mitzvahceremonies.com:2024/10/20 20:34:51
O porto de Gwadar, localizado na 1️⃣ província do Baluchistan, tem suas origens no financiamento chinês.
Quetta é 1️⃣ a capital da província do Baluchistan, onde também há uma presença de militantes islâmicos.
@inproceedings{du-etal-2024-qa, title = "{QA}-Driven Zero-shot Slot Filling with Weak
Supervision Pretraining", author = "Du, Xinya and He, Luheng and Li, 💰 Qi and Yu, Dian
and Pasupat, Panupong and Zhang, Yuan", editor = "Zong, Chengqing and Xia, Fei and Li,
Wenjie 💰 and Navigli, Roberto", booktitle = "Proceedings of the 59th Annual Meeting of
the Association for Computational Linguistics and the 11th 💰 International Joint
Conference on Natural Language Processing (Volume 2: Short Papers)", month = aug, year
= "2024", address = "Online", 💰 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 💰 essential component for building
task-oriented dialog systems. In this work, we focus on the zero-shot slot-filling
problem, where the model 💰 needs to predict slots and their values, given utterances from
new domains without training on the target domain. Prior methods 💰 directly encode slot
descriptions to generalize to unseen slot types. However, raw slot descriptions are
often ambiguous and do not 💰 encode enough semantic information, limiting the models{'}
zero-shot capability. To address this problem, we introduce QA-driven slot filling
(QASF), which 💰 extracts slot-filler spans from utterances with a span-based QA model. We
use a linguistically motivated questioning strategy to turn descriptions 💰 into
questions, allowing the model to generalize to unseen slot types. Moreover, our QASF
model can benefit from weak supervision 💰 signals from QA pairs synthetically generated
from unlabeled conversations. Our full system substantially outperforms baselines by
over 5{\%} on the 💰 SNIPS benchmark.", }
type="family">Du type="text">author type="given">Luheng authority="marcrelator" 💰 type="text">author type="personal"> type="family">Li type="text">author type="given">Dian authority="marcrelator" type="text">author type="personal"> type="family">Pasupat type="text">author type="given">Yuan authority="marcrelator" type="text">author type="family">Zong type="text">editor 💰 type="given">Fei authority="marcrelator" type="text">editor type="personal"> type="family">Li type="text">editor type="given">Roberto authority="marcgt">conference publication is an essential component for building task-oriented dialog systems. In this work, 💰 we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their values, given utterances from 💰 new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize to unseen slot types. 💰 However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the models’ zero-shot capability. To 💰 address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with a span-based QA model. 💰 We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to generalize to unseen slot 💰 types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated from unlabeled conversations. Our 💰 full system substantially outperforms baselines by over 5% on the SNIPS benchmark. type="doi">10.18653/v1/2024.acl-short.83 💰 %0 Conference Proceedings %T QA-Driven Zero-shot Slot Filling with Weak Supervision Pretraining 💰 %A Du, Xinya %A He, Luheng %A Li, Qi %A Yu, Dian %A Pasupat, Panupong %A Zhang, Yuan %Y Zong, 💰 Chengqing %Y Xia, Fei %Y Li, Wenjie %Y Navigli, Roberto %S Proceedings of the 59th Annual Meeting of the Association 💰 for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) %D 2024 %8 💰 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 💰 systems. In this work, we focus on the zero-shot slot-filling problem, where the model needs to predict slots and their 💰 values, given utterances from new domains without training on the target domain. Prior methods directly encode slot descriptions to generalize 💰 to unseen slot types. However, raw slot descriptions are often ambiguous and do not encode enough semantic information, limiting the 💰 models’ zero-shot capability. To address this problem, we introduce QA-driven slot filling (QASF), which extracts slot-filler spans from utterances with 💰 a span-based QA model. We use a linguistically motivated questioning strategy to turn descriptions into questions, allowing the model to 💰 generalize to unseen slot types. Moreover, our QASF model can benefit from weak supervision signals from QA pairs synthetically generated 💰 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 💰 %U //doi/10.18653/v1/2024.acl-short.83 %P 654-664
artigos relacionados
2024/10/20 20:34:51