Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation

• URL: http://arxiv.org/abs/2210.12902v1
• Date: Mon, 24 Oct 2022 01:15:06 GMT
• Title: Event-Centric Question Answering via Contrastive Learning and Invertible Event Transformation
• Authors: Junru Lu, Xingwei Tan, Gabriele Pergola, Lin Gui, Yulan He
• Abstract summary: We propose a novel QA model with contrastive learning and invertible event transformation, called TranCLR. Our proposed model utilizes an invertible transformation matrix to project semantic vectors of events into a common event embedding space, trained with contrastive learning, and thus naturally inject event semantic knowledge into mainstream QA pipelines.
• Score: 29.60817278635999
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Human reading comprehension often requires reasoning of event semantic relations in narratives, represented by Event-centric Question-Answering (QA). To address event-centric QA, we propose a novel QA model with contrastive learning and invertible event transformation, call TranCLR. Our proposed model utilizes an invertible transformation matrix to project semantic vectors of events into a common event embedding space, trained with contrastive learning, and thus naturally inject event semantic knowledge into mainstream QA pipelines. The transformation matrix is fine-tuned with the annotated event relation types between events that occurred in questions and those in answers, using event-aware question vectors. Experimental results on the Event Semantic Relation Reasoning (ESTER) dataset show significant improvements in both generative and extractive settings compared to the existing strong baselines, achieving over 8.4% gain in the token-level F1 score and 3.0% gain in Exact Match (EM) score under the multi-answer setting. Qualitative analysis reveals the high quality of the generated answers by TranCLR, demonstrating the feasibility of injecting event knowledge into QA model learning. Our code and models can be found at https://github.com/LuJunru/TranCLR.

Related papers

• Complex Reasoning over Logical Queries on Commonsense Knowledge Graphs [61.796960984541464]
  We present COM2 (COMplex COMmonsense), a new dataset created by sampling logical queries. We verbalize them using handcrafted rules and large language models into multiple-choice and text generation questions. Experiments show that language models trained on COM2 exhibit significant improvements in complex reasoning ability.
  arXiv  Detail & Related papers  (2024-03-12T08:13:52Z)
• Event Extraction as Question Generation and Answering [72.04433206754489]
  Recent work on Event Extraction has reframed the task as Question Answering (QA) We propose QGA-EE, which enables a Question Generation (QG) model to generate questions that incorporate rich contextual information instead of using fixed templates. Experiments show that QGA-EE outperforms all prior single-task-based models on the ACE05 English dataset.
  arXiv  Detail & Related papers  (2023-07-10T01:46:15Z)
• Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering [32.03893317439898]
  We propose a strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization. In particular, we define event-related knowledge constraints based on the event trigger annotations in the QA datasets. We conduct experiments on two event-centric QA datasets, TORQUE and ESTER.
  arXiv  Detail & Related papers  (2023-05-08T07:45:12Z)
• In Defense of Structural Symbolic Representation for Video Event-Relation Prediction [44.528350052251334]
  We conduct an empirical analysis to answer the following questions: 1) why SSR-based method failed; 2) how to understand the evaluation setting of video event relation prediction properly; and 3) how to uncover the potential of SSR-based methods. We propose to further contextualize the SSR-based model to an Event-Sequence Model and equip it with more factual knowledge through a simple yet effective way of reformulating external visual commonsense knowledge bases into an event-relation prediction pretraining dataset.
  arXiv  Detail & Related papers  (2023-01-06T14:43:19Z)
• Semantic Pivoting Model for Effective Event Detection [19.205550116466604]
  Event Detection aims to identify and classify mentions of event instances from unstructured articles. Existing techniques for event detection only use homogeneous one-hot vectors to represent the event type classes, ignoring the fact that the semantic meaning of the types is important to the task. We propose a Semantic Pivoting Model for Effective Event Detection (SPEED), which explicitly incorporates prior information during training and captures semantically meaningful correlations between input and events.
  arXiv  Detail & Related papers  (2022-11-01T19:20:34Z)
• ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification [74.6318379374801]
  We propose to pre-train a general Correlation-aware context-to-Event Transformer (ClarET) for event-centric reasoning. The proposed ClarET is applicable to a wide range of event-centric reasoning scenarios.
  arXiv  Detail & Related papers  (2022-03-04T10:11:15Z)
• Reliable Shot Identification for Complex Event Detection via Visual-Semantic Embedding [72.9370352430965]
  We propose a visual-semantic guided loss method for event detection in videos. Motivated by curriculum learning, we introduce a negative elastic regularization term to start training the classifier with instances of high reliability. An alternative optimization algorithm is developed to solve the proposed challenging non-net regularization problem.
  arXiv  Detail & Related papers  (2021-10-12T11:46:56Z)
• Learning Constraints and Descriptive Segmentation for Subevent Detection [74.48201657623218]
  We propose an approach to learning and enforcing constraints that capture dependencies between subevent detection and EventSeg prediction. We adopt Rectifier Networks for constraint learning and then convert the learned constraints to a regularization term in the loss function of the neural model.
  arXiv  Detail & Related papers  (2021-09-13T20:50:37Z)
• MUTANT: A Training Paradigm for Out-of-Distribution Generalization in Visual Question Answering [58.30291671877342]
  We present MUTANT, a training paradigm that exposes the model to perceptually similar, yet semantically distinct mutations of the input. MUTANT establishes a new state-of-the-art accuracy on VQA-CP with a $10.57%$ improvement.
  arXiv  Detail & Related papers  (2020-09-18T00:22:54Z)

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.