CLAIMar 13, 2017

Reinforcement Learning for Transition-Based Mention Detection

arXiv:1703.04489v12 citations
Originality Incremental advance
AI Analysis

This work addresses mention detection in NLP, presenting an incremental improvement with a novel method for a known bottleneck.

The paper tackles mention detection by introducing a reinforcement learning approach with an action-based formulation that allows flexible revision of past labeling decisions, achieving results comparable to a supervised counterpart while offering greater flexibility in handling longer mentions.

This paper describes an application of reinforcement learning to the mention detection task. We define a novel action-based formulation for the mention detection task, in which a model can flexibly revise past labeling decisions by grouping together tokens and assigning partial mention labels. We devise a method to create mention-level episodes and we train a model by rewarding correctly labeled complete mentions, irrespective of the inner structure created. The model yields results which are on par with a competitive supervised counterpart while being more flexible in terms of achieving targeted behavior through reward modeling and generating internal mention structure, especially on longer mentions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes