More Embeddings, Better Sequence Labelers?
Recent work proposes a family of contextual embeddings that significantly improves the accuracy of sequence labelers over non-contextual embeddings. However, there is no definite conclusion on whether we can build better sequence labelers by combining different kinds of embeddings in various settings. In this paper, we conduct extensive experiments on 3 tasks over 18 datasets and 8 languages to study the accuracy of sequence labeling with various embedding concatenations and make three observations: (1) concatenating more embedding variants leads to better accuracy in rich-resource and cross-domain settings and some conditions of low-resource settings; (2) concatenating additional contextual sub-word embeddings with contextual character embeddings hurts the accuracy in extremely low-resource settings; (3) based on the conclusion of (1), concatenating additional similar contextual embeddings cannot lead to further improvements. We hope these conclusions can help people build stronger sequence labelers in various settings.
Code (0)
등록된 구현이 없습니다.
Tasks
ChunkingWord EmbeddingsSimilar Papers 제목 키워드 기반
Neural Semantic Role Labeling with Dependency Path Embeddings
This paper introduces a novel model for semantic role labeling that makes use of neural sequence modeling techniques. Our approach is motivated by the observation that complex syntactic structures and related phenomena, …
Semantic Role LabelingVariational Sequential Labelers for Semi-Supervised Learning
We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative labeler. The generative models use latent…
Learning Word EmbeddingsWord EmbeddingsHuman-Machine Collaboration for Fast Land Cover Mapping
We propose incorporating human labelers in a model fine-tuning system that provides immediate user feedback. In our framework, human labelers can interactively query model predictions on unlabeled data, choose which data…
Active LearningBeauty in the Eye of AI: Aligning LLMs and Vision Models with Human Aesthetics in Network Visualization
Network visualization has traditionally relied on heuristic metrics, such as stress, under the assumption that optimizing them leads to aesthetic and informative layouts. However, no single metric consistently produces t…
Prompt EngineeringImproved Adaptive Algorithm for Scalable Active Learning with Weak Labeler
Active learning with strong and weak labelers considers a practical setting where we have access to both costly but accurate strong labelers and inaccurate but cheap predictions provided by weak labelers. We study this p…
Active Learning