Interpretable Natural Language Understanding

Interpretable Natural Language Understanding
复制标题

可解释的自然语言理解

DOI:
10.1145/3583780.3615315
复制
发表时间:
2023
期刊:
--
影响因子:
--
通讯作者:
He Y
He Y
中科院分区:
--
文献类型:
--
作者:
He Y

文献摘要

参考文献

相似文献

近年来,我们见证了自然语言处理(NLP)范式的转变,从对特定任务数据的大规模预训练语言模型(PLM)进行微调到基于任务的学习。在后者中,任务描述被嵌入到PLM输入中,使同一模型能够处理多个任务。虽然这两种方法在各种NLP任务中表现出令人印象深刻的性能,但它们的不透明性使得理解它们的内部工作和决策过程对人类具有挑战性。在这次演讲中,我将分享我的团队进行的研究,以解决语言理解中围绕神经模型的可解释性问题。这包括超越单词级解释的分层可解释文本分类器,基于PLM构建的文本分类器的不确定性解释,通过利用不同模式的信息来解释的推荐系统,以及可解释的学生答案评分。我将通过提供对可解释语言理解的潜在未来发展的见解来结束我的演讲。
In recent years, we have witnessed the shift of paradigms in Natural Language Processing (NLP) from fine-tuning large-scale pre-trained language models (PLMs) on task-specific data to prompt-based learning. In the latter, the task description is embedded into the PLM input, enabling the same model to handle multiple tasks. While both approaches have demonstrated impressive performance in various NLP tasks, their opaque nature makes comprehending their inner workings and decision-making processes challenging for humans.In this talk, I will share the research undertaken in my group to address the interpretability concerns surrounding neural models in language understanding. This includes a hierarchical interpretable text classifier going beyond word-level interpretations, uncertainty interpretation of text classifiers built on PLMs, explainable recommender systems by harnessing information across diverse modalities, and explainable student answer scoring. I will conclude my talk by offering insights into potential future developments in interpretable language understanding.
提炼 ChatGPT 以进行可解释的自动化学生答案评估
DOI: 10.18653/v1/2023.findings-emnlp.399
发表时间: 2023
期刊: --
影响因子: --
作者:
Li J
通讯作者: Li J
DOI: 10.48550/arxiv.2202.09792
发表时间: 2022
期刊: --
影响因子: --
作者:
Yan H
通讯作者: Yan H