Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Baan, Joris"'
With the rise of increasingly powerful and user-facing NLP systems, there is growing interest in assessing whether they have a good representation of uncertainty by evaluating the quality of their predictive distribution over outcomes. We identify tw
Externí odkaz:
http://arxiv.org/abs/2402.16102
Autor:
Baan, Joris, Daheim, Nico, Ilia, Evgenia, Ulmer, Dennis, Li, Haau-Sing, Fernández, Raquel, Plank, Barbara, Sennrich, Rico, Zerva, Chrysoula, Aziz, Wilker
Recent advances of powerful Language Models have allowed Natural Language Generation (NLG) to emerge as an important technology that can not only perform traditional tasks like summarisation or translation, but also serve as a natural language interf
Externí odkaz:
http://arxiv.org/abs/2307.15703
In Natural Language Generation (NLG) tasks, for any input, multiple communicative goals are plausible, and any goal can be put into words, or produced, in multiple ways. We characterise the extent to which human production varies lexically, syntactic
Externí odkaz:
http://arxiv.org/abs/2305.11707
Calibration is a popular framework to evaluate whether a classifier knows when it does not know - i.e., its predictive probabilities are a good indication of how likely a prediction is to be correct. Correctness is commonly estimated against the huma
Externí odkaz:
http://arxiv.org/abs/2210.16133
Attention mechanisms in deep learning architectures have often been used as a means of transparency and, as such, to shed light on the inner workings of the architectures. Recently, there has been a growing interest in whether or not this assumption
Externí odkaz:
http://arxiv.org/abs/1911.03898
Learning algorithms become more powerful, often at the cost of increased complexity. In response, the demand for algorithms to be transparent is growing. In NLP tasks, attention distributions learned by attention-based deep learning models are used t
Externí odkaz:
http://arxiv.org/abs/1907.00570
Autor:
Baan, Joris, Leible, Jana, Nikolaus, Mitja, Rau, David, Ulmer, Dennis, Baumgärtner, Tim, Hupkes, Dieuwke, Bruni, Elia
We present a detailed comparison of two types of sequence to sequence models trained to conduct a compositional task. The models are architecturally identical at inference time, but differ in the way that they are trained: our baseline model is train
Externí odkaz:
http://arxiv.org/abs/1906.01634