Learning to reason over scene graphs: a case study of finetuning GPT-2 into a robot language model for grounded task planning

Autor: Georgia Chalvatzaki, Ali Younes, Daljeet Nandha, An Thai Le, Leonardo F. R. Ribeiro, Iryna Gurevych

Publikováno v: Frontiers in Robotics and AI, Vol 10 (2023)

Long-horizon task planning is essential for the development of intelligent assistive and service robots. In this work, we investigate the applicability of a smaller class of large language models (LLMs), specifically GPT-2, in robotic task planning b

Externí odkaz: https://doaj.org/article/4fcfd322123f48e8bfb5e0661410de4c

UKP-SQUARE: An Online Platform for Question Answering Research

Autor: Tim Baumgärtner, Kexin Wang, Rachneet Sachdeva, Gregor Geigle, Max Eichler, Clifton Poth, Hannah Sterz, Haritz Puerto, Leonardo F. R. Ribeiro, Jonas Pfeiffer, Nils Reimers, Gözde Şahin, Iryna Gurevych

Publikováno v: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics: System Demonstrations.

Recent advances in NLP and information retrieval have given rise to a diverse set of question answering tasks that are of different formats (e.g., extractive, abstractive), require different model architectures (e.g., generative, discriminative), and

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::374383fb6ad1041053b6d785d8fe66cd
https://doi.org/10.18653/v1/2022.acl-demo.2

Modeling Graph Structure via Relative Position for Text Generation from Knowledge Graphs

Autor: Martin Schmitt, Iryna Gurevych, Leonardo F. R. Ribeiro, Philipp Dufter, Hinrich Schütze

We present Graformer, a novel Transformer-based encoder-decoder architecture for graph-to-text generation. With our novel graph self-attention, the encoding of a node relies on all nodes in the input graph - not only direct neighbors - facilitating t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::ddff61efdf6daf3267059a649fe4c503

Enhancing AMR-to-Text Generation with Dual Graph Representations

Autor: Iryna Gurevych, Leonardo F. R. Ribeiro, Claire Gardent

Publikováno v: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing
2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing, Nov 2019, Hong Kong, China. pp.3181--3192, ⟨10.18653/v1/D19-1314⟩
EMNLP/IJCNLP (1)

Generating text from graph-based data, such as Abstract Meaning Representation (AMR), is a challenging task due to the inherent difficulty in how to properly encode the structure of a graph with labeled edges. To address this difficulty, we propose a

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d90d8df32ad30d86d3b66d0b64006193
https://hal.science/hal-02277053/document

Performance of Monte Carlo Tree Search Algorithms when Playing the Game Ataxx

Autor: Daniel R. Figueiredo, Leonardo F. R. Ribeiro

Publikováno v: Anais do XV Encontro Nacional de Inteligência Artificial e Computacional (ENIAC 2018).

Monte Carlo Tree Search (MCTS) has recently emerged as a promising technique to play games with very large state spaces. Ataxx is a simple two-player board game with large and deep game tree. In this work, we apply different MCTS algorithms to play t

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=doi_________::ef14acfa853e1e2cf1b777a0ce926a49
https://doi.org/10.5753/eniac.2018.4423