Zobrazeno 1 - 10
of 199
pro vyhledávání: '"Androutsopoulos, Ion"'
Autor:
Kaliosis, Panagiotis, Pavlopoulos, John, Charalampakos, Foivos, Moschovis, Georgios, Androutsopoulos, Ion
Diagnostic Captioning (DC) automatically generates a diagnostic text from one or more medical images (e.g., X-rays, MRIs) of a patient. Treated as a draft, the generated text may assist clinicians, by providing an initial estimation of the patient's
Externí odkaz:
http://arxiv.org/abs/2406.14164
Creating effective and reliable task-oriented dialog systems (ToDSs) is challenging, not only because of the complex structure of these systems, but also due to the scarcity of training data, especially when several modules need to be trained separat
Externí odkaz:
http://arxiv.org/abs/2406.06127
The SemEval task on Argument Reasoning in Civil Procedure is challenging in that it requires understanding legal concepts and inferring complex arguments. Currently, most Large Language Models (LLM) excelling in the legal realm are principally purpos
Externí odkaz:
http://arxiv.org/abs/2405.08502
NLP research has explored different neural model architectures and sizes, datasets, training objectives, and transfer learning techniques. However, the choice of optimizer during training has not been explored as extensively. Typically, some variant
Externí odkaz:
http://arxiv.org/abs/2402.06948
Prompting Large Language Models (LLMs) performs impressively in zero- and few-shot settings. Hence, small and medium-sized enterprises (SMEs) that cannot afford the cost of creating large task-specific training datasets, but also the cost of pretrain
Externí odkaz:
http://arxiv.org/abs/2310.13395
Pre-trained Transformers currently dominate most NLP tasks. They impose, however, limits on the maximum input length (512 sub-words in BERT), which are too restrictive in the legal domain. Even sparse-attention models, such as Longformer and BigBird,
Externí odkaz:
http://arxiv.org/abs/2211.00974
Autor:
Xenouleas, Stratos, Tsoukara, Alexia, Panagiotakis, Giannis, Chalkidis, Ilias, Androutsopoulos, Ion
We consider zero-shot cross-lingual transfer in legal topic classification using the recent MultiEURLEX dataset. Since the original dataset contains parallel documents, which is unrealistic for zero-shot cross-lingual transfer, we develop a new versi
Externí odkaz:
http://arxiv.org/abs/2206.03785
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult. We experiment with data from the BioASQ challenge, which we au
Externí odkaz:
http://arxiv.org/abs/2204.04711
Autor:
Loukas, Lefteris, Fergadiotis, Manos, Chalkidis, Ilias, Spyropoulou, Eirini, Malakasiotis, Prodromos, Androutsopoulos, Ion, Paliouras, Georgios
Publicly traded companies are required to submit periodic reports with eXtensive Business Reporting Language (XBRL) word-level tags. Manually tagging the reports is tedious and costly. We, therefore, introduce XBRL tagging as a new entity extraction
Externí odkaz:
http://arxiv.org/abs/2203.06482
Autor:
Xenos, Alexandros, Pavlopoulos, John, Androutsopoulos, Ion, Dixon, Lucas, Sorensen, Jeffrey, Laugier, Leo
User posts whose perceived toxicity depends on the conversational context are rare in current toxicity detection datasets. Hence, toxicity detectors trained on existing datasets will also tend to disregard context, making the detection of context-sen
Externí odkaz:
http://arxiv.org/abs/2111.10223