Papers by Xinyun Chen

9 papers
Symbol tuning improves in-context learning in language models (2023.emnlp-main)

Copied to clipboard

Challenge: Language models are sensitive to the way that prompts are given, indicating that they are not reasoning in a robust manner.
Approach: They propose to fine tune language models on in-context input-label pairs where natural language labels are replaced with arbitrary symbols.
Outcome: The proposed model is much stronger at reasoning tasks and more robust to underspecified prompts than the standard model.
Exploring Underexplored Limitations of Cross-Domain Text-to-SQL Generalization (2021.emnlp-main)

Copied to clipboard

Challenge: Existing text-to-SQL models do not generalize when faced with domain knowledge that does not frequently appear in training data.
Approach: They propose a human-curated dataset based on the Spider benchmark for text-to-SQL translation.
Outcome: The proposed model performs better on unseen domains than existing models on public benchmarks.
PlotCoder: Hierarchical Decoding for Synthesizing Visualization Code in Programmatic Context (2021.acl-long)

Copied to clipboard

Challenge: Creating effective visualizations is a challenge given the myriad of parameters that users need to provide.
Approach: They propose to synthesize visualization programs from natural language utterances and programmatic context using PlotCoder.
Outcome: The proposed architecture models both the code context and the input utterance.
Benchmarking Language Models for Code Syntax Understanding (2022.findings-emnlp)

Copied to clipboard

Challenge: Pre-trained language models capture the syntactic rules of natural languages without fine-tuning on syntax understanding tasks.
Approach: They propose a benchmarking test to compare pre-trained language models with a large-scale dataset of programs annotated with syntactic relationships in their corresponding abstract syntax trees.
Outcome: The proposed model fails to match baselines based on positional offsets and keywords.
Measuring and Improving Compositional Generalization in Text-to-SQL via Component Alignment (2022.findings-naacl)

Copied to clipboard

Challenge: Existing models suffer performance degradation when evaluated on Spider-CG, even though every sub-sentence is seen during training.
Approach: They propose a clause-level compositional example generation method to generate compositional biases from SQL clauses.
Outcome: The proposed method improves generalization performance even on a training dataset.
Exploring Label Hierarchy in a Generative Way for Hierarchical Text Classification (2022.coling-1)

Copied to clipboard

Challenge: Existing methods for hierarchical text classification are lacking in the field of natural language processing.
Approach: They propose a hierarchy-aware T5 model with path-adaptive attention mechanism to exploit hierarchical dependency across different levels.
Outcome: The proposed model outperforms state-of-the-art models especially in Macro-F1 and low Macro.
Towards Robustness of Text-to-SQL Models against Synonym Substitution (2021.acl-long)

Copied to clipboard

Challenge: Existing text-to-SQL models rely on lexical matching between words in NL questions and tokens in table schemas, which may break the schema linking mechanism.
Approach: They propose a human-curated dataset for text-to-SQL translation . they replace schema-related words with manually selected synonyms .
Outcome: The proposed model outperforms its counterparts without the defense.
Natural SQL: Making SQL Easier to Infer from Natural Language Specifications (2021.findings-emnlp)

Copied to clipboard

Challenge: Existing models that do not support executable SQL generation can generate executable queries.
Approach: They propose an SQL intermediate representation called Natural SQL (NatSQL) they propose to preserve the core functionalities of SQL while simplifying the queries .
Outcome: The proposed model outperforms existing models on a text-to-SQL benchmark . it significantly improves the performance of previous models on the same dataset .
Re-appraising the Schema Linking for Text-to-SQL (2023.findings-acl)

Copied to clipboard

Challenge: Recent work has shown that schema linking reduces robustness of text-to-SQL models . EMSL is used to correlate natural language queries with the given database schema .
Approach: They propose a grammar linking module to help model align grammar references with SQL keywords.
Outcome: The proposed language model improves performance without using EMSL, the authors show . their language model is more robust, and the proposed grammar linking improves interoperability .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations