inproceedings{guenzler-et-al-2024-sovereign,
     title = {Soevereign at PerpectiveArg2024: Using LLMs with Argument Mining},
     author = {Guenzler, Robert and Sevgili, Oezge and Remus, Steffen and Biemann, Chris and Nikishina, Irina},
     booktitle = {Proceedings of the 11th Workshop on Argument Mining},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
   }

7. On Improving Repository-Level Code QA for Large Language Models

   Jan Strich, Florian Schneider, Irina Nikishina, and 1 more author

   In Proceedings of the ACL Student Research Workshop, Aug 2024

   Bib

   @inproceedings{strich-et-al-2024-improving,
     title = {On Improving Repository-Level Code QA for Large Language Models},
     author = {Strich, Jan and Schneider, Florian and Nikishina, Irina and Biemann, Chris},
     booktitle = {Proceedings of the ACL Student Research Workshop},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
   }

8. TextGraphs 2024 Shared Task on Text-Graph Representations for Knowledge Graph Question Answering

   Andrey Sakhovskiy, Mikhail Salnikov, Irina Nikishina, and 11 more authors

   In Proceedings of the Seventeen Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-17), Aug 2024

   Bib

   @inproceedings{sakhovskiy-et-al-2024-textgraphs,
     title = {TextGraphs 2024 Shared Task on Text-Graph Representations for Knowledge Graph Question Answering},
     author = {Sakhovskiy, Andrey and Salnikov, Mikhail and Nikishina, Irina and Usmanova, Aida and Kraft, Angelie and Möller, Cedric and Banerjee, Debayan and Huang, Junbo and Jiang, Longquan and Abdullah, Rana and Yan, Xi and Tutubalina, Elena and Usbeck, Ricardo and Panchenko, Alexander},
     booktitle = {Proceedings of the Seventeen Workshop on Graph-Based Methods for Natural Language Processing (TextGraphs-17)},
     month = aug,
     year = {2024},
     address = {Bangkok, Thailand},
     publisher = {Association for Computational Linguistics},
   }

9. Extending the Comparative Argumentative Machine: Multilingualism and Stance Detection

   Irina Nikishina, Alexander Bondarenko, Sebastian Zaczek, and 3 more authors

   Aug 2024

   Bib

   @article{nikishinaextending,
     title = {Extending the Comparative Argumentative Machine: Multilingualism and Stance Detection},
     author = {Nikishina, Irina and Bondarenko, Alexander and Zaczek, Sebastian and Haag, Onno Lander and Hagen, Matthias and Biemann, Chris},
     booktitle = {RATIO},
     year = {2024},
   }

10. BioWiC: An Evaluation Benchmark for Biomedical Concept Representation

    Hossein Rouhizadeh, Irina Nikishina, Anthony Yazdani, and 6 more authors

    Scientific Data 11, Aug 2024

    Bib

    @article{rouhizadeh2023biowic,
      title = {BioWiC: An Evaluation Benchmark for Biomedical Concept Representation},
      author = {Rouhizadeh, Hossein and Nikishina, Irina and Yazdani, Anthony and Bornet, Alban and Zhang, Boya and Ehrsam, Julien and Gaudet-Blavignac, Christophe and Naderi, Nona and Teodoro, Douglas},
      journal = {Scientific Data 11},
      pages = {2024--11 (455)},
      year = {2024},
      publisher = {Nature},
      url = {https://www.biorxiv.org/content/10.1101/2023.11.08.566170v1}
    }

11. Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning

    Viktor Moskvoretskii, Alexander Panchenko, and Irina Nikishina

    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024

    Abs Bib

    Recent studies on LLMs do not pay enough attention to linguistic and lexical semantic tasks, such as taxonomy learning. In this paper, we explore the capacities of Large Language Models featuring LLaMA-2 and Mistral for several Taxonomy-related tasks. We introduce a new methodology and algorithm for data collection via stochastic graph traversal leading to controllable data collection. Collected cases provide the ability to form nearly any type of graph operation. We test the collected dataset for learning taxonomy structure based on English WordNet and compare different input templates for fine-tuning LLMs. Moreover, we apply the fine-tuned models on such datasets on the downstream tasks achieving state-of-the-art results on the TexEval-2 dataset.

