NSTL国家科技图书文献中心

1. Are Large Language Models Good at Lexical Semantics? A Case of Taxonomy Learning NSTL国家科技图书文献中心

Viktor Moskvoretskii | Alexander Panchenko ... - 《2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation,Vol. 3》 - Joint International Conference on Computational Linguistics, Language Resources and Evaluation - 2024, - 1498～1510 - 共13页

摘要：Recent studies on LLMs do not pay enousdfgh attention to linguistic and lexical semantic tasks, such as taxonomy learning. In this paper, we explore the capacities of Large Language Models featuring L...

关键词： taxonomy construction | WordNet | hypernym prediction | LLMs

2. Leveraging Taxonomic Information from Large Language Models for Hyponymy Prediction NSTL国家科技图书文献中心

Polina Chernomorchen... | Alexander Panchenko ... - 《Analysis of Images, Social Networks and Texts: 11th International Conference, AIST 2023, Yerevan, Armenia, September 28-30, 2023, Revised Selected Papers》 - International Conference on Analysis of Images, Social Networks, and Texts - 2024, - 49～63 - 共15页

摘要：Pre-trained language models contain a vast amount of linguistic information as well as knowledge about the structure of the world. Both of these attributes are extremely beneficial for automatic enric...

关键词： Taxonomy enrichment | IS-A relations | Generative transformers | Hyponym prediction

3. RuCAM: Comparative Argumentative Machine for the Russian Language NSTL国家科技图书文献中心

Maria Maslova | Stefan Rebrikov ... - 《Analysis of Images, Social Networks and Texts: 11th International Conference, AIST 2023, Yerevan, Armenia, September 28-30, 2023, Revised Selected Papers》 - International Conference on Analysis of Images, Social Networks, and Texts - 2024, - 78～91 - 共14页

摘要：Comparative question answering is one of the question answering subtasks which requires not only to choose between two (or more) objects, but also to explain the choice and support it with arguments. ...

关键词： Comparative question answering | Russian language | Comparative question identification | Question answering

4. Extending the Comparative Argumentative Machine: Multilingualism and Stance Detection NSTL国家科技图书文献中心

Irina Nikishina | Alexander Bondarenko ... - 《Robust Argumentation Machines: First International Conference, RATIO 2024, Bielefeld, Germany, June 5-7, 2024, Proceedings》 - International Conference on Robust Argumentation Machines - 2024, - 317～334 - 共18页

摘要：The comparative argumentative machine CAM can retrieve arguments that answer comparative questions - questions that ask which of several to-be-compared options should be favored in some scenario. In t...

关键词： Answering comparative questions | Argumentation machines | Answer stance detection | Cross-Language argument retrieval

5. CAM 2.0: End-to-End Open Domain Comparative Question Answering System NSTL国家科技图书文献中心

Ahmad Shallouf | Hanna Herasimchyk ... - 《2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation,Vol. 4》 - Joint International Conference on Computational Linguistics, Language Resources and Evaluation - 2024, - 2657～2672 - 共16页

摘要：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...

关键词： comparative question answering | system demonstration | question answering | question classification | sequence tagging | stance classification | multi-sentence summarization

6. Taxonomy Enrichment with Text and Graph Vector Representation NSTL国家科技图书文献中心

Irina Nikishina - 《Analysis of Images, Social Networks and Texts: 10th International Conference, AIST 2021, Tbilisi, Georgia, December 16-18, 2021, Revised Selected Papers》 - International Conference on Analysis of Images, Social Networks, and Texts - 2022, - 9～19 - 共11页

摘要：Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with hypo-hypernym ("class-subc...

关键词： Knowledge graphs | Taxonomy enrichment | Graph vector representation

7. Deep JEDi: Deep Joint Entity Disambiguation to Wikipedia for Russian NSTL国家科技图书文献中心

Andrey Sysoev | Irina Nikishina - 《Analysis of Images, Social Networks and Texts: 8th International Conference, AIST 2019, Kazan, Russia, July 17–19, 2019, Revised Selected Papers》 - International Conference on Analysis of Images, Social Networks, and Texts - 2019, - 230～241 - 共12页

摘要：Over the past few years there has been a leap forward in both Entity Disambiguation and Entity Linking tasks. Meanwhile, Entity Disambiguation for Russian still lags behind advanced neural approaches ...

