GROOT: Corrective Reward Optimization for Generative Sequential Labeling

Kazuma Hashimoto, Karthik Raman

Keywords: sequential labeling, reward optimization, natural language processing

Abstract:

Sequential labeling is a fundamental NLP task, forming the backbone of many applications.
Supervised learning of Seq2Seq models (like T5) has shown great success on these problems.
However there remains a significant disconnect between the training objectives of these models vs the metrics and desiderata we care about in practical applications.
For example, a practical sequence tagging application may want to optimize for a certain precision-recall trade-off (of the top-k predictions) which is quite different from the standard objective of maximizing the likelihood of the gold labeled sequence.
Thus to bridge this gap, we propose GROOT -- a simple yet effective framework for Generative Reward Optimization Of Text sequences.
GROOT works by training a generative sequential labeling model to match the decoder output distribution with that of the (black-box) reward function.
Using an iterative training regime, we first generate prediction candidates, then correct errors in them, and finally contrast those candidates (based on their reward values).
As demonstrated via extensive experiments on four public benchmarks, GROOT significantly improves all reward metrics.
Furthermore, GROOT also leads to improvements of the overall decoder distribution as evidenced by the quality gains of the top-k candidates.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Submission Guidelines: Yes

Please Choose The Closest Area That Your Submission Falls Into: Applications (eg, speech processing, computer vision, NLP)

TL;DR: This paper proposes a novel framework for iteratively training Seq2Seq models to directly optimize a given blackbox reward metric, showing its effectiveness on sequential labeling tasks.

Community Implementations: [ 1 code implementation](https://www.catalyzex.com/paper/groot-corrective-reward-optimization-for/code)