Generative Question Answering: Learning to Answer the Whole Question

By Michael Lewis, Angela Fan. 2018

75 citations recorded by the source corpus.

How researchers see this paper

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

In Natural Language Processing

Citations in the corpus

Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answering (2019, methodology): “ing rather than true comprehension (Jia and Liang, 2017), the task of QG, which usually needs complicated semantic reasoning and syntactic variation, should be another way to encourage true machine comprehension (Lewis and Fan, 2019).”
Real-Time Open-Domain Question Answering with Dense-Sparse Phrase Index (2019, background): “It is worth noting that generative question answering (Lewis and Fan, 2019) has the opposite property; while it has a surface-form decoder by definition, it cannot easily enumerate a compact list of all possible”
Internet-augmented language models through few-shot prompting for open-domain question answering (2022, methodology): “…inference, where we choose an answer that maximizes p ( a | q ) = =1 p tfidf ( p i | q ) · p ( a i | q, p i ) , referred to as RAG throughout this work as it is inspired from the model of Lewis et al. [7] (ii) Noisy channel inference, where we choose an answer that maximizes p ( a i , q , [25, 26].”
Queens Are Powerful Too: Mitigating Gender Bias in Dialogue Generation (2019, background): “, 2018), and that these biases can be easy to learn compared to more challenging reasoning (Bolukbasi et al., 2016; Lewis and Fan, 2018).”
Models in the Loop: Aiding Crowdworkers with Generative Annotation Assistants (2021, background): “A long line of prior work has trained generative models for question answering (Du et al., 2017; Du and Cardie, 2018; Zhao et al., 2018; Lewis and Fan, 2019; Alberti et al., 2019; Puri et al., 2020; Yang et al., 2020; Bartolo et al., 2021; Lewis et al., 2021).”
Unified Vision-Language Pre-Training for Image Captioning and VQA (2019, background): “…model architectures to fuse question and image representations (Kim, Jun, and Zhang 2018; Anderson et al. 2018; Gao et al. 2019), new datasets or models to reduce the dataset bias (Zhang et al. 2016; Goyal et al. 2017; Agrawal et al. 2017) and ground the answer in the question (Lewis and Fan 2019).”
PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them (2021, background): “…various purposes, such as data augmentation (Alberti et al., 2019; Lewis et al., 2019b; Lee et al., 2021), improved retrieval (Nogueira et al., 2019), generative modelling for contextual QA (Lewis and Fan, 2018), as well as being studied in its own right (Du et al., 2017; Hosking and Riedel, 2019).”
Generating Fact Checking Briefs (2020, positive): “…the model must provide an explanation to justify no answer, we use an abstractive approach with a generative model; abstractive models have shown strong performance on various question answering tasks (Lewis and Fan, 2018; Dong et al., 2019; Radford et al.; Raffel et al., 2019; Lewis et al., 2020).”
Unsupervised Question Answering by Cloze Translation (2019, methodology): “Assuming uniform answer probabilities conditioned on context p ( a | c ) , this amounts to calculating arg max a p ( q | a (cid:48) , c ) by testing how likely each possible candidate answer could have generated the question, a similar method to the supervised approach of Lewis and Fan (2019).”
Don’t Take the Easy Way Out: Ensemble Based Methods for Avoiding Known Dataset Biases (2019, background): “Solutions include generative objectives to force models to understand all the input (Lewis and Fan, 2019), carefully designed model architecture (Agrawal et al., 2018; Zhang et al., 2016), or adversarial removal of class-indicative features from model’s internal representations (Ramakrish-nan et…”
Improving Question Answering Model Robustness with Synthetic Adversarial Data Generation (2021, methodology): “Many approaches have been proposed to generate question-answer pairs given a passage (Du et al., 2017; Du and Cardie, 2018; Zhao et al., 2018; Lewis and Fan, 2019; Alberti et al., 2019; Puri et al., 2020; Lewis et al., 2021b).”
A Wrong Answer or a Wrong Question? An Intricate Relationship between Question Reformulation and Answer Selection in Conversational Question Answering (2020, background): “Lewis and Fan (2019) also showed this deﬁciency of the state-of-the-art models for reading comprehension that learn to attend to just a few words in the question.”
Can NLI Models Verify QA Systems' Predictions? (2021, background): “…proposed in recent years: Wang and Bansal (2018); Khashabi et al. (2020); Liu et al. (2020) use perturbation based methods and adversarial training; Lewis and Fan (2018) propose generative QA to prevent the model from overﬁtting to simple patterns; Yeh and Chen (2019 Another line of work to make…”
Synthetic Data for Deep Learning (2019, background): “Latest works use architectures based on selfattention that have proven their worth across a wide variety of NLP tasks [351].”
The Curse of Performance Instability in Analysis Datasets: Consequences, Source, and Suggestions (2020, background): “, 2019), and for RC through different training objectives (Yeh and Chen, 2019; Lewis and Fan, 2019).”
Question Answering Infused Pre-training of General-Purpose Contextualized Representations (2021, methodology): “The model receives the passage as context and must generate the answer text, then a special separator token, then the question; this approach is simpler than prior approaches that use separate models for answer and question generation (Lewis and Fan, 2019; Alberti et al., 2019; Puri et al., 2020), a”