    @inproceedings{moskvoretskii-etal-2024-large-language,
      title = {Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning},
      author = {Moskvoretskii, Viktor and Panchenko, Alexander and Nikishina, Irina},
      editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
      booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
      month = may,
      year = {2024},
      address = {Torino, Italia},
      publisher = {ELRA and ICCL},
      url = {https://aclanthology.org/2024.lrec-main.133},
      pages = {1498--1510},
      dimensions = false,
    }

12. CAM 2.0: End-to-End Open Domain Comparative Question Answering System

    Ahmad Shallouf, Hanna Herasimchyk, Mikhail Salnikov, and 5 more authors

    In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), May 2024

    Abs Bib

    Comparative Question Answering (CompQA) is a Natural Language Processing task that combines Question Answering and Argument Mining approaches to answer subjective comparative questions in an efficient argumentative manner. In this paper, we present an end-to-end (full pipeline) system for answering comparative questions called CAM 2.0 as well as a public leaderboard called CompUGE that unifies the existing datasets under a single easy-to-use evaluation suite. As compared to previous web-form-based CompQA systems, it features question identification, object and aspect labeling, stance classification, and summarization using up-to-date models. We also select the most time- and memory-effective pipeline by comparing separately fine-tuned Transformer Encoder models which show state-of-the-art performance on the subtasks with Generative LLMs in few-shot and LoRA setups. We also conduct a user study for a whole-system evaluation.

    @inproceedings{shallouf-etal-2024-cam-2,
      title = {{CAM} 2.0: End-to-End Open Domain Comparative Question Answering System},
      author = {Shallouf, Ahmad and Herasimchyk, Hanna and Salnikov, Mikhail and Garrido Veliz, Rudy Alexandro and Mestvirishvili, Natia and Panchenko, Alexander and Biemann, Chris and Nikishina, Irina},
      editor = {Calzolari, Nicoletta and Kan, Min-Yen and Hoste, Veronique and Lenci, Alessandro and Sakti, Sakriani and Xue, Nianwen},
      booktitle = {Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)},
      month = may,
      year = {2024},
      address = {Torino, Italia},
      publisher = {ELRA and ICCL},
      url = {https://aclanthology.org/2024.lrec-main.238},
      pages = {2657--2672},
      dimensions = false,
    }

2023

1. RuCAM: Comparative Argumentative Machine for the Russian Language

   Maria Maslova, Stefan Rebrikov, Anton Artsishevski, and 3 more authors

   In AIST, May 2023

   Bib

   @inproceedings{DBLP:conf/aist/MaslovaRAZBN23,
     author = {Maslova, Maria and Rebrikov, Stefan and Artsishevski, Anton and Zaczek, Sebastian and Biemann, Chris and Nikishina, Irina},
     title = {RuCAM: Comparative Argumentative Machine for the Russian Language},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {14486},
     pages = {78--91},
     publisher = {Springer},
     year = {2023},
     dimensions = {false},
   }

2. Leveraging Taxonomic Information from Large Language Models for Hyponymy Prediction

   Polina Chernomorchenko, Alexander Panchenko, and Irina Nikishina

   In AIST, May 2023

   Bib

   @inproceedings{DBLP:conf/aist/ChernomorchenkoPN23,
     author = {Chernomorchenko, Polina and Panchenko, Alexander and Nikishina, Irina},
     title = {Leveraging Taxonomic Information from Large Language Models for Hyponymy
                       Prediction},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {14486},
     pages = {49--63},
     publisher = {Springer},
     year = {2023},
   }

