Challenge: Existing evaluation methods often fail to produce objective results and favor high similarity to the ground-truth question-answer pairs.
Approach: They propose an alternative approach to evaluate question-answer generation using Generative Interpretation (GI) GI outperforms existing evaluation methods in terms of human alignment .
Outcome: The proposed approach outperforms existing evaluation methods in human alignment and shows comparable performance with GPT3.5, only with BART-large.

Similar Papers

Asking Questions Like Educational Experts: Automatically Generating Question-Answer Pairs on Real-World Examination Data (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to generate high quality question-answer pairs are limited . a new framework is proposed for the question-answer generation task on real-world examination data.
Approach: They propose a multi-agent communication model to generate and optimize the question and keyphrases iteratively and then apply the generated question and keys to guide the generation of answers.
Outcome: The proposed framework makes great breakthroughs in the question-answer pair generation task.
Elaboration-Generating Commonsense Question Answering at Scale (2023.acl-long)

Copied to clipboard

Challenge: elaborations are generated using language models that generate background knowledge that helps improve performance . human evaluations show that the quality of the generated ellaborations is high .
Approach: They propose to finetune smaller language models to generate useful intermediate context . they compare a language model with an answer predictor and generate elaborations . human evaluations show that the quality of the generated ellaborations is high .
Outcome: The proposed framework outperforms other models on commonsense questions on four commons sense benchmarks.
Generating Responses that Reflect Meta Information in User-Generated Question Answer Pairs (2020.lrec-1)

Copied to clipboard

Challenge: Existing approaches to realize consistent personalities require expensive data collection.
Approach: They propose to collect question-answer pairs for particular characters from online users . meta information such as emotion and intimacy was also collected .
Outcome: The proposed method can be used to train neural conversational models with high quality questions and meta information.
Tomayto, Tomahto. Beyond Token-level Answer Equivalence for Question Answering Evaluation (2022.emnlp-main)

Copied to clipboard

Challenge: despite the importance of question answering, evaluations of QA systems are typically limited by manual annotations . despite this, little progress has been made in QA evaluations based on a single answer .
Approach: They propose to extend over exact match (EM) with predefined rules or token-level F1 measure . they propose to use a BERT matching measure to approximate QA predictions .
Outcome: The proposed model improves AE approximations and more accurately reflects the performance of systems.
Evaluation of Question Answer Generation for Portuguese: Insights and Datasets (2024.findings-emnlp)

Copied to clipboard

Challenge: Automatic question generation is an increasingly important task that can be applied in educational settings, data augmentation for question-answering (QA), and conversational systems.
Approach: They adapt and apply QAG approaches to generate question-answer pairs given context and look into strategies for error filtering and their effects.
Outcome: The proposed methods can generate question-answer pairs in Portuguese, a widely spoken language that is underrepresented in natural language processing research.
It is AI’s Turn to Ask Humans a Question: Question-Answer Pair Generation for Children’s Story Books (2022.acl-long)

Copied to clipboard

Challenge: Existing question answering (QA) techniques are created mainly to answer questions asked by humans, but in educational applications, teachers often need to decide what questions to ask .
Approach: They propose to use a fairytale-themed storybook as input to generate QA pairs that can test a student's comprehension skills.
Outcome: The proposed system outperforms state-of-the-art QAG baseline systems and builds an interactive story-telling application for the future real-world deployment.
All That’s ‘Human’ Is Not Gold: Evaluating Human Evaluation of Generated Text (2021.acl-long)

Copied to clipboard

Challenge: evaluators distinguish between human- and machine-authored text in three domains without training . evals' accuracy improved up to 55%, but it did not significantly improve across the three domain.
Approach: They examine the role untrained human evaluations play in NLG evaluation and propose ways to improve their evaluations.
Outcome: The evaluators distinguished between human- and machine-authored text at random chance level without training, but their accuracy did not improve across the three domains.
Covering Uncommon Ground: Gap-Focused Question Generation for Answer Assessment (2023.acl-short)

Copied to clipboard

Challenge: Human communication often involves information gaps between the interlocutors.
Approach: They propose a model that generates such gap-focused questions automatically . they propose an evaluation by human annotators of the generated questions .
Outcome: The proposed model outperforms human generated questions in a competitive environment.
Are Red Roses Red? Evaluating Consistency of Question-Answering Models (P19-1)

Copied to clipboard

Challenge: Existing question-answering systems are limited in their ability to test reasoning and comprehension.
Approach: They propose a method to automatically extract implications from QA datasets to evaluate models' consistency . they use a heuristic to generate such questions and retrain models with implication-augmented data .
Outcome: The proposed method shows that generated implications are well formed and valid . retraining with implication-augmented data improves consistency on both synthetic and human-generated implications.
A Feasibility Study of Answer-Agnostic Question Generation for Education (2022.findings-acl)

Copied to clipboard

Challenge: a feasibility study into the applicability of answer-agnostic question generation models to textbook passages is conducted . a significant portion of errors arise from asking irrelevant or un-interpretable questions, a study finds .
Approach: They conduct a feasibility study into the applicability of answer-agnostic question generation models to textbook passages.
Outcome: The proposed model reduces the time it takes to write questions that target salient concepts . the proposed model would help professors write quizzes faster and help students stay engaged .

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