Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features

Harrison, Vrindavan; Walker, Marilyn A.

doi:10.18653/v1/w18-6536

Cited by 32 publications

(21 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…7 Creating ground truth paraphrases: We randomly sampled a subset of about 1600 (question, entity) pairs collected from Steps 1 and 2 for obtaining human-generated question variations. We set up our task through the crowdsourcing platform Amazon Mechanical Turk (AMT) following similar dataset collection efforts (Rajpurkar et al, 2016;Harrison and Walker, 2018). Each question, along with the entity descriptions was examined by three crowdworkers.…”

Section: Firs Dataset Creationmentioning

confidence: 99%

On Generating Fact-Infused Question Variations

Deschamps¹,

Gollapalli

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

To fully model human-like ability to ask questions, automatic question generation (QG) models must be able to produce multiple expressions of the same question with different levels of detail. Unfortunately, existing datasets available for learning QG do not include paraphrases or question variations affecting a model's ability to learn this capability. We present FIRS, a dataset containing humangenerated fact-infused rewrites of questions from the widely-used SQuAD dataset to address this limitation. Questions in FIRS were obtained by combining a given question with facts of entities referenced in the question. We study a double encoder-decoder model, Fact-Infused Question Generator (FIQG ), for learning to generate fact-infused questions from a given question. Experimental results show that FIQG effectively incorporates information from facts to add more detail to a given question. To the best of our knowledge, ours is the first study to present fact-infusion as a novel form of question paraphrasing.

show abstract

Section: Firs Dataset Creationmentioning

confidence: 99%

On Generating Fact-Infused Question Variations

Deschamps¹,

Gollapalli

2021

Proceedings of the Conference Recent Advances in Natural Language Processing - Deep Learning for Natural Language Processing Me

View full text Add to dashboard Cite

show abstract

“…Seq2Seq models using long short-term memory (LSTM) with global attention are widely used for QG [8,15,18,20,40,42,43]. In decoding, the hidden states of the decoder are used to generate attention weights for the encoded representation of the input.…”

Section: Related Workmentioning

confidence: 99%

“…Moreover, they proposed selecting question words from a restricted vocabulary. In other models, more input features are added, such as part of speech, named entities, word case, coreference, and dependency [15,20,42,43]. These features are concatenated with the token embedding vector and answer-position signals, and are subsequently fed into an LSTM encoder.…”

Section: Related Workmentioning

confidence: 99%

Multi-turn dialogue-oriented pretrained question generation model

Wang

Rong

Zhang

et al. 2020

Complex Intell. Syst.

View full text Add to dashboard Cite

In recent years, teaching machines to ask meaningful and coherent questions has attracted considerable attention in natural language processing. Question generation has found wide applications in areas such as education (testing knowledge) and chatbots (enhancing interaction). Following previous studies on conversational question generation, we propose a pretrained, encoder–decoder model that can incorporate the semantic information from both passage and hidden conversation representations. We adopt BERT as the encoder to combine external text and dialogue history, and we design a multi-head attention-based decoder to incorporate the semantic information from both text and hidden dialogue representations into the decoding process, thereby generating coherent questions. Experiments with conversational question generation and document-grounded dialogue response generation tasks indicate that the proposed model is superior to baseline models in terms of both standard metrics and human evaluations.

show abstract

“…Starting from early rule-based approaches that relied on syntactic transformations or handcrafted semantic templates (Heilman and Smith, 2010;Lindberg et al, 2013;Mazidi and Nielsen, 2014), automatic question generation from text has gradually transitioned to neural sequence-to-sequence generation methods (Du et al, 2017;Duan et al, 2017;Harrison and Walker, 2018;Zhu et al, 2019). Most state-of-the-art generators also benefit from largescale language model pre-training Scialom et al, 2019;.…”

Section: Related Workmentioning

confidence: 99%

Improved Synthetic Training for Reading Comprehension

Chen¹,

Sultan²,

Castelli³

2020

Preprint

View full text Add to dashboard Cite

Automatically generated synthetic training examples have been shown to improve performance in machine reading comprehension (MRC). Compared to human annotated gold standard data, synthetic training data has unique properties, such as high availability at the possible expense of quality. In view of such differences, in this paper, we explore novel applications of synthetic examples to MRC. Our proposed pre-training and knowledge distillation strategies show significant improvements over existing methods. In a particularly surprising discovery, we observe that synthetic distillation often yields students that can outperform the teacher model.

show abstract

Neural Generation of Diverse Questions using Answer Focus, Contextual and Linguistic Features

Cited by 32 publications

References 27 publications

On Generating Fact-Infused Question Variations

On Generating Fact-Infused Question Variations

Multi-turn dialogue-oriented pretrained question generation model

Improved Synthetic Training for Reading Comprehension

Contact Info

Product

Resources

About