3. Large Language Models Meet Knowledge Graphs to Answer Factoid Questions

   Mikhail Salnikov, Hai Le, Prateek Rajput, and 4 more authors

   In Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation, Dec 2023

   Bib

   @inproceedings{salnikov-etal-2023-large,
     title = {Large Language Models Meet Knowledge Graphs to Answer Factoid Questions},
     author = {Salnikov, Mikhail and Le, Hai and Rajput, Prateek and Nikishina, Irina and Braslavski, Pavel and Malykh, Valentin and Panchenko, Alexander},
     editor = {Huang, Chu-Ren and Harada, Yasunari and Kim, Jong-Bok and Chen, Si and Hsu, Yu-Yin and Chersoni, Emmanuele and A, Pranav and Zeng, Winnie Huiheng and Peng, Bo and Li, Yuxi and Li, Junlin},
     booktitle = {Proceedings of the 37th Pacific Asia Conference on Language, Information and Computation},
     month = dec,
     year = {2023},
     address = {Hong Kong, China},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2023.paclic-1.63},
     pages = {635--644},
     dimensions = false
   }

4. Predicting Terms in IS-A Relations with Pre-trained Transformers

   Irina Nikishina, Polina Chernomorchenko, Anastasiia Demidova, and 2 more authors

   In Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings), Nov 2023

   Bib

   @inproceedings{nikishina-etal-2023-predicting,
     title = {Predicting Terms in {IS}-A Relations with Pre-trained Transformers},
     author = {Nikishina, Irina and Chernomorchenko, Polina and Demidova, Anastasiia and Panchenko, Alexander and Biemann, Chris},
     editor = {Park, Jong C. and Arase, Yuki and Hu, Baotian and Lu, Wei and Wijaya, Derry and Purwarianti, Ayu and Krisnadhi, Adila Alfa},
     booktitle = {Findings of the Association for Computational Linguistics: IJCNLP-AACL 2023 (Findings)},
     month = nov,
     year = {2023},
     address = {Nusa Dua, Bali},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2023.findings-ijcnlp.12},
     doi = {10.18653/v1/2023.findings-ijcnlp.12},
     pages = {134--148},
     dimensions = false,
   }

2022

1. Cross-Modal Contextualized Hidden State Projection Method for Expanding of Taxonomic Graphs

   Irina Nikishina, Alsu Vakhitova, Elena Tutubalina, and 1 more author

   In Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing, Oct 2022

   Abs Bib

   Taxonomy is a graph of terms organized hierarchically using is-a (hypernymy) relations. We suggest novel candidate-free task formulation for the taxonomy enrichment task. To solve the task, we leverage lexical knowledge from the pre-trained models to predict new words missing in the taxonomic resource. We propose a method that combines graph-, and text-based contextualized representations from transformer networks to predict new entries to the taxonomy. We have evaluated the method suggested for this task against text-only baselines based on BERT and fastText representations. The results demonstrate that incorporation of graph embedding is beneficial in the task of hyponym prediction using contextualized models. We hope the new challenging task will foster further research in automatic text graph construction methods.

   @inproceedings{nikishina-etal-2022-cross,
     title = {Cross-Modal Contextualized Hidden State Projection Method for Expanding of Taxonomic Graphs},
     author = {Nikishina, Irina and Vakhitova, Alsu and Tutubalina, Elena and Panchenko, Alexander},
     editor = {Ustalov, Dmitry and Gao, Yanjun and Panchenko, Alexander and Valentino, Marco and Thayaparan, Mokanarangan and Nguyen, Thien Huu and Penn, Gerald and Ramesh, Arti and Jana, Abhik},
     booktitle = {Proceedings of TextGraphs-16: Graph-based Methods for Natural Language Processing},
     month = oct,
     year = {2022},
     address = {Gyeongju, Republic of Korea},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.textgraphs-1.2},
     pages = {11--24},
     dimensions = false,
   }

2. RuArg-2022: Argument Mining Evaluation

   Evgeny V. Kotelnikov, Natalia V. Loukachevitch, Irina Nikishina, and 1 more author

