An Imitation Game for Learning Semantic Parsers from User Interaction
- URL: http://arxiv.org/abs/2005.00689v3
- Date: Thu, 15 Oct 2020 18:31:26 GMT
- Title: An Imitation Game for Learning Semantic Parsers from User Interaction
- Authors: Ziyu Yao, Yiqi Tang, Wen-tau Yih, Huan Sun, Yu Su
- Abstract summary: We suggest an alternative, human-in-the-loop methodology for learning semantic annotations directly from users.
A semantic should be introspective and prompt for user demonstration when uncertain.
In doing so it also gets to imitate the user behavior and continue improving itself autonomously.
- Score: 43.66945504686796
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Despite the widely successful applications, bootstrapping and fine-tuning
semantic parsers are still a tedious process with challenges such as costly
data annotation and privacy risks. In this paper, we suggest an alternative,
human-in-the-loop methodology for learning semantic parsers directly from
users. A semantic parser should be introspective of its uncertainties and
prompt for user demonstration when uncertain. In doing so it also gets to
imitate the user behavior and continue improving itself autonomously with the
hope that eventually it may become as good as the user in interpreting their
questions. To combat the sparsity of demonstration, we propose a novel
annotation-efficient imitation learning algorithm, which iteratively collects
new datasets by mixing demonstrated states and confident predictions and
re-trains the semantic parser in a Dataset Aggregation fashion (Ross et al.,
2011). We provide a theoretical analysis of its cost bound and also empirically
demonstrate its promising performance on the text-to-SQL problem. Code will be
available at https://github.com/sunlab-osu/MISP.
Related papers
- Vocabulary-Defined Semantics: Latent Space Clustering for Improving In-Context Learning [32.178931149612644]
In-context learning enables language models to adapt to downstream data or incorporate tasks by few samples as demonstrations within the prompts.
However, the performance of in-context learning can be unstable depending on the quality, format, or order of demonstrations.
We propose a novel approach "vocabulary-defined semantics"
arXiv Detail & Related papers (2024-01-29T14:29:48Z) - Understanding Before Recommendation: Semantic Aspect-Aware Review Exploitation via Large Language Models [53.337728969143086]
Recommendation systems harness user-item interactions like clicks and reviews to learn their representations.
Previous studies improve recommendation accuracy and interpretability by modeling user preferences across various aspects and intents.
We introduce a chain-based prompting approach to uncover semantic aspect-aware interactions.
arXiv Detail & Related papers (2023-12-26T15:44:09Z) - Learning to Simulate Natural Language Feedback for Interactive Semantic
Parsing [30.609805601567178]
We propose a new task simulating NL feedback for interactive semantic parsing.
We accompany the task with a novel feedback evaluator.
Our feedback simulator can help achieve comparable error correction performance as trained using the costly, full set of human annotations.
arXiv Detail & Related papers (2023-05-14T16:20:09Z) - Privacy-Preserving Domain Adaptation of Semantic Parsers [44.266262213139534]
We propose a two-stage Differentially Private (DP) generation method which first generates latent semantic parses, and then generates utterances based on the parses.
Our proposed approach improves MAUVE by 2.5$times$ and parse tree function type overlap by 1.3$times$ relative to current approaches for private synthetic data generation.
arXiv Detail & Related papers (2022-12-20T18:35:21Z) - SUN: Exploring Intrinsic Uncertainties in Text-to-SQL Parsers [61.48159785138462]
This paper aims to improve the performance of text-to-dependence by exploring the intrinsic uncertainties in the neural network based approaches (called SUN)
Extensive experiments on five benchmark datasets demonstrate that our method significantly outperforms competitors and achieves new state-of-the-art results.
arXiv Detail & Related papers (2022-09-14T06:27:51Z) - FineDiving: A Fine-grained Dataset for Procedure-aware Action Quality
Assessment [93.09267863425492]
We argue that understanding both high-level semantics and internal temporal structures of actions in competitive sports videos is the key to making predictions accurate and interpretable.
We construct a new fine-grained dataset, called FineDiving, developed on diverse diving events with detailed annotations on action procedures.
arXiv Detail & Related papers (2022-04-07T17:59:32Z) - On The Ingredients of an Effective Zero-shot Semantic Parser [95.01623036661468]
We analyze zero-shot learning by paraphrasing training examples of canonical utterances and programs from a grammar.
We propose bridging these gaps using improved grammars, stronger paraphrasers, and efficient learning methods.
Our model achieves strong performance on two semantic parsing benchmarks (Scholar, Geo) with zero labeled data.
arXiv Detail & Related papers (2021-10-15T21:41:16Z) - Infusing Finetuning with Semantic Dependencies [62.37697048781823]
We show that, unlike syntax, semantics is not brought to the surface by today's pretrained models.
We then use convolutional graph encoders to explicitly incorporate semantic parses into task-specific finetuning.
arXiv Detail & Related papers (2020-12-10T01:27:24Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.