Filters








80 Hits in 4.6 sec

Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing [article]

Jonathan Herzig, Jonathan Berant
2018 arXiv   pre-print
In this paper, we introduce a zero-shot approach to semantic parsing that can parse utterances in unseen domains while only being trained on examples in other source domains.  ...  Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize  ...  Acknowledgments We thank Kyle Richardson, Vivek Srikumar and the anonymous reviewers for their constructive feedback.  ... 
arXiv:1804.07918v2 fatcat:oquc4teqprau7g3yntqtnzq7bi

Decoupling Structure and Lexicon for Zero-Shot Semantic Parsing

Jonathan Herzig, Jonathan Berant
2018 Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing  
In this paper, we introduce a zero-shot approach to semantic parsing that can parse utterances in unseen domains while only being trained on examples in other source domains.  ...  Building a semantic parser quickly in a new domain is a fundamental challenge for conversational interfaces, as current semantic parsers require expensive supervision and lack the ability to generalize  ...  Acknowledgments We thank Kyle Richardson, Vivek Srikumar and the anonymous reviewers for their constructive feedback.  ... 
doi:10.18653/v1/d18-1190 dblp:conf/emnlp/HerzigB18 fatcat:cxvadldzdndzvb76a3hhgkgkiq

Robust Zero-Shot Cross-Domain Slot Filling with Example Values

Darsh Shah, Raghav Gupta, Amir Fayazi, Dilek Hakkani-Tur
2019 Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics  
Prior zero-shot slot filling models use slot descriptions to learn concepts, but are not robust to misaligned schemas.  ...  We propose utilizing both the slot description and a small number of examples of slot values, which may be easily available, to learn semantic representations of slots which are transferable across domains  ...  We would also like to thank the Deep Dialogue team at Google Research for their support.  ... 
doi:10.18653/v1/p19-1547 dblp:conf/acl/ShahGFH19 fatcat:qrdmwn45srbdneyourkyaa5nje

Zero-shot Learning of Classifiers from Natural Language Quantification

Shashank Srivastava, Igor Labutov, Tom Mitchell
2018 Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)  
We use semantic parsing to map explanations to probabilistic assertions grounded in latent class labels and observed attributes of unlabeled data, and leverage the differential semantics of linguistic  ...  Experiments on three domains show that the learned classifiers outperform previous approaches for learning with limited data, and are comparable with fully supervised classifiers trained from a small number  ...  The authors would also like to thank the anonymous reviewers for helpful comments and suggestions.  ... 
doi:10.18653/v1/p18-1029 dblp:conf/acl/MitchellSL18 fatcat:fuhmnmaqzbghnjdat3w4ofz3jm

Neural Event Semantics for Grounded Language Understanding

Shyamal Buch, Li Fei-Fei, Noah D. Goodman
2021 Transactions of the Association for Computational Linguistics  
These classifiers apply to spatial regions (events) and NES derives its semantic structure from language by routing events to different classifier argument inputs via soft attention.  ...  We present a new conjunctivist framework, neural event semantics (NES), for compositional grounded language understanding.  ...  Paul Pietroski for helpful discussions and support.  ... 
doi:10.1162/tacl_a_00402 fatcat:m4lm22fvajeupc7xkwyxxnjoiu

Machine Learning with World Knowledge: The Position and Survey [article]

Yangqiu Song, Dan Roth
2017 arXiv   pre-print
representation, inference for knowledge linking and disambiguation, and learning with direct or indirect supervision.  ...  Particularly, labeling large amount of data for each domain-specific problem can be very time consuming and costly.  ...  Government is authorized to reproduce and distribute reprints for Governmental purposes notwithstanding any copyright notation thereon.  ... 
arXiv:1705.02908v1 fatcat:t4fypa6h3vampcp64eosvppsfe

Program Transfer for Answering Complex Questions over Knowledge Bases [article]

Shulin Cao, Jiaxin Shi, Zijun Yao, Xin Lv, Jifan Yu, Lei Hou, Juanzi Li, Zhiyuan Liu, Jinghui Xiao
2022 arXiv   pre-print
For program transfer, we design a novel two-stage parsing framework with an efficient ontology-guided pruning strategy.  ...  Second, given the question and sketch, an argument parser searches the detailed arguments from the KB for functions. During the searching, we incorporate the KB ontology to prune the search space.  ...  Other works consider a zero-shot semantic parsing task (Givoli and Reichart, 2019) , decoupling structures from lexicons for transfer.  ... 
arXiv:2110.05743v3 fatcat:roq4z6smuzhf3mn34oahbdcsee

Refining Language Models with Compositional Explanations [article]

Huihan Yao, Ying Chen, Qinyuan Ye, Xisen Jin, Xiang Ren
2021 arXiv   pre-print
We additionally introduce a regularization term allowing adjustments for both importance and interaction of features to better rectify model behavior.  ...  By parsing these explanations into executable logic rules, the human-specified refinement advice from a small set of explanations can be generalized to more training examples.  ...  Acknowledgments and Disclosure of Funding  ... 
arXiv:2103.10415v3 fatcat:g7qy7gpevzc2zbees74zt4folm

Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey [article]

Bonan Min, Hayley Ross, Elior Sulem, Amir Pouran Ben Veyseh, Thien Huu Nguyen, Oscar Sainz, Eneko Agirre, Ilana Heinz, Dan Roth
2021 arXiv   pre-print
We conclude with discussions on limitations and suggested directions for future research.  ...  We also present approaches that use pre-trained language models to generate data for training augmentation or other purposes.  ...  Acknowledgments We would like to thank Paul Cummer for his insightful comments on this work.  ... 
arXiv:2111.01243v1 fatcat:4xfjkkby2bfnhdrhmrdlliy76m

Word Alignment by Fine-tuning Embeddings on Parallel Corpora [article]

Zi-Yi Dou, Graham Neubig
2021 arXiv   pre-print
Word alignment over parallel corpora has a wide variety of applications, including learning translation lexicons, cross-lingual transfer of language processing tools, and automatic evaluation or analysis  ...  We perform experiments on five language pairs and demonstrate that our model can consistently outperform previous state-of-the-art models of all varieties.  ...  Acknowledgement We thank our reviewers for helpful suggestions.  ... 
arXiv:2101.08231v4 fatcat:2szocktps5dsjfqsqkuodn4vwm

A survey of joint intent detection and slot filling models in natural language understanding

Henry Weld, Xiaoqi Huang, Siqu Long, Josiah Poon, Soyeon Caren Han
2022 ACM Computing Surveys  
Intent classification, to identify the speaker's intention, and slot filling, to label each token with a semantic type, are critical tasks in natural language understanding.  ...  More recently joint models, that address the two tasks together, have achieved state-of-the-art performance for each task, and have shown there exists a strong relationship between the two.  ...  We further note that all the few and zero shot papers reviewed use annotated data sets for evaluation, hence still need to be transferred to new unseen data sets.  ... 
doi:10.1145/3547138 fatcat:sbv2bqasqba6zkojqmi4jb4blm

Asking It All: Generating Contextualized Questions for any Semantic Role [article]

Valentina Pyatkin, Paul Roit, Julian Michael, Reut Tsarfaty, Yoav Goldberg, Ido Dagan
2021 arXiv   pre-print
Our evaluation demonstrates that we generate diverse and well-formed questions for a large, broad-coverage ontology of predicates and roles.  ...  We develop a two-stage model for this task, which first produces a context-independent question prototype for each role and then revises it to be contextually appropriate for the passage.  ...  Acknowledgments We would like to thank Daniela Brook-Weiss for helping in the initial stages of this project and the anonymous reviewers for their insightful comments.  ... 
arXiv:2109.04832v1 fatcat:lknnmgojpjhanevfp2cqydsw2y

Reinforcement Learning-based Dialogue Guided Event Extraction to Exploit Argument Relations [article]

Qian Li, Hao Peng, Jianxin Li, Jia Wu, Yuanxing Ning, Lihong Wang, Philip S. Yu, Zheng Wang
2021 arXiv   pre-print
Experimental results show that our approach consistently outperforms seven state-of-the-art event extraction methods for the classification of events and argument role and argument identification.  ...  While the relationship and interactions between multiple arguments are useful for settling the argument roles, such information is largely ignored by existing approaches.  ...  R ELATED W ORK representations from the parsed AMR structure [39].  ... 
arXiv:2106.12384v2 fatcat:blyylym77vdupbrolil2dtmrna

Hierarchical Control of Situated Agents through Natural Language [article]

Shuyan Zhou, Pengcheng Yin, Graham Neubig
2021 arXiv   pre-print
We also demonstrate that our framework is more data-efficient, and that it allows for fast iterative development.  ...  We instantiate this framework on the IQA and ALFRED datasets for NL instruction following. Our model outperforms reactive baselines by a large margin on both datasets.  ...  Yoav Artzi, Dipanjan Das, and Slav Petrov. 2014. Learning compact lexicons for CCG semantic pars- ing.  ... 
arXiv:2109.08214v1 fatcat:ujz6bla7zneo7n7uzz4fa46kti

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
12, 2021 Eum, Sungmin; Kwon, Heesung 536 Semantics to Space(S2S): Embedding semantics into spatial space for zero-shot verb-object query inferencing DAY 1 -Jan 12, 2021 Li, Runze; Bhanu, Bir  ...  13, 2021 Liu, Tengfei; Hu, Yongli; Gao, Junbin; Sun, Yanfeng; Yin, Baocai 2294 Zero-Shot Text Classification with Semantically Extended Graph Convolutional Network DAY 2 -Jan 13, 2021 Xin, Yuan  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm
« Previous Showing results 1 — 15 out of 80 results