   Oct 2022

   Bib

   @article{DBLP:journals/corr/abs-2206-09249,
     author = {Kotelnikov, Evgeny V. and Loukachevitch, Natalia V. and Nikishina, Irina and Panchenko, Alexander},
     title = {RuArg-2022: Argument Mining Evaluation},
     booktitle = {Computational Linguistics and Intellectual Technologies},
     year = {2022},
   }

3. RUSSE-2022: Findings of the First Russian Detoxification Task Based on Parallel Corpora

   Daryna Dementieva, Irina Nikishina, Varvara Logacheva, and 6 more authors

   Oct 2022

   Bib

   @article{russe2022detoxification,
     title = {RUSSE-2022: Findings of the First Russian Detoxification Task Based on Parallel Corpora},
     author = {Dementieva, Daryna and Nikishina, Irina and Logacheva, Varvara and Fenogenova, Alena and Dale, David and Krotova, Irina and Semenov, Nikita and Shavrina, Tatiana and Panchenko, Alexander},
     booktitle = {Computational Linguistics and Intellectual Technologies},
     year = {2022},
   }

4. TaxFree: a Visualization Tool for Candidate-free Taxonomy Enrichment

   Irina Nikishina, Ivan Andrianov, Alsu Vakhitova, and 1 more author

   In Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations, Nov 2022

   Abs Bib

   Taxonomies are widely used in a various number of downstream NLP tasks and, therefore, should be kept up-to-date. In this paper, we present TaxFree, an open source system for taxonomy visualisation and automatic Taxonomy Enrichment without pre-defined candidates on the example of WordNet-3.0. As oppose to the traditional task formulation (where the list of new words is provided beforehand), we provide an approach for automatic extension of a taxonomy using a large pre-trained language model. As an advantage to the existing visualisation tools of WordNet, TaxFree also integrates graphic representations of synsets from ImageNet. Such visualisation tool can be used for both updating taxonomies and inspecting them for the required modifications.

   @inproceedings{nikishina-etal-2022-taxfree,
     title = {{T}ax{F}ree: a Visualization Tool for Candidate-free Taxonomy Enrichment},
     author = {Nikishina, Irina and Andrianov, Ivan and Vakhitova, Alsu and Panchenko, Alexander},
     editor = {Buntine, Wray and Liakata, Maria},
     booktitle = {Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing: System Demonstrations},
     month = nov,
     year = {2022},
     address = {Taipei, Taiwan},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.aacl-demo.5},
     pages = {39--47},
     dimensions = false,
   }

5. A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification

   Varvara Logacheva, Daryna Dementieva, Irina Krotova, and 4 more authors

   In Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval), May 2022

   Abs Bib

   It is often difficult to reliably evaluate models which generate text. Among them, text style transfer is a particularly difficult to evaluate, because its success depends on a number of parameters. We conduct an evaluation of a large number of models on a detoxification task. We explore the relations between the manual and automatic metrics and find that there is only weak correlation between them, which is dependent on the type of model which generated text. Automatic metrics tend to be less reliable for better-performing models. However, our findings suggest that, ChrF and BertScore metrics can be used as a proxy for human evaluation of text detoxification to some extent.

   @inproceedings{logacheva-etal-2022-study,
     title = {A Study on Manual and Automatic Evaluation for Text Style Transfer: The Case of Detoxification},
     author = {Logacheva, Varvara and Dementieva, Daryna and Krotova, Irina and Fenogenova, Alena and Nikishina, Irina and Shavrina, Tatiana and Panchenko, Alexander},
     editor = {Belz, Anya and Popovi{\'c}, Maja and Reiter, Ehud and Shimorina, Anastasia},
     booktitle = {Proceedings of the 2nd Workshop on Human Evaluation of NLP Systems (HumEval)},
     month = may,
     year = {2022},
     address = {Dublin, Ireland},
     publisher = {Association for Computational Linguistics},
     url = {https://aclanthology.org/2022.humeval-1.8},
     pages = {90--101},
     dimensions = false,
   }

