TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
Natural Language Inference	SNLI	512D Dynamic Meta-Embeddings	% Test Accuracy	86.7	# 52
Natural Language Inference	SNLI	512D Dynamic Meta-Embeddings	% Train Accuracy	91.6	# 34
Natural Language Inference	SNLI	512D Dynamic Meta-Embeddings	Parameters	9m	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/dynamic-meta-embeddings-for-improved-sentence/natural-language-inference-on-snli)](https://paperswithcode.com/sota/natural-language-inference-on-snli?p=dynamic-meta-embeddings-for-improved-sentence)`

Dynamic Meta-Embeddings for Improved Sentence Representations

EMNLP 2018 · Douwe Kiela, Changhan Wang, Kyunghyun Cho ·

While one of the first steps in many NLP systems is selecting what pre-trained word embeddings to use, we argue that such a step is better left for neural networks to figure out by themselves. To that end, we introduce dynamic meta-embeddings, a simple yet effective method for the supervised learning of embedding ensembles, which leads to state-of-the-art performance within the same model class on a variety of tasks. We subsequently show how the technique can be used to shed new light on the usage of word embeddings in NLP systems.