Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913285001969664 |
|---|---|
| author | Pryor, Connor Yuan, Quan Liu, Jeremiah Kazemi, Mehran Ramachandran, Deepak Bedrax-Weiss, Tania Getoor, Lise |
| author_facet | Pryor, Connor Yuan, Quan Liu, Jeremiah Kazemi, Mehran Ramachandran, Deepak Bedrax-Weiss, Tania Getoor, Lise |
| contents | Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design and discourse analysis. Existing DSI approaches are often purely data-driven, deploy models that infer latent states without access to domain knowledge, underperform when the training corpus is limited/noisy, or have difficulty when test dialogs exhibit distributional shifts from the training domain. This work explores a neural-symbolic approach as a potential solution to these problems. We introduce Neural Probabilistic Soft Logic Dialogue Structure Induction (NEUPSL DSI), a principled approach that injects symbolic knowledge into the latent space of a generative neural model. We conduct a thorough empirical investigation on the effect of NEUPSL DSI learning on hidden representation quality, few-shot learning, and out-of-domain generalization performance. Over three dialog structure induction datasets and across unsupervised and semi-supervised settings for standard and cross-domain generalization, the injection of symbolic knowledge using NEUPSL DSI provides a consistent boost in performance over the canonical baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_17853 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic Pryor, Connor Yuan, Quan Liu, Jeremiah Kazemi, Mehran Ramachandran, Deepak Bedrax-Weiss, Tania Getoor, Lise Computation and Language Machine Learning Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design and discourse analysis. Existing DSI approaches are often purely data-driven, deploy models that infer latent states without access to domain knowledge, underperform when the training corpus is limited/noisy, or have difficulty when test dialogs exhibit distributional shifts from the training domain. This work explores a neural-symbolic approach as a potential solution to these problems. We introduce Neural Probabilistic Soft Logic Dialogue Structure Induction (NEUPSL DSI), a principled approach that injects symbolic knowledge into the latent space of a generative neural model. We conduct a thorough empirical investigation on the effect of NEUPSL DSI learning on hidden representation quality, few-shot learning, and out-of-domain generalization performance. Over three dialog structure induction datasets and across unsupervised and semi-supervised settings for standard and cross-domain generalization, the injection of symbolic knowledge using NEUPSL DSI provides a consistent boost in performance over the canonical baselines. |
| title | Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic |
| topic | Computation and Language Machine Learning |
| url | https://arxiv.org/abs/2403.17853 |