Neural Generative Question Answering

By Jun Yin, Xin Jiang, Zhengdong Lu, Lifeng Shang, Hang Li, Xiaoming Li. 2015

218 citations recorded by the source corpus.

This paper presents an end-to-end neural network model, named Neural Generative Question Answering (GENQA), that can generate answers to simple factoid questions, based on the facts in a knowledge-base. More specifically, the model is built on the encoder-decoder framework for sequence-to-sequence learning, while equipped with the ability to enquire the knowledge-base, and is trained on a corpus of question-answer pairs, with their associated triples in the knowledge-base. Empirical study shows the proposed model can effectively deal with the variations of questions and answers, and generate right and natural answers by referring to the facts in the knowledge-base. The experiment on question answering demonstrates that the proposed model can outperform an embedding-based QA model as well as a neural dialogue model trained on the same data.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Prompting & Reasoning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Prompting & Reasoning

Citations in the corpus

Survey of Hallucination in Natural Language Generation (2022, background): “[220] propose Neural Generative Question Answering (GENQA), an end-to-end model that generates answers to simple factoid questions based on the knowledge base, while Bi et al.”
Troubling Trends in Machine Learning Scholarship (2018, background): “Bending the term further, some discriminative models are now referred to as generative models on account of producing structured outputs [76], a mistake that we (ZL) make in [47].”
BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis (2019, background): “…of products and services, it is very hard, if not impossible, to pre-compile an up-to-date and reliable knowledge base to cover a wide assortment of questions that customers may ask, such as in factoid-based KB-QA (Xu et al., 2016; Fader et al., 2014; Kwok et al., 2001; Yin et al., 2015).”
A Neural Knowledge Language Model (2016, background): “Our knowledge memory is also related to the recent literature on neural networks with external memory [2, 43, 36, 13] which is applied to question answering [43, 8, 44] and reading comprehension [18, 19].”
Few-Shot NLG with Pre-Trained Language Model (2019, background): “Some examples are task-oriented dialog, question answering (He et al. 2017; Su et al. 2016; Saha et al. 2018; Yin et al. 2016) and interdisciplinary applications such as medicine (Hasan and Farri 2019; Cawsey, Webber, and Jones 1997) and health-care (Hasan and Farri 2019; DiMarco et al. 2007),…”
A Survey on Dialogue Systems: Recent Advances and New Frontiers (2017, methodology): “ultimodal space and made progress in perplexity. A similar task is to generate an answer for a question according to outside knowledge. Unlike the general method of tuple retrieval in knowledge base, [116] used words from knowledge base together with common words in generation process. Empirical stu”
Towards Understanding Gender Bias in Relation Extraction (2019, neutral): “answering systems (Bordes et al., 2014; Yin et al., 2016; Cui et al., 2019).”
The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches (2018, methodology): “GAN is used for response generation and question answering system [232,233].”
End-to-End Reinforcement Learning of Dialogue Agents for Information Access (2016, methodology): “Our work is motivated by the neural GenQA (Yin et al., 2016a) and neural enquirer (Yin et al., 2016b) models for querying KB and tables via natural language in a fully “neuralized” way.”
A Survey of Knowledge-enhanced Text Generation (2020, methodology): “Scoring function also could be bi-linear model [170], rule-based method [10] and etc.”
Topic-to-Essay Generation with Neural Networks (2018, background): “Response generation [Yin et al. , 2015; Xing et al. , 2016] is a sequence-to-sequence task, the input and the output of which are both sentences and two sentences are always centering around one topic.”
Factuality Enhanced Language Models for Open-Ended Text Generation (2022, background): “…GPT-3 In previous studies, different metrics and methods have been proposed to measure and improve the factual accuracy of language generation within different tasks [11], including text summarization [e.g., 12–15], question answering [e.g., 16–18], and table-to-text generation [e.g., 19, 20].”
CGMH: Constrained Sentence Generation by Metropolis-Hastings Sampling (2018, methodology): “Most previous work makes use of attention or copying mechanisms to impose the keyword constraints in a soft manner, which means that the constraint may not be satisﬁed (Yin et al. 2016; Gu et al. 2016).”
Table-to-Text: Describing Table Region With Natural Language (2018, methodology): “Inspired by the recent success of copying mechanism in seq2seq learning (Gulcehre et al. 2016; Gu et al. 2016; Yin et al. 2015; Luong et al. 2015; Nallapati et al. 2016), we develop a ﬂexible copying mechanism that is capable of copying contents from table cells.”
Answer-based Adversarial Training for Generating Clarification Questions (2019, methodology): “…(Bahdanau et al., 2015; Luong et al., 2015), summarization (Nallapati et al., 2016), dialog (Bor-des et al., 2016; Li et al., 2016a; Serban et al., 2017), textual style transfer (Jhamtani et al., 2017; Rao and Tetreault, 2018) and question answering (Yin et al., 2016; Serban et al., 2016).”
Mechanism-Aware Neural Machine for Dialogue Response Generation (2017, methodology): “Different from the conventional neural encoder-decoder (Cho et al. 2014; Sutskever, Vinyals, and Le 2014) for response generation (Shang, Lu, and Li 2015; Yin et al. 2016), a framework of encoder-diverter-decoder is developed, where the module of diverter is used to generate mechanism-aware context.”
If Beam Search Is the Answer, What Was the Question? (2020, background): “As such, it became the nat-ural choice for decoding neural probabilistic text generators—whose design makes evaluating the full search space impossible (Kalchbrenner and Blunsom, 2013; Sutskever et al., 2014; Vinyals and Le, 2015; Yin et al., 2016).”
Recent advances in deep learning based dialogue systems: a systematic survey (2021, background): “Knowledge grounded systems use Memory Networks to store external knowledge and the generator retrieves relevant knowledge facts from it at the generation stage (Ghazvininejad et al., 2018; Vougiouklis et al., 2016; Yin et al., 2015).”
Coupling Distributed and Symbolic Execution for Natural Language Queries (2016, methodology): “In this section, we first introduce the fully distributed (neuralized) enquirer [Yin et al., 2016b].”
Collaborative Multi-Agent Dialogue Model Training Via Reinforcement Learning (2019, methodology): “…most widely and successfully adopted for language generation in several tasks as machine translation (e.g. Sutskever et al., 2014), question answering (e.g. Yin et al., 2016), text summarization (e.g. Chopra et al., 2016), and conversational models (e.g. Shang et al., 2015; Serban et al., 2016).”