paper-with-me

Papers

What Can a Generative Language Model Answer About a Passage?

2021-11-01 · EMNLP (MRQA) 2021 11 · Douglas Summers-Stay, Claire Bonial, Clare Voss

Generative language models trained on large, diverse corpora can answer questions about a passage by generating the most likely continuation of the passage followed by a question/answer pair. However, accuracy rates vary depending on the type of question asked. In this paper we keep the passage fixed, and test with a wide variety of question types, exploring the strengths and weaknesses of the GPT-3 language model. We provide the passage and test questions as a challenge set for other language models.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage Modelling

Similar Papers 제목 키워드 기반

GripRank: Bridging the Gap between Retrieval and Generation via the Generative Knowledge Improved Passage Ranking

2023-05-29 · Jiaqi Bai, Hongcheng Guo, Jiaheng Liu, Jian Yang 외

Retrieval-enhanced text generation has shown remarkable progress on knowledge-intensive language tasks, such as open-domain question answering and knowledge-enhanced dialogue generation, by leveraging passages retrieved …

Answer GenerationDialogue GenerationKnowledge DistillationLanguage Modelling+6

Reinforced Dynamic Reasoning for Conversational Question Generation

2019-07-29 · ACL 2019 7 · Boyuan Pan, Hao Li, Ziyu Yao, Deng Cai 외

This paper investigates a new task named Conversational Question Generation (CQG) which is to generate a question based on a passage and a conversation history (i.e., previous turns of question-answer pairs). CQG is a cr…

DecoderQuestion AnsweringQuestion GenerationQuestion-Generation+1

Weak Supervision Enhanced Generative Network for Question Generation

2019-07-01 · Yutong Wang, Jiyuan Zheng, Qijiong Liu, Zhou Zhao 외

Automatic question generation according to an answer within the given passage is useful for many applications, such as question answering system, dialogue system, etc. Current neural-based methods mostly take two steps w…

DecoderQuestion AnsweringQuestion GenerationQuestion-Generation

How Much Reading Does Reading Comprehension Require? A Critical Investigation of Popular Benchmarks

2018-08-14 · EMNLP 2018 10 · Divyansh Kaushik, Zachary C. Lipton

Many recent papers address reading comprehension, where examples consist of (question, passage, answer) tuples. Presumably, a model must combine information from both questions and passages to predict corresponding answe…

Reading ComprehensionSentence

Tag and Correct: Question aware Open Information Extraction with Two-stage Decoding

2020-09-16 · Martin Kuo, Yaobo Liang, Lei Ji, Nan Duan 외

Question Aware Open Information Extraction (Question aware Open IE) takes question and passage as inputs, outputting an answer tuple which contains a subject, a predicate, and one or more arguments. Each field of answer …

DecoderOpen Information ExtractionTAG