Search Results for author: Menglin Xia

Found 5 papers, 2 papers with code

Hybrid Retrieval-Augmented Generation for Real-time Composition Assistance

no code implementations8 Aug 2023 Xuchao Zhang, Menglin Xia, Camille Couturier, Guoqing Zheng, Saravan Rajmohan, Victor Ruhle

By integrating this retrieval augmented memory, the client model acquires the capability to generate highly effective responses, benefiting from the LLM's capabilities.

Language Modelling Large Language Model +1

Multilingual Neural Semantic Parsing for Low-Resourced Languages

1 code implementation Joint Conference on Lexical and Computational Semantics 2021 Menglin Xia, Emilio Monti

To evaluate our multilingual models on human-written sentences as opposed to machine translated ones, we introduce a new multilingual semantic parsing dataset in English, Italian and Japanese based on the Facebook Task Oriented Parsing (TOP) dataset.

Machine Translation Semantic Parsing +3

Generating Semantically Valid Adversarial Questions for TableQA

no code implementations26 May 2020 Yi Zhu, Yiwei Zhou, Menglin Xia

Finally, we demonstrate that adversarial training with SAGE augmented data can improve performance and robustness of TableQA systems.

Adversarial Attack Question Answering

Automatic learner summary assessment for reading comprehension

no code implementations NAACL 2019 Menglin Xia, Ekaterina Kochmar, Ted Briscoe

Automating the assessment of learner summaries provides a useful tool for assessing learner reading comprehension.

Reading Comprehension

Cannot find the paper you are looking for? You can Submit a new open access paper.