SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution

• URL: http://arxiv.org/abs/2403.17245v1
• Date: Mon, 25 Mar 2024 22:46:16 GMT
• Title: SPLICE: A Singleton-Enhanced PipeLIne for Coreference REsolution
• Authors: Yilun Zhu, Siyao Peng, Sameer Pradhan, Amir Zeldes,
• Abstract summary: Singleton mentions, i.e.entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. Previous attempts to incorporate their detection in end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention spans in the OntoNotes benchmark. This paper addresses this limitation by combining predicted mentions from existing nested NER systems and features derived from OntoNotes syntax trees.
• Score: 11.062090350704617
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Singleton mentions, i.e.~entities mentioned only once in a text, are important to how humans understand discourse from a theoretical perspective. However previous attempts to incorporate their detection in end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention spans in the OntoNotes benchmark. This paper addresses this limitation by combining predicted mentions from existing nested NER systems and features derived from OntoNotes syntax trees. With this approach, we create a near approximation of the OntoNotes dataset with all singleton mentions, achieving ~94% recall on a sample of gold singletons. We then propose a two-step neural mention and coreference resolution system, named SPLICE, and compare its performance to the end-to-end approach in two scenarios: the OntoNotes test set and the out-of-domain (OOD) OntoGUM corpus. Results indicate that reconstructed singleton training yields results comparable to end-to-end systems for OntoNotes, while improving OOD stability (+1.1 avg. F1). We conduct error analysis for mention detection and delve into its impact on coreference clustering, revealing that precision improvements deliver more substantial benefits than increases in recall for resolving coreference chains.

Related papers

• Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization [12.084539012992412]
  This paper presents a coreference model that learns singletons as well as features such as entity type and information status. This approach achieves new state-of-the-art scores on the OntoGUM benchmark.
  arXiv  Detail & Related papers  (2023-09-20T18:44:24Z)
• TOLD: A Novel Two-Stage Overlap-Aware Framework for Speaker Diarization [54.41494515178297]
  We reformulate speaker diarization as a single-label classification problem. We propose the overlap-aware EEND (EEND-OLA) model, in which speaker overlaps and dependency can be modeled explicitly. Compared with the original EEND, the proposed EEND-OLA achieves a 14.39% relative improvement in terms of diarization error rates.
  arXiv  Detail & Related papers  (2023-03-08T05:05:26Z)
• Neural Coreference Resolution based on Reinforcement Learning [53.73316523766183]
  Coreference resolution systems need to solve two subtasks. One task is to detect all of the potential mentions, the other is to learn the linking of an antecedent for each possible mention. We propose a reinforcement learning actor-critic-based neural coreference resolution system.
  arXiv  Detail & Related papers  (2022-12-18T07:36:35Z)
• Speaker Embedding-aware Neural Diarization: a Novel Framework for Overlapped Speech Diarization in the Meeting Scenario [51.5031673695118]
  We reformulate overlapped speech diarization as a single-label prediction problem. We propose the speaker embedding-aware neural diarization (SEND) system.
  arXiv  Detail & Related papers  (2022-03-18T06:40:39Z)
• Instance-Level Relative Saliency Ranking with Graph Reasoning [126.09138829920627]
  We present a novel unified model to segment salient instances and infer relative saliency rank order. A novel loss function is also proposed to effectively train the saliency ranking branch. experimental results demonstrate that our proposed model is more effective than previous methods.
  arXiv  Detail & Related papers  (2021-07-08T13:10:42Z)
• Explaining and Improving Model Behavior with k Nearest Neighbor Representations [107.24850861390196]
  We propose using k nearest neighbor representations to identify training examples responsible for a model's predictions. We show that kNN representations are effective at uncovering learned spurious associations. Our results indicate that the kNN approach makes the finetuned model more robust to adversarial inputs.
  arXiv  Detail & Related papers  (2020-10-18T16:55:25Z)
• Reinforcement Learning-based N-ary Cross-Sentence Relation Extraction [3.342376225738321]
  Models of n-ary cross sentence relation extraction based on distant supervision assume that consecutive sentences mentioning n entities describe the relation of these n entities. On the other hand, some non-consecutive sentences also describe one relation and these sentences cannot be labeled under this assumption. We propose a novel sentence distribution estimator model to address the first problem.
  arXiv  Detail & Related papers  (2020-09-26T20:39:55Z)
• Coreference Resolution System for Indonesian Text with Mention Pair Method and Singleton Exclusion using Convolutional Neural Network [0.0]
  We propose a new coreference resolution system for Indonesian text with mention pair method. In addition to lexical and syntactic features, in order to learn the representation of the mentions words and context, we use word embeddings and feed them to CNN. Our proposed system outperforms the state-of-the-art system.
  arXiv  Detail & Related papers  (2020-09-11T22:21:19Z)
• SueNes: A Weakly Supervised Approach to Evaluating Single-Document Summarization via Negative Sampling [25.299937353444854]
  We present a proof-of-concept study to a weakly supervised summary evaluation approach without the presence of reference summaries. Massive data in existing summarization datasets are transformed for training by pairing documents with corrupted reference summaries.
  arXiv  Detail & Related papers  (2020-05-13T15:40:13Z)
• Paraphrasing vs Coreferring: Two Sides of the Same Coin [28.80553558538015]
  We study the potential synergy between two different NLP tasks. We use annotations from an event coreference dataset as distant supervision to re-scoreally-extracted predicate paraphrases. We also use the same re-ranking features as additional inputs to a state-of-the-art event coreference resolution model.
  arXiv  Detail & Related papers  (2020-04-30T17:29:17Z)
• Active Learning for Coreference Resolution using Discrete Annotation [76.36423696634584]
  We improve upon pairwise annotation for active learning in coreference resolution. We ask annotators to identify mention antecedents if a presented mention pair is deemed not coreferent. In experiments with existing benchmark coreference datasets, we show that the signal from this additional question leads to significant performance gains per human-annotation hour.
  arXiv  Detail & Related papers  (2020-04-28T17:17:11Z)

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.