Moving on from OntoNotes: Coreference Resolution Model Transfer

• URL: http://arxiv.org/abs/2104.08457v1
• Date: Sat, 17 Apr 2021 05:35:07 GMT
• Title: Moving on from OntoNotes: Coreference Resolution Model Transfer
• Authors: Patrick Xia, Benjamin Van Durme
• Abstract summary: We quantify transferability of coreference resolution models based on the number of annotated documents available in the target dataset. We establish new benchmarks across several datasets, including state-of-the-art results on LitBank and PreCo.
• Score: 47.5441257300917
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Academic neural models for coreference resolution are typically trained on a single dataset (OntoNotes) and model improvements are then benchmarked on that dataset. However, real-world usages of coreference resolution models depend on the annotation guidelines and the domain of the target dataset, which often differ from those of OntoNotes. We aim to quantify transferability of coreference resolution models based on the number of annotated documents available in the target dataset. We examine five target datasets and find that continued training is consistently effective and especially beneficial when there are few target documents. We establish new benchmarks across several datasets, including state-of-the-art results on LitBank and PreCo.

Related papers

• On Evaluation of Vision Datasets and Models using Human Competency Frameworks [20.802372291783488]
  Item Response Theory (IRT) is a framework that infers interpretable latent parameters for an ensemble of models and each dataset item. We assess model calibration, select informative data subsets, and demonstrate the usefulness of its latent parameters for analyzing and comparing models and datasets in computer vision.
  arXiv  Detail & Related papers  (2024-09-06T06:20:11Z)
• RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization [36.973388673687815]
  RanLayNet is a synthetic document dataset enriched with automatically assigned labels. We show that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents.
  arXiv  Detail & Related papers  (2024-04-15T07:50:15Z)
• Building a Winning Team: Selecting Source Model Ensembles using a Submodular Transferability Estimation Approach [20.86345962679122]
  Estimating the transferability of publicly available pretrained models to a target task has assumed an important place for transfer learning tasks. We propose a novel Optimal tranSport-based suBmOdular tRaNsferability metric (OSBORN) to estimate the transferability of an ensemble of models to a downstream task.
  arXiv  Detail & Related papers  (2023-09-05T17:57:31Z)
• infoVerse: A Universal Framework for Dataset Characterization with Multidimensional Meta-information [68.76707843019886]
  infoVerse is a universal framework for dataset characterization. infoVerse captures multidimensional characteristics of datasets by incorporating various model-driven meta-information. In three real-world applications (data pruning, active learning, and data annotation), the samples chosen on infoVerse space consistently outperform strong baselines.
  arXiv  Detail & Related papers  (2023-05-30T18:12:48Z)
• On Generalization in Coreference Resolution [66.05112218880907]
  We consolidate a set of 8 coreference resolution datasets targeting different domains to evaluate the off-the-shelf performance of models. We then mix three datasets for training; even though their domain, annotation guidelines, and metadata differ, we propose a method for jointly training a single model. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance.
  arXiv  Detail & Related papers  (2021-09-20T16:33:22Z)
• Adaptive Active Learning for Coreference Resolution [37.261220564076964]
  Recent developments in incremental coreference resolution allow for a novel approach to active learning in this setting. By lowering the data barrier for coreference, coreference resolvers can rapidly adapt to a series of previously unconsidered domains.
  arXiv  Detail & Related papers  (2021-04-15T17:21:51Z)
• Improving Zero and Few-Shot Abstractive Summarization with Intermediate Fine-tuning and Data Augmentation [101.26235068460551]
  Models pretrained with self-supervised objectives on large text corpora achieve state-of-the-art performance on English text summarization tasks. Models are typically fine-tuned on hundreds of thousands of data points, an infeasible requirement when applying summarization to new, niche domains. We introduce a novel and generalizable method, called WikiTransfer, for fine-tuning pretrained models for summarization in an unsupervised, dataset-specific manner.
  arXiv  Detail & Related papers  (2020-10-24T08:36:49Z)
• Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark [54.782397511033345]
  Crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts. We present a new unified cross-datasets benchmark with 14 NLI datasets and re-evaluate 9 widely-used neural network-based NLI models. Our proposed evaluation scheme and experimental baselines could provide a basis to inspire future reliable NLI research.
  arXiv  Detail & Related papers  (2020-10-15T11:50:12Z)
• $n$-Reference Transfer Learning for Saliency Prediction [73.17061116358036]
  We propose a few-shot transfer learning paradigm for saliency prediction. The proposed framework is gradient-based and model-agnostic. The results show that the proposed framework achieves a significant performance improvement.
  arXiv  Detail & Related papers  (2020-07-09T23:20:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.