paper-with-me

Papers

Question Generation Based on Grammar Knowledge and Fine-grained Classification

2022-10-01 · COLING 2022 10 · Yuan Sun, Sisi Liu, Zhengcuo Dan, Xiaobing Zhao

Question generation is the task of automatically generating questions based on given context and answers, and there are problems that the types of questions and answers do not match. In minority languages such as Tibetan, since the grammar rules are complex and the training data is small, the related research on question generation is still in its infancy. To solve the above problems, this paper constructs a question type classifier and a question generator. We perform fine-grained division of question types and integrate grammatical knowledge into question type classifiers to improve the accuracy of question types. Then, the types predicted by the question type classifier are fed into the question generator. Our model improves the accuracy of interrogative words in generated questions, and the BLEU-4 on SQuAD reaches 17.52, the BLEU-4 on HotpotQA reaches 19.31, the BLEU-4 on TibetanQA reaches 25.58.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Question GenerationQuestion-Generation

Similar Papers 제목 키워드 기반

SPARQA: Skeleton-based Semantic Parsing for Complex Questions over Knowledge Bases

2020-03-31 · Yawei Sun, Lingling Zhang, Gong Cheng, Yuzhong Qu

Semantic parsing transforms a natural language question into a formal query over a knowledge base. Many existing methods rely on syntactic parsing like dependencies. However, the accuracy of producing such expressive for…

Semantic ParsingSentence

Personalized Questions, Answers and Grammars: Aiding the Search for Relevant Web Information

2017-09-01 · WS 2017 9 · Marta Gatius

This work proposes an organization of knowledge to facilitate the generation of personalized questions, answers and grammars from web documents. To reduce the human effort needed in the generation of the linguistic resou…

Text Generation

XGrammar-2: Efficient Dynamic Structured Generation Engine for Agentic LLMs

2026-01-07 · Linzhang Li, Yixin Dong, Guanjie Wang, Ziyi Xu 외 arxiv

Modern LLM agents increasingly rely on dynamic structured generation, such as tool calling and response protocols. Unlike traditional structured generation with static structures, these workloads vary both across request…

Paraphrase Generation from Latent-Variable PCFGs for Semantic Parsing

2016-01-22 · WS 2016 9 · Shashi Narayan, Siva Reddy, Shay B. Cohen

One of the limitations of semantic parsing approaches to open-domain question answering is the lexicosyntactic gap between natural language questions and knowledge base entries -- there are many ways to ask a question, a…

Open-Domain Question AnsweringParaphrase GenerationQuestion AnsweringSemantic Parsing+1

PersLitEval: Fine-grained Benchmark and Evaluation of LLMs on Persian Literature Questions

2026-05-26 · Ruhallah Niazi, Faeze Ghorbanpour, Alexander Fraser arxiv

Despite impressive multilingual capabilities, large language models (LLMs) remain poorly evaluated on literary knowledge in non-English languages. We introduce PersLitEval, a benchmark of 4,514 Persian literature multipl…