@inproceedings{du-etal-2024-qa, title = "{QA}-Driven Zero-shot Slot Filling with Weak
Supervision Pretraining", author = "Du, Xinya and He, Luheng and Li, 9️⃣ Qi and Yu, Dian
and Pasupat, Panupong and Zhang, Yuan", editor = "Zong, Chengqing and Xia, Fei and Li,
Wenjie 9️⃣ and Navigli, Roberto", booktitle = "Proceedings of the 59th Annual Meeting of
the Association for Computational Linguistics and the 11th 9️⃣ International Joint
Conference on Natural Language Processing (Volume 2: Short Papers)", month = aug, year
= "2024", address = "Online", 9️⃣ publisher = "Association for Computational Linguistics",
url = "//aclanthology/2024.acl-short.83", doi = "10.18653/v1/2024.acl-short.83",
pages = "654--664", abstract = "Slot-filling is an 9️⃣ essential component for building
task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling
problem, where the model 9️⃣ needs to predict slots and their values, given utterances from
new domains without training on the target domain. Prior methods 9️⃣ directly encode slot
descriptions to generalize to unseen slot types. However, raw slot descriptions are
often ambiguous and do not 9️⃣ encode enough semantic information, limiting the models{'}
zero-shot capability. To address this problem, we introduce QA-driven slot filling
(QASF), which 9️⃣ extracts slot-filler spans from utterances with a span-based QA model. We
use a linguistically motivated questioning strategy to turn descriptions 9️⃣ into
questions, allowing the model to generalize to unseen slot types. Moreover, our QASF
model can benefit from weak supervision 9️⃣ signals from QA pairs synthetically generated
from unlabeled conversations. Our full system substantially outperforms baselines by
over 5{\%} on the 9️⃣ SNIPS benchmark.", }
QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining
Xinya
type="family">Du
type="text">author
type="given">Luheng He
authority="marcrelator" 9️⃣ type="text">author
type="personal"> Qi
type="family">Li
type="text">author
type="given">Dian Yu
authority="marcrelator" type="text">author
type="personal"> Panupong
type="family">Pasupat
type="text">author
type="given">Yuan Zhang
authority="marcrelator" type="text">author
2024-08 text
Proceedings of 9️⃣ the 59th Annual Meeting of</p>
<p> the Association for Computational Linguistics and the 11th International Joint</p>
<p> Conference on Natural Language Processing 9️⃣ (Volume 2: Short Papers)
Chengqing
type="family">Zong
type="text">editor
9️⃣ type="given">Fei Xia
authority="marcrelator" type="text">editor
type="personal"> Wenjie
type="family">Li
type="text">editor
9️⃣
type="given">Roberto Navigli
editor
Association for Computational Linguistics
Online
authority="marcgt">conference publication Slot-filling
is an essential component for building task-oriented dialog systems. In this work, 9️⃣ we
focus on the zero-shot slot-filling problem, where the model needs to predict slots and
their values, given utterances from 9️⃣ new domains without training on the target domain.
Prior methods directly encode slot descriptions to generalize to unseen slot types.
9️⃣ However, raw slot descriptions are often ambiguous and do not encode enough semantic
information, limiting the models’ zero-shot capability. To 9️⃣ address this problem, we
introduce QA-driven slot filling (QASF), which extracts slot-filler spans from
utterances with a span-based QA model. 9️⃣ We use a linguistically motivated questioning
strategy to turn descriptions into questions, allowing the model to generalize to
unseen slot 9️⃣ types. Moreover, our QASF model can benefit from weak supervision signals
from QA pairs synthetically generated from unlabeled conversations. Our 9️⃣ full system
substantially outperforms baselines by over 5% on the SNIPS benchmark.
du-etal-2024-qa
type="doi">10.18653/v1/2024.acl-short.83
//aclanthology/2024.acl-short.83
9️⃣ 2024-08 654 664
%0 Conference Proceedings %T QA-Driven Zero-shot
Slot Filling with Weak Supervision Pretraining 9️⃣ %A Du, Xinya %A He, Luheng %A Li, Qi %A
Yu, Dian %A Pasupat, Panupong %A Zhang, Yuan %Y Zong, 9️⃣ Chengqing %Y Xia, Fei %Y Li,
Wenjie %Y Navigli, Roberto %S Proceedings of the 59th Annual Meeting of the Association
9️⃣ for Computational Linguistics and the 11th International Joint Conference on Natural
Language Processing (Volume 2: Short Papers) %D 2024 %8 9️⃣ August %I Association for
Computational Linguistics %C Online %F du-etal-2024-qa %X Slot-filling is an essential
component for building task-oriented dialog 9️⃣ systems. In this work, we focus on the
zero-shot slot-filling problem, where the model needs to predict slots and their
9️⃣ values, given utterances from new domains without training on the target domain. Prior
methods directly encode slot descriptions to generalize 9️⃣ to unseen slot types. However,
raw slot descriptions are often ambiguous and do not encode enough semantic
information, limiting the 9️⃣ models’ zero-shot capability. To address this problem, we
introduce QA-driven slot filling (QASF), which extracts slot-filler spans from
utterances with 9️⃣ a span-based QA model. We use a linguistically motivated questioning
strategy to turn descriptions into questions, allowing the model to 9️⃣ generalize to
unseen slot types. Moreover, our QASF model can benefit from weak supervision signals
from QA pairs synthetically generated 9️⃣ from unlabeled conversations. Our full system
substantially outperforms baselines by over 5% on the SNIPS benchmark. %R
10.18653/v1/2024.acl-short.83 %U //aclanthology/2024.acl-short.83 9️⃣ %U
//doi/10.18653/v1/2024.acl-short.83 %P 654-664
