paper-with-me

홈 › Papers

Imitation Learning of Agenda-based Semantic Parsers

2015-01-01 · TACL 2015 1 · Jonathan Berant, Percy Liang

Semantic parsers conventionally construct logical forms bottom-up in a fixed order, resulting in the generation of many extraneous partial logical forms. In this paper, we combine ideas from imitation learning and agenda-based parsing to train a semantic parser that searches partial logical forms in a more strategic order. Empirically, our parser reduces the number of constructed partial logical forms by an order of magnitude, and obtains a 6x-9x speedup over fixed-order parsing, while maintaining comparable accuracy.

📄 PDF Abstract BibTeX

Code (1)

https://worksheets.codalab.org/worksheets/0x8fdfad310dd84b7baf683b520b4b64d5 공식 구현

Tasks

Imitation LearningQuestion AnsweringSemantic Parsing

Similar Papers 제목 키워드 기반

An Imitation Game for Learning Semantic Parsers from User Interaction

2020-05-02 · EMNLP 2020 11 · Ziyu Yao, Yiqi Tang, Wen-tau Yih, Huan Sun 외

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 altern…

Imitation LearningText to SQLText-To-SQL

Fast Domain Adaptation of Semantic Parsers via Paraphrase Attention

2019-11-01 · WS 2019 11 · Avik Ray, Yilin Shen, Hongxia Jin

Semantic parsers are used to convert user{'}s natural language commands to executable logical form in intelligent personal agents. Labeled datasets required to train such parsers are expensive to collect, and are never c…

Domain Adaptation

Is neural semantic parsing good at ellipsis resolution, or isn't it?

2025-07-31 · Xiao Zhang, Johan bos arxiv

Neural semantic parsers have shown good overall performance for a variety of linguistic phenomena, reaching semantic matching scores of more than 90%. But how do such parsers perform on strongly context-sensitive phenome…

Data AugmentationSemantic Parsing

On Robustness of Neural Semantic Parsers

2021-02-02 · EACL 2021 2 · Shuo Huang, Zhuang Li, Lizhen Qu, Lei Pan

Semantic parsing maps natural language (NL) utterances into logical forms (LFs), which underpins many advanced NLP problems. Semantic parsers gain performance boosts with deep neural networks, but inherit vulnerabilities…

Data AugmentationSemantic Parsing

FrameASt: A Framework for Second-level Agenda Setting in Parliamentary Debates through the Lense of Comparative Agenda Topics

2022-06-01 · ParlaCLARIN (LREC) 2022 6 · Christopher Klamm, Ines Rehbein, Simone Paolo Ponzetto

This paper presents a framework for studying second-level political agenda setting in parliamentary debates, based on the selection of policy topics used by political actors to discuss a specific issue on the parliamenta…

Topic Classification