A survey on non-autoregressive generation for neural machine translation and beyond

Y **ao, L Wu, J Guo, J Li, M Zhang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Non-autoregressive (NAR) generation, which is first proposed in neural machine translation
(NMT) to speed up inference, has attracted much attention in both machine learning and …

Token-level self-evolution training for sequence-to-sequence learning

K Peng, L Ding, Q Zhong, Y Ouyang… - Proceedings of the …, 2023 - aclanthology.org
Adaptive training approaches, widely used in sequence-to-sequence models, commonly
reweigh the losses of different target tokens based on priors, eg word frequency. However …

Findings of the IWSLT 2022 Evaluation Campaign.

A Anastasopoulos, L Barrault, L Bentivogli… - Proceedings of the 19th …, 2022 - cris.fbk.eu
The evaluation campaign of the 19th International Conference on Spoken Language
Translation featured eight shared tasks:(i) Simultaneous speech translation,(ii) Offline …

Knowledge graph augmented network towards multiview representation learning for aspect-based sentiment analysis

Q Zhong, L Ding, J Liu, B Du, H **… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To
better comprehend long complicated sentences and obtain accurate aspect-specific …

GL-GIN: Fast and accurate non-autoregressive model for joint multiple intent detection and slot filling

L Qin, F Wei, T **e, X Xu, W Che, T Liu - arxiv preprint arxiv:2106.01925, 2021 - arxiv.org
Multi-intent SLU can handle multiple intents in an utterance, which has attracted increasing
attention. However, the state-of-the-art joint models heavily rely on autoregressive …

Mrrl: Modifying the reference via reinforcement learning for non-autoregressive joint multiple intent detection and slot filling

X Cheng, Z Zhu, B Cao, Q Ye, Y Zou - Findings of the Association …, 2023 - aclanthology.org
With the rise of non-autoregressive approach, some non-autoregressive models for joint
multiple intent detection and slot filling have obtained the promising inference speed …

Towards spoken language understanding via multi-level multi-grained contrastive learning

X Cheng, W Xu, Z Zhu, H Li, Y Zou - Proceedings of the 32nd ACM …, 2023 - dl.acm.org
Spoken language understanding (SLU) is a core task in task-oriented dialogue systems,
which aims at understanding user's current goal through constructing semantic frames. SLU …

Multitask learning for multilingual intent detection and slot filling in dialogue systems

M Firdaus, A Ekbal, E Cambria - Information Fusion, 2023 - Elsevier
Dialogue systems are becoming an ubiquitous presence in our everyday lives having a
huge impact on business and society. Spoken language understanding (SLU) is the critical …

Co-guiding net: Achieving mutual guidances between multiple intent detection and slot filling via heterogeneous semantics-label graphs

B **ng, IW Tsang - arxiv preprint arxiv:2210.10375, 2022 - arxiv.org
Recent graph-based models for joint multiple intent detection and slot filling have obtained
promising results through modeling the guidance from the prediction of intents to the …

NLU++: A multi-label, slot-rich, generalisable dataset for natural language understanding in task-oriented dialogue

I Casanueva, I Vulić, GP Spithourakis… - arxiv preprint arxiv …, 2022 - arxiv.org
We present NLU++, a novel dataset for natural language understanding (NLU) in task-
oriented dialogue (ToD) systems, with the aim to provide a much more challenging …