关键词： Disambiguation to wikipedia | Wikification for russian | Encoder-decoder neural network architecture | Joint embeddings | Sequence labeling

NSTL主题词： Wikipedia | Russian | Joints | Joints

8. RusNLP: Semantic Search Engine for Russian NLP Conference Papers NSTL国家科技图书文献中心

Irina Nikishina | Amir Bakarov ... - 《Analysis of Images, Social Networks and Texts: 7th International Conference, AIST 2018, Moscow, Russia, July 5–7, 2018, Revised Selected Papers》 - International Conference on Analysis of Images, Social Networks, and Texts - 2018, - 111～120 - 共10页

摘要：We present RusNLP, a web service implementing semantic search engine and recommendation system over proceedings of three major Russian NLP conferences (Dialogue, AIST and AINL). The collected corpus s...

关键词： Information retrieval | Semantic similarity | Scientific literature search | Document representations | Academic communities

NSTL主题词： Search engines | Conference Papers | NINL gene | Natural Language Processing | Russian | Semantics

9. On Improving Repository-Level Code QA for Large Language Models NSTL国家科技图书文献中心

Jan Strich | Florian Schneider ... - 《62nd Annual Meeting of the Association for Computational Linguistics.Student Research Workshop》 - Annual meeting of the Association for Computational Linguistics - 2024, - 303～338 - 共36页

摘要：Large Language Models (LLMs) such as Chat-GPT, GitHub Copilot, Llama, or Mistral assist programmers as copilots and knowledge sources to make the coding process faster and more efficient. This paper a...

10. TaxoLLaMA: WordNet-based Model for Solving Multiple Lexical Semantic Tasks NSTL国家科技图书文献中心

Viktor Moskvoretskii | Ekaterina Neminova ... - 《62nd annual meeting of the Association for Computational Linguistics,vol. 4.Long papers》 - Annual meeting of the Association for Computational Linguistics - 2024, - 2331～2350 - 共20页

摘要：In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the ou...

摘要：Recent studies on LLMs do not pay enousdfgh attention to linguistic and lexical semantic tasks, such as taxonomy learning. In this paper, we explore the capacities of Large Language Models featuring L...

关键词： taxonomy construction | WordNet | hypernym prediction | LLMs

摘要：Pre-trained language models contain a vast amount of linguistic information as well as knowledge about the structure of the world. Both of these attributes are extremely beneficial for automatic enric...

关键词： Taxonomy enrichment | IS-A relations | Generative transformers | Hyponym prediction

摘要：Comparative question answering is one of the question answering subtasks which requires not only to choose between two (or more) objects, but also to explain the choice and support it with arguments. ...

关键词： Comparative question answering | Russian language | Comparative question identification | Question answering

摘要：The comparative argumentative machine CAM can retrieve arguments that answer comparative questions - questions that ask which of several to-be-compared options should be favored in some scenario. In t...

关键词： Answering comparative questions | Argumentation machines | Answer stance detection | Cross-Language argument retrieval

摘要：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...

关键词： comparative question answering | system demonstration | question answering | question classification | sequence tagging | stance classification | multi-sentence summarization

摘要：Knowledge graphs such as DBpedia, Freebase or Wikidata always contain a taxonomic backbone that allows the arrangement and structuring of various concepts in accordance with hypo-hypernym ("class-subc...

关键词： Knowledge graphs | Taxonomy enrichment | Graph vector representation

摘要：Over the past few years there has been a leap forward in both Entity Disambiguation and Entity Linking tasks. Meanwhile, Entity Disambiguation for Russian still lags behind advanced neural approaches ...

关键词： Disambiguation to wikipedia | Wikification for russian | Encoder-decoder neural network architecture | Joint embeddings | Sequence labeling

NSTL主题词： Wikipedia | Russian | Joints | Joints

摘要：We present RusNLP, a web service implementing semantic search engine and recommendation system over proceedings of three major Russian NLP conferences (Dialogue, AIST and AINL). The collected corpus s...

关键词： Information retrieval | Semantic similarity | Scientific literature search | Document representations | Academic communities

NSTL主题词： Search engines | Conference Papers | NINL gene | Natural Language Processing | Russian | Semantics

摘要：Large Language Models (LLMs) such as Chat-GPT, GitHub Copilot, Llama, or Mistral assist programmers as copilots and knowledge sources to make the coding process faster and more efficient. This paper a...

摘要：In this paper, we explore the capabilities of LLMs in capturing lexical-semantic knowledge from WordNet on the example of the LLaMA-2-7b model and test it on multiple lexical semantic tasks. As the ou...

4008-161-200 800-990-8900

国家科技图书文献中心