$2 * n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems

• URL: http://arxiv.org/abs/2305.05672v1
• Date: Tue, 9 May 2023 05:33:32 GMT
• Title: $2 * n$ is better than $n^2$: Decomposing Event Coreference Resolution into Two Tractable Problems
• Abstract summary: Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. We show that we get comparable results to the state of the art on two popular ECR datasets. We also analyze the mention pairs that are "hard" to accurately classify as coreferent or non-coreferent.
• Score: 3.777476692151661
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Event Coreference Resolution (ECR) is the task of linking mentions of the same event either within or across documents. Most mention pairs are not coreferent, yet many that are coreferent can be identified through simple techniques such as lemma matching of the event triggers or the sentences in which they appear. Existing methods for training coreference systems sample from a largely skewed distribution, making it difficult for the algorithm to learn coreference beyond surface matching. Additionally, these methods are intractable because of the quadratic operations needed. To address these challenges, we break the problem of ECR into two parts: a) a heuristic to efficiently filter out a large number of non-coreferent pairs, and b) a training approach on a balanced set of coreferent and non-coreferent mention pairs. By following this approach, we show that we get comparable results to the state of the art on two popular ECR datasets while significantly reducing compute requirements. We also analyze the mention pairs that are "hard" to accurately classify as coreferent or non-coreferent. Code at https://github.com/ahmeshaf/lemma_ce_coref

Related papers

• $V_1$: Unifying Generation and Self-Verification for Parallel Reasoners [69.66089681814013]
  $V_$ is a framework that unifies generation and verification through efficient pairwise ranking.<n>$V_$-Infer improves Pass@1 by up to $10%$ over pointwise verification.<n>$V_$-PairRL achieves $7$--$9%$ test-time scaling gains over standard RL and pointwise joint training.
  arXiv  Detail & Related papers  (2026-03-04T17:22:16Z)
• CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming [58.48683464644606]
  We introduce CPRet, a retrieval-oriented benchmark suite for competitive programming.<n>Our contribution includes both high-quality training data and temporally separated test sets for reliable evaluation.<n>We develop two task-specialized retrievers based on this dataset: CPRetriever-Code, trained with a novel Group-InfoNCE loss for problem-code alignment, and CPRetriever-Prob, fine-tuned for identifying problem-level similarity.
  arXiv  Detail & Related papers  (2025-05-19T10:07:51Z)
• Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought [56.71873693264532]
  We prove that a two-layer transformer with $D$ steps of continuous CoTs can solve the directed graph reachability problem.<n>In our construction, each continuous thought vector is a superposition state that encodes multiple search frontiers simultaneously.
  arXiv  Detail & Related papers  (2025-05-18T18:36:53Z)
• Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization [65.8915778873691]
  conditional distributions is a central problem in machine learning. We propose a new learning paradigm that integrates both paired and unpaired data. Our approach also connects intriguingly with inverse entropic optimal transport (OT)
  arXiv  Detail & Related papers  (2024-10-03T16:12:59Z)
• Semisupervised score based matching algorithm to evaluate the effect of public health interventions [3.221788913179251]
  In one-to-one matching algorithms, a large number of "pairs" to be matched could mean both the information from a large sample and a large number of tasks. We propose a novel one-to-one matching algorithm based on a quadratic score function $S_beta(x_i,x_j)= betaT (x_i-x_j)(x_i-x_j)T beta$.
  arXiv  Detail & Related papers  (2024-03-19T02:24:16Z)
• Semi-DETR: Semi-Supervised Object Detection with Detection Transformers [105.45018934087076]
  We analyze the DETR-based framework on semi-supervised object detection (SSOD) We present Semi-DETR, the first transformer-based end-to-end semi-supervised object detector. Our method outperforms all state-of-the-art methods by clear margins.
  arXiv  Detail & Related papers  (2023-07-16T16:32:14Z)
• On the Sample Complexity of Representation Learning in Multi-task Bandits with Global and Local structure [77.60508571062958]
  We investigate the sample complexity of learning the optimal arm for multi-task bandit problems. Arms consist of two components: one that is shared across tasks (that we call representation) and one that is task-specific (that we call predictor) We devise an algorithm OSRL-SC whose sample complexity approaches the lower bound, and scales at most as $H(Glog(delta_G)+ Xlog(delta_H))$, with $X,G,H$ being, respectively, the number of tasks, representations and predictors.
  arXiv  Detail & Related papers  (2022-11-28T08:40:12Z)
• Efficient Nearest Neighbor Search for Cross-Encoder Models using Matrix Factorization [60.91600465922932]
  We present an approach that avoids the use of a dual-encoder for retrieval, relying solely on the cross-encoder. Our approach provides test-time recall-vs-computational cost trade-offs superior to the current widely-used methods.
  arXiv  Detail & Related papers  (2022-10-23T00:32:04Z)
• Contrastive Representation Learning for Cross-Document Coreference Resolution of Events and Entities [0.0]
  We present an approach to entity and event coreference resolution utilizing contrastive representation learning. Our method achieves state-of-the-art results on a number of key metrics on the ECB+ corpus.
  arXiv  Detail & Related papers  (2022-05-23T16:30:20Z)
• Deep Probabilistic Graph Matching [72.6690550634166]
  We propose a deep learning-based graph matching framework that works for the original QAP without compromising on the matching constraints. The proposed method is evaluated on three popularly tested benchmarks (Pascal VOC, Willow Object and SPair-71k) and it outperforms all previous state-of-the-arts on all benchmarks.
  arXiv  Detail & Related papers  (2022-01-05T13:37:27Z)
• Focus on what matters: Applying Discourse Coherence Theory to Cross Document Coreference [22.497877069528087]
  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.
  arXiv  Detail & Related papers  (2021-10-11T15:41:47Z)
• Online Matching in Sparse Random Graphs: Non-Asymptotic Performances of Greedy Algorithm [20.582965700659788]
  We estimate the competitive ratio of the simplest algorithm, GREEDY, by approximating some relevant discrete processes by their continuous counterparts. We prove that, quite surprisingly, GREEDY can have better performance guarantees than RANKING, another celebrated algorithm for online matching.
  arXiv  Detail & Related papers  (2021-07-02T12:18:19Z)
• Linear-Time Gromov Wasserstein Distances using Low Rank Couplings and Costs [45.87981728307819]
  The ability to compare and align related datasets living in heterogeneous spaces plays an increasingly important role in machine learning. The Gromov-Wasserstein (GW) formalism can help tackle this problem.
  arXiv  Detail & Related papers  (2021-06-02T12:50:56Z)
• Learning to Accelerate Heuristic Searching for Large-Scale Maximum Weighted b-Matching Problems in Online Advertising [51.97494906131859]
  Bipartite b-matching is fundamental in algorithm design, and has been widely applied into economic markets, labor markets, etc. Existing exact and approximate algorithms usually fail in such settings due to either requiring intolerable running time or too much computation resource. We propose textttNeuSearcher which leverages the knowledge learned from previously instances to solve new problem instances.
  arXiv  Detail & Related papers  (2020-05-09T02:48:23Z)
• Ranking a set of objects: a graph based least-square approach [70.7866286425868]
  We consider the problem of ranking $N$ objects starting from a set of noisy pairwise comparisons provided by a crowd of equal workers. We propose a class of non-adaptive ranking algorithms that rely on a least-squares intrinsic optimization criterion for the estimation of qualities.
  arXiv  Detail & Related papers  (2020-02-26T16:19:09Z)

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.