Injecting linguistic knowledge into BERT for Dialogue State Tracking

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Feng, Xiaohan, Wu, Xixin, Meng, Helen
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913427417464832
author Feng, Xiaohan
Wu, Xixin
Meng, Helen
author_facet Feng, Xiaohan
Wu, Xixin
Meng, Helen
contents Dialogue State Tracking (DST) models often employ intricate neural network architectures, necessitating substantial training data, and their inference process lacks transparency. This paper proposes a method that extracts linguistic knowledge via an unsupervised framework and subsequently utilizes this knowledge to augment BERT's performance and interpretability in DST tasks. The knowledge extraction procedure is computationally economical and does not require annotations or additional training data. The injection of the extracted knowledge can be achieved by the addition of simple neural modules. We employ the Convex Polytopic Model (CPM) as a feature extraction tool for DST tasks and illustrate that the acquired features correlate with syntactic and semantic patterns in the dialogues. This correlation facilitates a comprehensive understanding of the linguistic features influencing the DST model's decision-making process. We benchmark this framework on various DST tasks and observe a notable improvement in accuracy.
format Preprint
id arxiv_https___arxiv_org_abs_2311_15623
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Injecting linguistic knowledge into BERT for Dialogue State Tracking
Feng, Xiaohan
Wu, Xixin
Meng, Helen
Computation and Language
Artificial Intelligence
Machine Learning
Dialogue State Tracking (DST) models often employ intricate neural network architectures, necessitating substantial training data, and their inference process lacks transparency. This paper proposes a method that extracts linguistic knowledge via an unsupervised framework and subsequently utilizes this knowledge to augment BERT's performance and interpretability in DST tasks. The knowledge extraction procedure is computationally economical and does not require annotations or additional training data. The injection of the extracted knowledge can be achieved by the addition of simple neural modules. We employ the Convex Polytopic Model (CPM) as a feature extraction tool for DST tasks and illustrate that the acquired features correlate with syntactic and semantic patterns in the dialogues. This correlation facilitates a comprehensive understanding of the linguistic features influencing the DST model's decision-making process. We benchmark this framework on various DST tasks and observe a notable improvement in accuracy.
title Injecting linguistic knowledge into BERT for Dialogue State Tracking
topic Computation and Language
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2311.15623