Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

by   Sam Wiseman, et al.
Toyota Technological Institute at Chicago

Retrieve-and-edit based approaches to structured prediction, where structures associated with retrieved neighbors are edited to form new structures, have recently attracted increased interest. However, much recent work merely conditions on retrieved structures (e.g., in a sequence-to-sequence framework), rather than explicitly manipulating them. We show we can perform accurate sequence labeling by explicitly (and only) copying labels from retrieved neighbors. Moreover, because this copying is label-agnostic, we can achieve impressive performance in zero-shot sequence-labeling tasks. We additionally consider a dynamic programming approach to sequence labeling in the presence of retrieved neighbors, which allows for controlling the number of distinct (copied) segments used to form a prediction, and leads to both more interpretable and accurate predictions.


page 1

page 2

page 3

page 4


k-Nearest Neighbors by Means of Sequence to Sequence Deep Neural Networks and Memory Networks

k-Nearest Neighbors is one of the most fundamental but effective classif...

A Sequence-to-Sequence Model for Semantic Role Labeling

We explore a novel approach for Semantic Role Labeling (SRL) by casting ...

Few-Shot Sequence Labeling with Label Dependency Transfer

Few-shot sequence labeling faces a unique challenge compared with the ot...

Exemplar Auditing for Multi-Label Biomedical Text Classification

Many practical applications of AI in medicine consist of semi-supervised...

An Exploration of Arbitrary-Order Sequence Labeling via Energy-Based Inference Networks

Many tasks in natural language processing involve predicting structured ...

Generative Adversarial Data Programming

The paucity of large curated hand-labeled training data forms a major bo...

Please sign up or login with your details

Forgot password? Click here to reset