6. Taxonomy enrichment with text and graph vector representations

   Irina Nikishina, Mikhail Tikhomirov, Varvara Logacheva, and 3 more authors

   Semantic Web, May 2022

   Bib

   @article{DBLP:journals/semweb/NikishinaTLNPL22,
     author = {Nikishina, Irina and Tikhomirov, Mikhail and Logacheva, Varvara and Nazarov, Yuriy and Panchenko, Alexander and Loukachevitch, Natalia V.},
     title = {Taxonomy enrichment with text and graph vector representations},
     journal = {Semantic Web},
     volume = {13},
     number = {3},
     pages = {441--475},
     year = {2022},
   }

2021

1. Evaluation of Taxonomy Enrichment on Diachronic WordNet Versions

   Irina Nikishina, Natalia Loukachevitch, Varvara Logacheva, and 1 more author

   In Proceedings of the 11th Global Wordnet Conference, Jan 2021

   Abs Bib

   The vast majority of the existing approaches for taxonomy enrichment apply word embeddings as they have proven to accumulate contexts (in a broad sense) extracted from texts which are sufficient for attaching orphan words to the taxonomy. On the other hand, apart from being large lexical and semantic resources, taxonomies are graph structures. Combining word embeddings with graph structure of taxonomy could be of use for predicting taxonomic relations. In this paper we compare several approaches for attaching new words to the existing taxonomy which are based on the graph representations with the one that relies on fastText embeddings. We test all methods on Russian and English datasets, but they could be also applied to other wordnets and languages.

   @inproceedings{nikishina-etal-2021-evaluation,
     title = {Evaluation of Taxonomy Enrichment on Diachronic {W}ord{N}et Versions},
     author = {Nikishina, Irina and Loukachevitch, Natalia and Logacheva, Varvara and Panchenko, Alexander},
     editor = {Vossen, Piek and Fellbaum, Christiane},
     booktitle = {Proceedings of the 11th Global Wordnet Conference},
     month = jan,
     year = {2021},
     address = {University of South Africa (UNISA)},
     publisher = {Global Wordnet Association},
     url = {https://aclanthology.org/2021.gwc-1.15},
     pages = {126--136},
     dimensions = false,
   }

2. Taxonomy Enrichment with Text and Graph Vector Representation

   Irina Nikishina

   In AIST, Jan 2021

   Bib

   @inproceedings{DBLP:conf/aist/Nikishina21,
     author = {Nikishina, Irina},
     title = {Taxonomy Enrichment with Text and Graph Vector Representation},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {13217},
     pages = {9--19},
     publisher = {Springer},
     year = {2021},
   }

3. Semantic Recommendation System for Bilingual Corpus of Academic Papers

   Anna Safaryan, Petr Filchenkov, Weijia Yan, and 2 more authors

   In AIST (Supplement), Jan 2021

   Bib

   @inproceedings{DBLP:conf/aist/SafaryanFYKN20,
     author = {Safaryan, Anna and Filchenkov, Petr and Yan, Weijia and Kutuzov, Andrey and Nikishina, Irina},
     title = {Semantic Recommendation System for Bilingual Corpus of Academic Papers},
     booktitle = {{AIST} (Supplement)},
     series = {Communications in Computer and Information Science},
     volume = {1357},
     pages = {22--36},
     publisher = {Springer},
     year = {2021},
   }

2020

1. Studying Taxonomy Enrichment on Diachronic WordNet Versions

   Irina Nikishina, Varvara Logacheva, Alexander Panchenko, and 1 more author

   In Proceedings of the 28th International Conference on Computational Linguistics, Dec 2020

   Abs Bib

   Ontologies, taxonomies, and thesauri have always been in high demand in a large number of NLP tasks. However, most studies are focused on the creation of lexical resources rather than the maintenance of the existing ones and keeping them up-to-date. In this paper, we address the problem of taxonomy enrichment. Namely, we explore the possibilities of taxonomy extension in a resource-poor setting and present several methods which are applicable to a large number of languages. We also create novel English and Russian datasets for training and evaluating taxonomy enrichment systems and describe a technique of creating such datasets for other languages.

