Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Label-Agnostic Sequence Labeling by Copying Nearest Neighbors

About

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 when transferring to new sequence-labeling tasks without retraining. 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.

Sam Wiseman, Karl Stratos• 2019

Related benchmarks

TaskDatasetResultRank
Named Entity RecognitionMIT Restaurant
Micro-F18.1
50
Named Entity RecognitionMIT Movie (target)
F1 Score8.6
36
Named Entity RecognitionCrossNER--
35
Named Entity RecognitionATIS target
F1 Score5.1
18
Showing 4 of 4 rows

Other info

Follow for update