Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus

Serban, Iulian Vlad; García-Durán, Alberto; Gülçehre, Çağlar; Ahn, Sungjin; Chandar, Sarath; Courville, Aaron; Bengio, Yoshua

doi:10.48550/arxiv.1603.06807

Cited by 21 publications

(34 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Dataset Construction Techniques While some KGQA datasets are automatically generated [32], most of them are manually created either by (i) using in-house workers [38] or crowd-sourcing [10], (ii) or extract questions from online question answering platforms such as search engines, online forum, etc [4]. Most (single-turn/multi-turn) conversational QA datasets are generated using semiautomated approaches [31,9].…”

Section: Kgqa Datasetsmentioning

confidence: 99%

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

Kacupaj¹,

Banerjee²,

Singh³

et al. 2021

Preprint

View full text Add to dashboard Cite

This paper presents ParaQA, a question answering (QA) dataset with multiple paraphrased responses for single-turn conversation over knowledge graphs (KG). The dataset was created using a semiautomated framework for generating diverse paraphrasing of the answers using techniques such as back-translation. The existing datasets for conversational question answering over KGs (single-turn/multi-turn) focus on question paraphrasing and provide only up to one answer verbalization. However, ParaQA contains 5000 question-answer pairs with a minimum of two and a maximum of eight unique paraphrased responses for each question. We complement the dataset with baseline models and illustrate the advantage of having multiple paraphrased answers through commonly used metrics such as BLEU and METEOR. The ParaQA dataset is publicly available on a persistent URI for broader usage and adaptation in the research community.

show abstract

Section: Kgqa Datasetsmentioning

confidence: 99%

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

Kacupaj¹,

Banerjee²,

Singh³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Deep neural networks (DNNs) have achieved remarkable performances on a wide range of applications in artificial intelligence including computer vision [1], [2], [3] and natural language processing [4], [5]. The performance gain comes at a high cost of computation and memory in inference.…”

Section: Introductionmentioning

confidence: 99%

Locally Linear Region Knowledge Distillation

Deng,

Zhongfei

2020

Preprint

View full text Add to dashboard Cite

Knowledge distillation (KD) is an effective technique to transfer knowledge from one neural network (teacher) to another (student), thus improving the performance of the student. To make the student better mimic the behavior of the teacher, the existing work focuses on designing different criteria to align their logits or representations. Different from these efforts, we address knowledge distillation from a novel data perspective. We argue that transferring knowledge at sparse training data points cannot enable the student to well capture the local shape of the teacher function. To address this issue, we propose locally linear region knowledge distillation (L 2 RKD) which transfers the knowledge in local, linear regions from a teacher to a student. This is achieved by enforcing the student to mimic the outputs of the teacher function in local, linear regions. To the end, the student is able to better capture the local shape of the teacher function and thus achieves a better performance. Despite its simplicity, extensive experiments demonstrate that L 2 RKD is superior to the original KD in many aspects as it outperforms KD and the other state-of-the-art approaches by a large margin, shows robustness and superiority under few-shot settings, and is more compatible with the existing distillation approaches to further improve their performances significantly.

show abstract

“…a conversation with human users (Mostafazadeh et al, 2016). While many other works focus on QG from images (Mostafazadeh et al, 2016;Fan et al, 2018;Li et al, 2018) or knowledge bases (Serban et al, 2016;Elsahar et al, 2018), in this work, we focus on QG from textual data.…”

Section: Introductionmentioning

confidence: 99%

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

Chen,

Wu,

Zaki

2019

Preprint

View full text Add to dashboard Cite

Natural question generation (QG) is a challenging yet rewarding task, that aims to generate questions given an input passage and a target answer. Previous works on QG, however, either (i) ignore the rich structure information hidden in the word sequence, (ii) fail to fully exploit the target answer, or (iii) solely rely on cross-entropy loss that leads to issues like exposure bias and evaluation discrepancy between training and testing. To address the above limitations, in this paper, we propose a reinforcement learning (RL) based graphto-sequence (Graph2Seq) architecture for the QG task. Our model consists of a Graph2Seq generator where a novel bidirectional graph neural network (GNN) based encoder is applied to embed the input passage incorporating the answer information via a simple yet effective Deep Alignment Network, and an evaluator where a mixed objective function combining both cross-entropy loss and RL loss is designed for ensuring the generation of semantically and syntactically valid text. The proposed model is end-to-end trainable, and achieves new state-of-the-art scores and outperforms all previous methods by a great margin on the SQuAD benchmark.

show abstract

Generating Factoid Questions With Recurrent Neural Networks: The 30M Factoid Question-Answer Corpus

Cited by 21 publications

References 0 publications

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

ParaQA: A Question Answering Dataset with Paraphrase Responses for Single-Turn Conversation

Locally Linear Region Knowledge Distillation

Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation

Contact Info

Product

Resources

About