   @inproceedings{nikishina-etal-2020-studying,
     title = {Studying Taxonomy Enrichment on Diachronic {W}ord{N}et Versions},
     author = {Nikishina, Irina and Logacheva, Varvara and Panchenko, Alexander and Loukachevitch, Natalia},
     editor = {Scott, Donia and Bel, Nuria and Zong, Chengqing},
     booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
     month = dec,
     year = {2020},
     address = {Barcelona, Spain (Online)},
     publisher = {International Committee on Computational Linguistics},
     url = {https://aclanthology.org/2020.coling-main.276},
     pages = {3095--3106},
   }

2. RUSSE’2020: Findings of the First Taxonomy Enrichment Task for the Russian language

   Irina Nikishina, Varvara Logacheva, Alexander Panchenko, and 1 more author

   CoRR, Dec 2020

   Bib

   @article{DBLP:journals/corr/abs-2005-11176,
     author = {Nikishina, Irina and Logacheva, Varvara and Panchenko, Alexander and Loukachevitch, Natalia V.},
     title = {RUSSE'2020: Findings of the First Taxonomy Enrichment Task for the
                       Russian language},
     journal = {CoRR},
     volume = {abs/2005.11176},
     year = {2020},
   }

2019

1. Deep JEDi: Deep Joint Entity Disambiguation to Wikipedia for Russian

   Andrey Sysoev, and Irina Nikishina

   In AIST, Dec 2019

   Bib

   @inproceedings{DBLP:conf/aist/SysoevN19,
     author = {Sysoev, Andrey and Nikishina, Irina},
     title = {Deep JEDi: Deep Joint Entity Disambiguation to Wikipedia for Russian},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {11832},
     pages = {230--241},
     publisher = {Springer},
     year = {2019},
   }

2. Double-Blind Peer-Reviewing and Inclusiveness in Russian NLP Conferences

   Andrey Kutuzov, and Irina Nikishina

   In AIST, Dec 2019

   Bib

   @inproceedings{DBLP:conf/aist/KutuzovN19,
     author = {Kutuzov, Andrey and Nikishina, Irina},
     title = {Double-Blind Peer-Reviewing and Inclusiveness in Russian {NLP} Conferences},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {11832},
     pages = {3--8},
     publisher = {Springer},
     year = {2019},
   }

2018

1. RusNLP: Semantic Search Engine for Russian NLP Conference Papers

   Irina Nikishina, Amir Bakarov, and Andrey Kutuzov

   In AIST, Dec 2018

   Bib

   @inproceedings{DBLP:conf/aist/NikishinaBK18,
     author = {Nikishina, Irina and Bakarov, Amir and Kutuzov, Andrey},
     title = {RusNLP: Semantic Search Engine for Russian {NLP} Conference Papers},
     booktitle = {{AIST}},
     series = {Lecture Notes in Computer Science},
     volume = {11179},
     pages = {111--120},
     publisher = {Springer},
     year = {2018},
   }

2. Smart Context Generation for Disambiguation to Wikipedia

   Andrey Sysoev, and Irina Nikishina

   In Artificial Intelligence and Natural Language, Dec 2018

   Bib

   @inproceedings{Sysoev2018SmartCG,
     title = {Smart Context Generation for Disambiguation to Wikipedia},
     author = {Sysoev, Andrey and Nikishina, Irina},
     booktitle = {Artificial Intelligence and Natural Language},
     year = {2018},
     url = {https://api.semanticscholar.org/CorpusID:69842254},
   }

3. Russian computational linguistics: topical structure in 2007–2017 conference papers

   Amir Bakarov, Andrey Kutuzov, and Irina Nikishina

   Proceedings of Dialogue-2018, online papers. ABBYY, Dec 2018

   Bib

   @article{bakarov2018russian,
     title = {Russian computational linguistics: topical structure in 2007--2017 conference papers},
     author = {Bakarov, Amir and Kutuzov, Andrey and Nikishina, Irina},
     journal = {Proceedings of Dialogue-2018, online papers. ABBYY},
     year = {2018},
   }