A Feasibility Study of Answer-Agnostic Question Generation for Education

Dugan, Liam; Miltsakaki, Eleni; Upadhyay, Shriyash; Ginsberg, Etan; Gonzalez, Hannah; Choi, Dayheon; Yuan, Chuning; Callison-Burch, Chris

doi:10.48550/arxiv.2203.08685

Cited by 1 publication

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We based our choice of the model on the findings by Dong et al (2019) and , who showed that language models that are fine-tuned jointly on Question Answering and Question Generation, outperform individual models fine-tuned independently on those tasks. More specifically, we use the model by Dugan et al (2022) and make slight modifications. Dugan et al (2022) used a T5 model fine-tuned on SQuAD and further fine-tuned it on three tasks simultaneously: Question Generation (GQ), Question Answering (QA), and Answer Extraction (AE).…”

Section: Question-answer Generationmentioning

confidence: 99%

“…More specifically, we use the model by Dugan et al (2022) and make slight modifications. Dugan et al (2022) used a T5 model fine-tuned on SQuAD and further fine-tuned it on three tasks simultaneously: Question Generation (GQ), Question Answering (QA), and Answer Extraction (AE). They also included a summarization module to create lexically diverse question-answer pairs.…”

Section: Question-answer Generationmentioning

confidence: 99%

“…We found that using this module sometimes leads to factually incorrect passages, and leave this to future work. Similar to Dugan et al (2022), we split the original passages into whole sentences that are shorter than 512 tokens. 3 We then generate the pairs using the first three sub-passages.…”

Section: Question-answer Generationmentioning

confidence: 99%

“…For Question Answering (QA), data augmentation has been used to generate paraphrases via backtranslation (Longpre et al, 2019), to replace parts of the input text with translations (Singh et al, 2019), and to generate novel questions or answers (Riabi et al, 2021;Shakeri et al, 2021;Dugan et al, 2022). In the cross-lingual setting, available data have been translated into different languages (Singh et al, 2019;Kumar et al, 2019;Riabi et al, 2021;Shakeri et al, 2021) and language models have been used to train question and answer generation models (Kumar et al, 2019;Chi et al, 2020;Riabi et al, 2021;Shakeri et al, 2021).…”

Section: Related Work Passage Retrieval and Answer Generationmentioning

confidence: 99%

“…In the cross-lingual setting, available data have been translated into different languages (Singh et al, 2019;Kumar et al, 2019;Riabi et al, 2021;Shakeri et al, 2021) and language models have been used to train question and answer generation models (Kumar et al, 2019;Chi et al, 2020;Riabi et al, 2021;Shakeri et al, 2021). Our approach is different from previous work in Cross-lingual Question Answering task in that it only requires English passages to augment the training data, as answers are generated automatically from the trained model by Dugan et al (2022). In addition, our filtering heuristics remove incorrectly generated question-answer pairs, which allows us to keep only question-answer pairs with answers that are more likely to be translated correctly, thus limiting the problem of error propagation.…”

Section: Related Work Passage Retrieval and Answer Generationmentioning

confidence: 99%

See 4 more Smart Citations

ZusammenQA: Data Augmentation with Specialized Models for Cross-lingual Open-retrieval Question Answering System

Hung¹,

Green²,

Litschko³

et al. 2022

Proceedings of the Workshop on Multilingual Information Access (MIA)

View full text Add to dashboard Cite

This paper introduces our proposed system for the MIA Shared Task on Cross-lingual Openretrieval Question Answering (COQA). In this challenging scenario, given an input question the system has to gather evidence documents from a multilingual pool and generate from them an answer in the language of the question. We devised several approaches combining different model variants for three main components: Data Augmentation, Passage Retrieval, and Answer Generation. For passage retrieval, we evaluated the monolingual BM25 ranker against the ensemble of re-rankers based on multilingual pretrained language models (PLMs) and also variants of the shared task baseline, re-training it from scratch using a recently introduced contrastive loss that maintains a strong gradient signal throughout training by means of mixed negative samples. For answer generation, we focused on languageand domain-specialization by means of continued language model (LM) pretraining of existing multilingual encoders. Additionally, for both passage retrieval and answer generation, we augmented the training data provided by the task organizers with automatically generated question-answer pairs created from Wikipedia passages to mitigate the issue of data scarcity, particularly for the low-resource languages for which no training data were provided. Our results show that language-and domain-specialization as well as data augmentation help, especially for low-resource languages.

show abstract

Section: Question-answer Generationmentioning

confidence: 99%

Section: Question-answer Generationmentioning

confidence: 99%

Section: Question-answer Generationmentioning

confidence: 99%