Optimizing Differentiable Relaxations of Coreference Evaluation Metrics
Coreference evaluation metrics are hard to optimize directly as they are non-differentiable functions, not easily decomposable into elementary decisions. Consequently, most approaches optimize objectives only indirectly related to the end goal, resulting in suboptimal performance. Instead, we propose a differentiable relaxation that lends itself to gradient-based optimisation, thus bypassing the need for reinforcement learning or heuristic modification of cross-entropy. We show that by modifying the training objective of a competitive neural coreference system, we obtain a substantial gain in performance. This suggests that our approach can be regarded as a viable alternative to using reinforcement learning or more computationally expensive imitation learning.
Code (1)
Tasks
Imitation Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Similar Papers 제목 키워드 기반
Differentiable Satellite Constellation Configuration via Relaxed Coverage and Revisit Objectives
Satellite constellation design requires optimizing orbital parameters across multiple satellites to maximize mission specific metrics. For many types of mission, it is desirable to maximize coverage and minimize revisit …
End-to-end Neural Coreference Resolution Revisited: A Simple yet Effective Baseline
Since the first end-to-end neural coreference resolution model was introduced, many extensions to the model have been proposed, ranging from using higher-order inference to directly optimizing evaluation metrics using re…
coreference-resolutionCoreference ResolutionEfficient Differentiable Approximation of Generalized Low-rank Regularization
Low-rank regularization (LRR) has been widely applied in various machine learning tasks, but the associated optimization is challenging. Directly optimizing the rank function under constraints is NP-hard in general. To o…
GPUDAG Learning on the Permutahedron
We propose a continuous optimization framework for discovering a latent directed acyclic graph (DAG) from observational data. Our approach optimizes over the polytope of permutation vectors, the so-called Permutahedron, …
Hashing as Tie-Aware Learning to Rank
Hashing, or learning binary embeddings of data, is frequently used in nearest neighbor retrieval. In this paper, we develop learning to rank formulations for hashing, aimed at directly optimizing ranking-based evaluation…
Image RetrievalLearning-To-RankRetrieval