Filters








4 Hits in 7.9 sec

BUAP: Evaluating Features for Multilingual and Cross-Level Semantic Textual Similarity

Darnes Vilariño, David Pinto, Saul Leon, Mireya Tovar, Beatriz Beltrán
2014 Proceedings of the 8th International Workshop on Semantic Evaluation (SemEval 2014)  
In this paper we present the evaluation of different features for multiligual and crosslevel semantic textual similarity.  ...  Three different types of features were used: lexical, knowledge-based and corpus-based.  ...  In this paper, we evaluate different features for determining those that obtain the best performances for calculating both, cross-level semantic similarity and multilingual semantic textual similarity.  ... 
doi:10.3115/v1/s14-2022 dblp:conf/semeval/VilarinoPLTB14 fatcat:u2uju352n5cdjmrjh7bzel756a

Semeval-2013 Task 8: Cross-lingual Textual Entailment for Content Synchronization

Matteo Negri, Alessandro Marchetti, Yashar Mehdad, Luisa Bentivogli, Danilo Giampiccolo
2013 International Workshop on Semantic Evaluation  
This paper presents the second round of the task on Cross-lingual Textual Entailment for Content Synchronization, organized within SemEval-2013.  ...  We report on the training and test data used for evaluation, the process of their creation, the participating systems (six teams, 61 runs), the approaches adopted and the results achieved.  ...  The authors would also like to acknowledge Pamela Forner and Giovanni Moretti from CELCT, and the volunteer translators that contributed to the creation of the dataset: Giusi Calo, Victoria Díaz, Bianca  ... 
dblp:conf/semeval/NegriMMBG13 fatcat:n5god77ng5auxkspgooihr7vbe

Semeval-2012 Task 8: Cross-lingual Textual Entailment for Content Synchronization

Matteo Negri, Alessandro Marchetti, Yashar Mehdad, Luisa Bentivogli, Danilo Giampiccolo
2012 International Workshop on Semantic Evaluation  
This paper presents the first round of the task on Cross-lingual Textual Entailment for Content Synchronization, organized within SemEval-2012.  ...  We report on the training and test data used for evaluation, the process of their creation, the participating systems (10 teams, 92 runs), the approaches adopted and the results achieved.  ...  The authors would also like to acknowledge Giovanni Moretti from CELCT for evaluation scripts and technical assistance, and the volunteer translators that contributed to the creation of the dataset: María  ... 
dblp:conf/semeval/NegriMMBG12 fatcat:uba2fngi55bnldjlao7elr6wkq

Counterfactual Memorization in Neural Language Models [article]

Chiyuan Zhang, Daphne Ippolito, Katherine Lee, Matthew Jagielski, Florian Tramèr, Nicholas Carlini
2021 arXiv   pre-print
As models continue to scale up in parameters, training data, and compute, understanding memorization in language models is both important from a learning-theoretical point of view, and is practically crucial  ...  We further estimate the influence of each training example on the validation set and on generated texts, and show that this can provide direct evidence of the source of memorization at test time.  ...  Moreover, it will be necessary to construct datasets where such kind of semantically similar but textually different document pairs exist.  ... 
arXiv:2112.12938v1 fatcat:72hizr3uajfyhjad7gssqjxsxi