3 |
Causal Direction of Data Collection Matters: Implications of Causal and Anticausal Learning for NLP
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
4 |
Classifying Dyads for Militarized Conflict Analysis
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
5 |
Efficient Sampling of Dependency Structure
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
6 |
Searching for More Efficient Dynamic Programs
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 (2021)
|
|
BASE
|
|
Show details
|
|
7 |
“Let Your Characters Tell Their Story”: A Dataset for Character-Centric Narrative Understanding
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 (2021)
|
|
BASE
|
|
Show details
|
|
8 |
A Bayesian Framework for Information-Theoretic Probing
|
|
|
|
In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (2021)
|
|
BASE
|
|
Show details
|
|
9 |
Improving Dialogue State Tracking with Turn-based Loss Function and Sequential Data Augmentation
|
|
|
|
Abstract:
While state-of-the-art Dialogue State Tracking (DST) models show promising results, all of them rely on a traditional cross-entropy loss function during the training process, which may not be optimal for improving the joint goal accuracy. Although several approaches recently propose augmenting the training set by copying user utterances and replacing the real slot values with other possible or even similar values, they are not effective at improving the performance of existing DST models. To address these challenges, we propose a Turn-based Loss Function (TLF) that penalises the model if it inaccurately predicts a slot value at the early turns more so than in later turns in order to improve joint goal accuracy. We also propose a simple but effective Sequential Data Augmentation (SDA) algorithm to generate more complex user utterances and system responses to effectively train existing DST models. Experimental results on two standard DST benchmark collections demonstrate that our proposed TLF and SDA techniques significantly improve the effectiveness of the state-of-the-art DST model by approximately 7-8% relative reduction in error and achieves a new state-of-the-art joint goal accuracy with 59.50 and 54.90 on MultiWOZ2.1 and MultiWOZ2.2, respectively.
|
|
URL: http://eprints.gla.ac.uk/256991/ https://aclanthology.org/2021.findings-emnlp.144 http://eprints.gla.ac.uk/256991/2/256991.pdf
|
|
BASE
|
|
Hide details
|
|
10 |
AWESSOME : An unsupervised sentiment intensity scoring framework using neural word embeddings
|
|
|
|
BASE
|
|
Show details
|
|
11 |
Robust fragment-based framework for cross-lingual sentence retrieval
|
|
|
|
In: Findings of the Association for Computational Linguistics: EMNLP 2021 ; 935 ; 944 (2021)
|
|
BASE
|
|
Show details
|
|
12 |
Evaluating multilingual text encoders for unsupervised cross-lingual retrieval
|
|
|
|
BASE
|
|
Show details
|
|
13 |
Come hither or go away? Recognising pre-electoral coalition signals in the news
|
|
|
|
BASE
|
|
Show details
|
|
14 |
LIIR at SemEval-2020 Task 12: A Cross-Lingual Augmentation Approach for Multilingual Offensive Language Identification ...
|
|
|
|
BASE
|
|
Show details
|
|
15 |
Autoregressive Reasoning over Chains of Facts with Transformers ...
|
|
|
|
BASE
|
|
Show details
|
|
16 |
Rethinking summarization and storytelling for modern social multimedia
|
|
|
|
In: Rudinac, Stevan, Chua, Tat-Seng, Diaz-Ferreyra, Nicolas, Friedland, Gerald, Gornostaja, Tatjana, Huet, Benoit, Kaptein, Rianne, Lindén, Krister, Moens, Marie-Francine, Peltonen, Jaakko, Redi, Miriam, Schedl, Markus, Shamma, David A, Smeaton, Alan F. orcid:0000-0003-1028-8389 and Xie, Lexing (2018) Rethinking summarization and storytelling for modern social multimedia. In: The 24th International Conference on Multimedia Modeling (MMM2018), 5-7 Feb, 2018, Bangkok, Thailand. ISBN 978-3-319-73599-3 (2018)
|
|
BASE
|
|
Show details
|
|
17 |
Word-Level Loss Extensions for Neural Temporal Relation Classification ...
|
|
|
|
BASE
|
|
Show details
|
|
18 |
A deep learning approach to bilingual lexicon induction in the biomedical domain ...
|
|
|
|
BASE
|
|
Show details
|
|
19 |
A deep learning approach to bilingual lexicon induction in the biomedical domain. ...
|
|
|
|
BASE
|
|
Show details
|
|
20 |
A deep learning approach to bilingual lexicon induction in the biomedical domain.
|
|
|
|
BASE
|
|
Show details
|
|
|
|