While neural networks are ubiquitous in state-of-the-art semantic parsers, it has been shown that most standard models suffer from dramatic performance losses when faced with compositionally out-of-distribution (OOD) data. Recently several methods ha
ve been proposed to improve compositional generalization in semantic parsing. In this work we instead focus on the problem of detecting compositionally OOD examples with neural semantic parsers, which, to the best of our knowledge, has not been investigated before. We investigate several strong yet simple methods for OOD detection based on predictive uncertainty. The experimental results demonstrate that these techniques perform well on the standard SCAN and CFQ datasets. Moreover, we show that OOD detection can be further improved by using a heterogeneous ensemble.
The current natural language processing is strongly focused on raising accuracy. The progress comes at a cost of super-heavy models with hundreds of millions or even billions of parameters. However, simple syntactic tasks such as part-of-speech (POS)
tagging, dependency parsing or named entity recognition (NER) do not require the largest models to achieve acceptable results. In line with this assumption we try to minimize the size of the model that jointly performs all three tasks. We introduce ComboNER: a lightweight tool, orders of magnitude smaller than state-of-the-art transformers. It is based on pre-trained subword embeddings and recurrent neural network architecture. ComboNER operates on Polish language data. The model has outputs for POS tagging, dependency parsing and NER. Our paper contains some insights from fine-tuning of the model and reports its overall results.
We present our contribution to the IWPT 2021 shared task on parsing into enhanced Universal Dependencies. Our main system component is a hybrid tree-graph parser that integrates (a) predictions of spanning trees for the enhanced graphs with (b) addit
ional graph edges not present in the spanning trees. We also adopt a finetuning strategy where we first train a language-generic parser on the concatenation of data from all available languages, and then, in a second step, finetune on each individual language separately. Additionally, we develop our own complete set of pre-processing modules relevant to the shared task, including tokenization, sentence segmentation, and multiword token expansion, based on pre-trained XLM-R models and our own pre-training of character-level language models. Our submission reaches a macro-average ELAS of 89.24 on the test set. It ranks top among all teams, with a margin of more than 2 absolute ELAS over the next best-performing submission, and best score on 16 out of 17 languages.
Solar Energy and Hydrogen are possible replacement options for fossil fuel, But a major drawback to the full implementation of solar energy, in particular photovoltaic (PV), is the lowering of conversion efficiency of PV cells due to elevated cell t
emperatures while in operation. Also, hydrogen must be produced in gaseous or liquid form before it can be used as fuel; but its‟ present major conversion process produces an abundance of carbon dioxide which is harming the environment through global warming. In search of resolutions to these issues, this research investigated the application of Thermal Management to Photovoltaic (PV) modules in an attempt to reverse the effects of elevated cell temperature. The investigation also examined the effects of the thermally managed PV module to a Electrolyzer (Hydrogen Generator) for the production of hydrogen gas in an environmentally friendly way.
The results of the investigation showed that the cooling system stopped the cell temperature from rising, reversed the negative effects on conversion efficiency, and increased the power output of the module by as much as 33%. The results also showed that the thermally managed PV module when coupled to the hydrogen generator impacted positively with an appreciablely increase of up to 26% in hydrogen gas production.
