تقرير
Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering
العنوان: | Event Knowledge Incorporation with Posterior Regularization for Event-Centric Question Answering |
---|---|
المؤلفون: | Lu, Junru, Pergola, Gabriele, Gui, Lin, He, Yulan |
سنة النشر: | 2023 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Computation and Language |
الوصف: | We propose a simple yet effective strategy to incorporate event knowledge extracted from event trigger annotations via posterior regularization to improve the event reasoning capability of mainstream question-answering (QA) models for event-centric QA. In particular, we define event-related knowledge constraints based on the event trigger annotations in the QA datasets, and subsequently use them to regularize the posterior answer output probabilities from the backbone pre-trained language models used in the QA setting. We explore two different posterior regularization strategies for extractive and generative QA separately. For extractive QA, the sentence-level event knowledge constraint is defined by assessing if a sentence contains an answer event or not, which is later used to modify the answer span extraction probability. For generative QA, the token-level event knowledge constraint is defined by comparing the generated token from the backbone language model with the answer event in order to introduce a reward or penalty term, which essentially adjusts the answer generative probability indirectly. We conduct experiments on two event-centric QA datasets, TORQUE and ESTER. The results show that our proposed approach can effectively inject event knowledge into existing pre-trained language models and achieves strong performance compared to existing QA models in answer evaluation. Code and models can be found: https://github.com/LuJunru/EventQAviaPR. Comment: work in process |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2305.04522 |
رقم الأكسشن: | edsarx.2305.04522 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |