Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema
Task-oriented dialog systems empower users to accom- plish their goals by facilitating intuitive and expres- sive natural language interactions. State-of-the-art ap- proaches in task-oriented dialog systems formulate the problem as a conditional sequence generation task and fine-tune pre-trained cau...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
LibraryPress@UF
2023-05-01
|
| Series: | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| Subjects: | |
| Online Access: | https://journals.flvc.org/FLAIRS/article/view/133072 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850271256556863488 |
|---|---|
| author | Adib Mosharrof M.H. Maqbool A.B. Siddique |
| author_facet | Adib Mosharrof M.H. Maqbool A.B. Siddique |
| author_sort | Adib Mosharrof |
| collection | DOAJ |
| description | Task-oriented dialog systems empower users to accom-
plish their goals by facilitating intuitive and expres-
sive natural language interactions. State-of-the-art ap-
proaches in task-oriented dialog systems formulate the
problem as a conditional sequence generation task and
fine-tune pre-trained causal language models in the su-
pervised setting. This requires labeled training data
for each new domain or task, and acquiring such data
is prohibitively laborious and expensive, thus making
it a bottleneck for scaling systems to a wide range
of domains. To overcome this challenge, we intro-
duce a novel Zero-Shot generalizable end-to-end Task-
oriented Dialog system, ZS-ToD, that leverages domain
schemas to allow for robust generalization to unseen do-
mains and exploits effective summarization of the dia-
log history. We employ GPT-2 as a backbone model and
introduce a two-step training process where the goal of
the first step is to learn the general structure of the dialog
data and the second step optimizes the response gen-
eration as well as intermediate outputs, such as dialog
state and system actions. As opposed to state-of-the-art
systems that are trained to fulfill certain intents in the
given domains and memorize task-specific conversa-
tional patterns, ZS-ToD learns generic task-completion
skills by comprehending domain semantics via domain
schemas and generalizing to unseen domains seam-
lessly. We conduct an extensive experimental evaluation
on SGD and SGD-X datasets that span up to 20 unique
domains and ZS-ToD outperforms state-of-the-art sys-
tems on key metrics, with an improvement of +17% on
joint goal accuracy and +5 on inform. Additionally,
we present a detailed ablation study to demonstrate the
effectiveness of the proposed components and training
mechanism. |
| format | Article |
| id | doaj-art-4710ea83ef8a49e6867d78485b69f65a |
| institution | OA Journals |
| issn | 2334-0754 2334-0762 |
| language | English |
| publishDate | 2023-05-01 |
| publisher | LibraryPress@UF |
| record_format | Article |
| series | Proceedings of the International Florida Artificial Intelligence Research Society Conference |
| spelling | doaj-art-4710ea83ef8a49e6867d78485b69f65a2025-08-20T01:52:18ZengLibraryPress@UFProceedings of the International Florida Artificial Intelligence Research Society Conference2334-07542334-07622023-05-013610.32473/flairs.36.13307269340Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain SchemaAdib Mosharrof0https://orcid.org/0000-0002-8960-8455M.H. Maqbool1https://orcid.org/0009-0006-9547-666XA.B. Siddique2https://orcid.org/0000-0002-3587-7289University of KentuckyUniversity of Central FloridaUniversity of KentuckyTask-oriented dialog systems empower users to accom- plish their goals by facilitating intuitive and expres- sive natural language interactions. State-of-the-art ap- proaches in task-oriented dialog systems formulate the problem as a conditional sequence generation task and fine-tune pre-trained causal language models in the su- pervised setting. This requires labeled training data for each new domain or task, and acquiring such data is prohibitively laborious and expensive, thus making it a bottleneck for scaling systems to a wide range of domains. To overcome this challenge, we intro- duce a novel Zero-Shot generalizable end-to-end Task- oriented Dialog system, ZS-ToD, that leverages domain schemas to allow for robust generalization to unseen do- mains and exploits effective summarization of the dia- log history. We employ GPT-2 as a backbone model and introduce a two-step training process where the goal of the first step is to learn the general structure of the dialog data and the second step optimizes the response gen- eration as well as intermediate outputs, such as dialog state and system actions. As opposed to state-of-the-art systems that are trained to fulfill certain intents in the given domains and memorize task-specific conversa- tional patterns, ZS-ToD learns generic task-completion skills by comprehending domain semantics via domain schemas and generalizing to unseen domains seam- lessly. We conduct an extensive experimental evaluation on SGD and SGD-X datasets that span up to 20 unique domains and ZS-ToD outperforms state-of-the-art sys- tems on key metrics, with an improvement of +17% on joint goal accuracy and +5 on inform. Additionally, we present a detailed ablation study to demonstrate the effectiveness of the proposed components and training mechanism.https://journals.flvc.org/FLAIRS/article/view/133072task oriented dialog systemgptnatural language processingsgd datasetdstc8end to end todzero shot generalizable |
| spellingShingle | Adib Mosharrof M.H. Maqbool A.B. Siddique Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema Proceedings of the International Florida Artificial Intelligence Research Society Conference task oriented dialog system gpt natural language processing sgd dataset dstc8 end to end tod zero shot generalizable |
| title | Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema |
| title_full | Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema |
| title_fullStr | Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema |
| title_full_unstemmed | Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema |
| title_short | Zero-Shot Generalizable End-to-End Task-Oriented Dialog System using Context Summarization and Domain Schema |
| title_sort | zero shot generalizable end to end task oriented dialog system using context summarization and domain schema |
| topic | task oriented dialog system gpt natural language processing sgd dataset dstc8 end to end tod zero shot generalizable |
| url | https://journals.flvc.org/FLAIRS/article/view/133072 |
| work_keys_str_mv | AT adibmosharrof zeroshotgeneralizableendtoendtaskorienteddialogsystemusingcontextsummarizationanddomainschema AT mhmaqbool zeroshotgeneralizableendtoendtaskorienteddialogsystemusingcontextsummarizationanddomainschema AT absiddique zeroshotgeneralizableendtoendtaskorienteddialogsystemusingcontextsummarizationanddomainschema |