نقيم ثلاثة أنظمة محلل التبعية الرائدة من النماذج المختلفة في مجموعة فرعية صغيرة متناثرة من اللغات من حيث أمامي باريتو الكفاءة من دقتها.نظرا لأننا مهتمون بالكفاءة، فإننا نقيم المحللين الأساسيين دون نماذج لغة محددة (لأن هذه شبكات ضخمة وعادة ما تشكل معظم الوقت لحساب الوقت) أو غيرها من التعزيزات التي يمكن تطبيقها على أي منهم.تظهر تحليل BiAffine كاختيار افتراضي متوازن، مع تحليل وضع العلامات على التسلسل هو الأفضل إذا كانت سرعة الاستدلال (ولكن لا تكلفة الطاقة التدريبية) هي الأولوية.
We evaluate three leading dependency parser systems from different paradigms on a small yet diverse subset of languages in terms of their accuracy-efficiency Pareto front. As we are interested in efficiency, we evaluate core parsers without pretrained language models (as these are typically huge networks and would constitute most of the compute time) or other augmentations that can be transversally applied to any of them. Biaffine parsing emerges as a well-balanced default choice, with sequence-labelling parsing being preferable if inference speed (but not training energy cost) is the priority.
References used
https://aclanthology.org/
MeasEval aims at identifying quantities along with the entities that are measured with additional properties within English scientific documents. The variety of styles used makes measurements, a most crucial aspect of scientific writing, challenging
We describe the DCU-EPFL submission to the IWPT 2021 Parsing Shared Task: From Raw Text to Enhanced Universal Dependencies. The task involves parsing Enhanced UD graphs, which are an extension of the basic dependency trees designed to be more facilit
Accurate recovery of predicate-argument structure from a Universal Dependency (UD) parse is central to downstream tasks such as extraction of semantic roles or event representations. This study introduces compchains, a categorization of the hierarchy
Abstract Interpretable rationales for model predictions are crucial in practical applications. We develop neural models that possess an interpretable inference process for dependency parsing. Our models adopt instance-based inference, where dependenc
This paper describes the Duluth system that participated in SemEval-2021 Task 11, NLP Contribution Graph. It details the extraction of contribution sentences and scientific entities and their relations from scholarly articles in the domain of Natural