paper-with-me

홈 › Papers

A Structured Span Selector

2022-05-08 · NAACL 2022 7 · Tianyu Liu, Yuchen Eleanor Jiang, Ryan Cotterell, Mrinmaya Sachan

Many natural language processing tasks, e.g., coreference resolution and semantic role labeling, require selecting text spans and making decisions about them. A typical approach to such tasks is to score all possible spans and greedily select spans for task-specific downstream processing. This approach, however, does not incorporate any inductive bias about what sort of spans ought to be selected, e.g., that selected spans tend to be syntactic constituents. In this paper, we propose a novel grammar-based structured span selection model which learns to make use of the partial span-level annotation provided for such problems. Compared to previous approaches, our approach gets rid of the heuristic greedy span selection scheme, allowing us to model the downstream task on an optimal set of spans. We evaluate our model on two popular span prediction tasks: coreference resolution and semantic role labeling. We show empirical improvements on both.

📄 PDF Abstract BibTeX arXiv:2205.03977

Code (1)

lyutyuh/structured-span-selector 공식 구현 pytorch

Tasks

coreference-resolutionCoreference ResolutionInductive BiasSemantic Role Labeling

Similar Papers 제목 키워드 기반

Using Context to Improve the Spanish WordNet Translation

2018-01-01 · GWC 2018 1 · Alfonso Methol, Guillermo López, Juan Álvarez, Luis Chiruzzo 외

We present some strategies for improving the Spanish version of WordNet, part of the MCR, selecting new lemmas for the Spanish synsets by translating the lemmas of the corresponding English synsets. We used four simple s…

Translation

On the Effectiveness of Minimal Context Selection for Robust Question Answering

2018-10-30 · Anonymous

Machine learning models for question-answering (QA), where given a question and a passage, the learner must select some span in the passage as an answer, are known to be brittle. By inserting a single nuisance sentence i…

Adversarial RobustnessQuestion AnsweringSentence

Structured Matrix Recovery via the Generalized Dantzig Selector

2016-04-12 · NeurIPS 2016 12 · Sheng Chen, Arindam Banerjee

In recent years, structured matrix recovery problems have gained considerable attention for its real world applications, such as recommender systems and computer vision. Much of the existing work has focused on matrices …

Recommendation Systems

Improving Distantly Supervised Relation Extraction with Neural Noise Converter and Conditional Optimal Selector

2018-11-14 · Shanchan Wu, Kai Fan, Qiong Zhang

Distant supervised relation extraction has been successfully applied to large corpus with thousands of relations. However, the inevitable wrong labeling problem by distant supervision will hurt the performance of relatio…

RelationRelation Extraction

Deep Elastic Networks with Model Selection for Multi-Task Learning

2019-09-11 · ICCV 2019 10 · Chanho Ahn, Eunwoo Kim, Songhwai Oh

In this work, we consider the problem of instance-wise dynamic network model selection for multi-task learning. To this end, we propose an efficient approach to exploit a compact but accurate model in a backbone architec…

image-classificationImage ClassificationModel SelectionMulti-Task Learning