A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
- URL: http://arxiv.org/abs/2404.01921v2
- Date: Wed, 8 May 2024 04:07:35 GMT
- Title: A Rationale-centric Counterfactual Data Augmentation Method for Cross-Document Event Coreference Resolution
- Authors: Bowen Ding, Qingkai Min, Shengkun Ma, Yingjie Li, Linyi Yang, Yue Zhang,
- Abstract summary: We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM)
We develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop.
Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.
- Score: 29.34028569245905
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Based on Pre-trained Language Models (PLMs), event coreference resolution (ECR) systems have demonstrated outstanding performance in clustering coreferential events across documents. However, the existing system exhibits an excessive reliance on the `triggers lexical matching' spurious pattern in the input mention pair text. We formalize the decision-making process of the baseline ECR system using a Structural Causal Model (SCM), aiming to identify spurious and causal associations (i.e., rationales) within the ECR task. Leveraging the debiasing capability of counterfactual data augmentation, we develop a rationale-centric counterfactual data augmentation method with LLM-in-the-loop. This method is specialized for pairwise input in the ECR system, where we conduct direct interventions on triggers and context to mitigate the spurious association while emphasizing the causation. Our approach achieves state-of-the-art performance on three popular cross-document ECR benchmarks and demonstrates robustness in out-of-domain scenarios.
Related papers
- Crossmodal ASR Error Correction with Discrete Speech Units [16.58209270191005]
We propose a post-ASR processing approach for ASR Error Correction (AEC)
We explore pre-training and fine-tuning strategies and uncover an ASR domain discrepancy phenomenon.
We propose the incorporation of discrete speech units to align with and enhance the word embeddings for improving AEC quality.
arXiv Detail & Related papers (2024-05-26T19:58:38Z) - Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
We propose Mulan, a unified multi-modal causal structure learning method for root cause localization.
We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data.
We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
arXiv Detail & Related papers (2024-02-04T05:50:38Z) - DCR-Consistency: Divide-Conquer-Reasoning for Consistency Evaluation and
Improvement of Large Language Models [4.953092503184905]
This work proposes DCR, an automated framework for evaluating and improving the consistency of Large Language Models (LLMs) generated texts.
We introduce an automatic metric converter (AMC) that translates the output from DCE into an interpretable numeric score.
Our approach also substantially reduces nearly 90% of output inconsistencies, showing promise for effective hallucination mitigation.
arXiv Detail & Related papers (2024-01-04T08:34:16Z) - Utilizing Contextual Clues and Role Correlations for Enhancing Document-level Event Argument Extraction [14.684710634595866]
Document-level event argument extraction is a crucial yet challenging task within the field of information extraction.
Here, we introduce a novel framework named CARLG, comprising two innovative components: the Contextual Clues Aggregation (CCA) and the Role-based Latent Information Guidance (RLIG)
We then instantiate the CARLG framework into two variants based on two types of current mainstream EAE approaches. Notably, our CARLG framework introduces less than 1% new parameters yet significantly improving the performance.
arXiv Detail & Related papers (2023-10-08T11:09:16Z) - REX: Rapid Exploration and eXploitation for AI Agents [103.68453326880456]
We propose an enhanced approach for Rapid Exploration and eXploitation for AI Agents called REX.
REX introduces an additional layer of rewards and integrates concepts similar to Upper Confidence Bound (UCB) scores, leading to more robust and efficient AI agent performance.
arXiv Detail & Related papers (2023-07-18T04:26:33Z) - A robust method for reliability updating with equality information using
sequential adaptive importance sampling [8.254850675268957]
Reliability updating refers to a problem that integrates Bayesian updating technique with structural reliability analysis.
This paper proposes an innovative method called RU-SAIS, which combines elements of sequential importance sampling and K-means clustering.
Results show that RU-SAIS achieves a more accurate and robust estimator of the posterior failure probability than the existing methods.
arXiv Detail & Related papers (2023-03-08T12:55:40Z) - Reasoning over Hybrid Chain for Table-and-Text Open Domain QA [69.8436986668218]
We propose a ChAin-centric Reasoning and Pre-training framework (CARP)
CARP utilizes hybrid chain to model the explicit intermediate reasoning process across table and text for question answering.
We also propose a novel chain-centric pre-training method, to enhance the pre-trained model in identifying the cross-modality reasoning process.
arXiv Detail & Related papers (2022-01-15T16:11:55Z) - Attention-based Multi-hypothesis Fusion for Speech Summarization [83.04957603852571]
Speech summarization can be achieved by combining automatic speech recognition (ASR) and text summarization (TS)
ASR errors directly affect the quality of the output summary in the cascade approach.
We propose a cascade speech summarization model that is robust to ASR errors and that exploits multiple hypotheses generated by ASR to attenuate the effect of ASR errors on the summary.
arXiv Detail & Related papers (2021-11-16T03:00:29Z) - SAIS: Supervising and Augmenting Intermediate Steps for Document-Level
Relation Extraction [51.27558374091491]
We propose to explicitly teach the model to capture relevant contexts and entity types by supervising and augmenting intermediate steps (SAIS) for relation extraction.
Based on a broad spectrum of carefully designed tasks, our proposed SAIS method not only extracts relations of better quality due to more effective supervision, but also retrieves the corresponding supporting evidence more accurately.
arXiv Detail & Related papers (2021-09-24T17:37:35Z) - Joint Contextual Modeling for ASR Correction and Language Understanding [60.230013453699975]
We propose multi-task neural approaches to perform contextual language correction on ASR outputs jointly with language understanding (LU)
We show that the error rates of off the shelf ASR and following LU systems can be reduced significantly by 14% relative with joint models trained using small amounts of in-domain data.
arXiv Detail & Related papers (2020-01-28T22:09:25Z)
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.