Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference

• URL: http://arxiv.org/abs/2110.05362v1
• Date: Mon, 11 Oct 2021 15:41:47 GMT
• Title: Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference
• Authors: William Held, Dan Iter, Dan Jurafsky
• Abstract summary: Event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full $n2$ pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora.
• Score: 22.497877069528087
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Performing event and entity coreference resolution across documents vastly increases the number of candidate mentions, making it intractable to do the full $n^2$ pairwise comparisons. Existing approaches simplify by considering coreference only within document clusters, but this fails to handle inter-cluster coreference, common in many applications. As a result cross-document coreference algorithms are rarely applied to downstream tasks. We draw on an insight from discourse coherence theory: potential coreferences are constrained by the reader's discourse focus. We model the entities/events in a reader's focus as a neighborhood within a learned latent embedding space which minimizes the distance between mentions and the centroids of their gold coreference clusters. We then use these neighborhoods to sample only hard negatives to train a fine-grained classifier on mention pairs and their local discourse features. Our approach achieves state-of-the-art results for both events and entities on the ECB+, Gun Violence, Football Coreference, and Cross-Domain Cross-Document Coreference corpora. Furthermore, training on multiple corpora improves average performance across all datasets by 17.2 F1 points, leading to a robust coreference resolution model for use in downstream tasks where link distribution is unknown.

Related papers

• Contextual Document Embeddings [77.22328616983417]
  We propose two complementary methods for contextualized document embeddings. First, an alternative contrastive learning objective that explicitly incorporates the document neighbors into the intra-batch contextual loss. Second, a new contextual architecture that explicitly encodes neighbor document information into the encoded representation.
  arXiv  Detail & Related papers  (2024-10-03T14:33:34Z)
• ABCDE: Application-Based Cluster Diff Evals [49.1574468325115]
  It aims to be practical: it allows items to have associated importance values that are application-specific, it is frugal in its use of human judgements when determining which clustering is better, and it can report metrics for arbitrary slices of items. The approach to measuring the delta in the clustering quality is novel: instead of trying to construct an expensive ground truth up front and evaluating the each clustering with respect to that, ABCDE samples questions for judgement on the basis of the actual diffs between the clusterings.
  arXiv  Detail & Related papers  (2024-07-31T08:29:35Z)
• Enhancing Cross-Document Event Coreference Resolution by Discourse Structure and Semantic Information [33.21818213257603]
  Cross-document event coreference resolution models can only compute mention similarity directly or enhance mention representation by extracting event arguments. We propose the construction of document-level Rhetorical Structure Theory (RST) trees and cross-document Lexical Chains to model the structural and semantic information of documents. We have developed a large-scale Chinese cross-document event coreference dataset to fill this gap.
  arXiv  Detail & Related papers  (2024-06-23T02:54:48Z)
• Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union [113.20223082664681]
  We propose the use of fine-grained mIoUs along with corresponding worst-case metrics. These fine-grained metrics offer less bias towards large objects, richer statistical information, and valuable insights into model and dataset auditing. Our benchmark study highlights the necessity of not basing evaluations on a single metric and confirms that fine-grained mIoUs reduce the bias towards large objects.
  arXiv  Detail & Related papers  (2023-10-30T03:45:15Z)
• Bi-level Alignment for Cross-Domain Crowd Counting [113.78303285148041]
  Current methods rely on external data for training an auxiliary task or apply an expensive coarse-to-fine estimation. We develop a new adversarial learning based method, which is simple and efficient to apply. We evaluate our approach on five real-world crowd counting benchmarks, where we outperform existing approaches by a large margin.
  arXiv  Detail & Related papers  (2022-05-12T02:23:25Z)
• Author Clustering and Topic Estimation for Short Texts [69.54017251622211]
  We propose a novel model that expands on the Latent Dirichlet Allocation by modeling strong dependence among the words in the same document. We also simultaneously cluster users, removing the need for post-hoc cluster estimation. Our method performs as well as -- or better -- than traditional approaches to problems arising in short text.
  arXiv  Detail & Related papers  (2021-06-15T20:55:55Z)
• Exploiting Global Contextual Information for Document-level Named Entity Recognition [46.99922251839363]
  We propose a model called Global Context enhanced Document-level NER (GCDoc) At word-level, a document graph is constructed to model a wider range of dependencies between words. At sentence-level, for appropriately modeling wider context beyond single sentence, we employ a cross-sentence module. Our model reaches F1 score of 92.22 (93.40 with BERT) on CoNLL 2003 dataset and 88.32 (90.49 with BERT) on Ontonotes 5.0 dataset.
  arXiv  Detail & Related papers  (2021-06-02T01:52:07Z)
• WEC: Deriving a Large-scale Cross-document Event Coreference dataset from Wikipedia [14.324743524196874]
  We present Wikipedia Event Coreference (WEC), an efficient methodology for gathering a large-scale dataset for cross-document event coreference from Wikipedia. We apply this methodology to the English Wikipedia and extract our large-scale WEC-Eng dataset. We develop an algorithm that adapts components of state-of-the-art models for within-document coreference resolution to the cross-document setting.
  arXiv  Detail & Related papers  (2021-04-11T14:54:35Z)
• Efficient Clustering from Distributions over Topics [0.0]
  We present an approach that relies on the results of a topic modeling algorithm over documents in a collection as a means to identify smaller subsets of documents where the similarity function can be computed. This approach has proved to obtain promising results when identifying similar documents in the domain of scientific publications.
  arXiv  Detail & Related papers  (2020-12-15T10:52:19Z)
• Segmentation Approach for Coreference Resolution Task [4.000580823870735]
  In coreference resolution, it is important to consider all members of a coreference cluster and decide about all of them at once. This paper proposes a new approach for coreference resolution which can resolve all coreference mentions to a given mention in the document in one pass.
  arXiv  Detail & Related papers  (2020-06-30T16:44:28Z)

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.