On Generalization in Coreference Resolution

• URL: http://arxiv.org/abs/2109.09667v1
• Date: Mon, 20 Sep 2021 16:33:22 GMT
• Title: On Generalization in Coreference Resolution
• Authors: Shubham Toshniwal, Patrick Xia, Sam Wiseman, Karen Livescu, Kevin Gimpel
• Abstract summary: 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.
• Score: 66.05112218880907
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: While coreference resolution is defined independently of dataset domain, most models for performing coreference resolution do not transfer well to unseen domains. 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 on this heterogeneous data mixture by using data augmentation to account for annotation differences and sampling to balance the data quantities. We find that in a zero-shot setting, models trained on a single dataset transfer poorly while joint training yields improved overall performance, leading to better generalization in coreference resolution models. This work contributes a new benchmark for robust coreference resolution and multiple new state-of-the-art results.

Related papers

• Universal Semi-supervised Model Adaptation via Collaborative Consistency Training [92.52892510093037]
  We introduce a realistic and challenging domain adaptation problem called Universal Semi-supervised Model Adaptation (USMA) We propose a collaborative consistency training framework that regularizes the prediction consistency between two models. Experimental results demonstrate the effectiveness of our method on several benchmark datasets.
  arXiv  Detail & Related papers  (2023-07-07T08:19:40Z)
• Dataless Knowledge Fusion by Merging Weights of Language Models [51.8162883997512]
  Fine-tuning pre-trained language models has become the prevalent paradigm for building downstream NLP models. This creates a barrier to fusing knowledge across individual models to yield a better single model. We propose a dataless knowledge fusion method that merges models in their parameter space.
  arXiv  Detail & Related papers  (2022-12-19T20:46:43Z)
• An Empirical Study on Multi-Domain Robust Semantic Segmentation [42.79166534691889]
  We train a unified model that is expected to perform well across domains on several popularity segmentation datasets. Our solution ranks 2nd on RVC 2022 semantic segmentation task, with a dataset only 1/3 size of the 1st model used.
  arXiv  Detail & Related papers  (2022-12-08T12:04:01Z)
• Cross-Domain Ensemble Distillation for Domain Generalization [17.575016642108253]
  We propose a simple yet effective method for domain generalization, named cross-domain ensemble distillation (XDED) Our method generates an ensemble of the output logits from training data with the same label but from different domains and then penalizes each output for the mismatch with the ensemble. We show that models learned by our method are robust against adversarial attacks and image corruptions.
  arXiv  Detail & Related papers  (2022-11-25T12:32:36Z)
• Heterogeneous Target Speech Separation [52.05046029743995]
  We introduce a new paradigm for single-channel target source separation where the sources of interest can be distinguished using non-mutually exclusive concepts. Our proposed heterogeneous separation framework can seamlessly leverage datasets with large distribution shifts.
  arXiv  Detail & Related papers  (2022-04-07T17:14:20Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Moving on from OntoNotes: Coreference Resolution Model Transfer [47.5441257300917]
  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.
  arXiv  Detail & Related papers  (2021-04-17T05:35:07Z)
• 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)

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.