Incorporating External Knowledge into Machine Reading for Generative Question Answering

By Bin Bi, Chen Wu, Ming Yan, Wei Wang, Jiangnan Xia, Chenliang Li. 2019

46 citations recorded by the source corpus.

Commonsense and background knowledge is required for a QA model to answer many nontrivial questions. Different from existing work on knowledge-aware QA, we focus on a more challenging task of leveraging external knowledge to generate answers in natural language for a given question with context. In this paper, we propose a new neural model, Knowledge-Enriched Answer Generator (KEAG), which is able to compose a natural answer by exploiting and aggregating evidence from all four information sources available: question, passage, vocabulary and knowledge. During the process of answer generation, KEAG adaptively determines when to utilize symbolic knowledge and which fact from the knowledge is useful. This allows the model to exploit external knowledge that is not explicitly stated in the given text, but that is relevant for generating an answer. The empirical study on public benchmark of answer generation demonstrates that KEAG improves answer quality over models without knowledge and existing knowledge-aware models, confirming its effectiveness in leveraging knowledge.

Subfields: Artificial Intelligence, Retrieval-Augmented Generation, Information Retrieval & Search, Natural Language Processing

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

1. Soujanya Poria
2. Navonil Majumder
3. Rada Mihalcea
4. Devamanyu Hazarika
5. Erik Cambria
6. Deepanway Ghosal
7. Pascale Fung
8. Chenliang Li

In Retrieval-Augmented Generation

1. Meng Jiang
2. Soujanya Poria
3. W. Yu
4. Devamanyu Hazarika
5. Chenguang Zhu

In Information Retrieval & Search

1. Heng Ji
2. Meng Jiang
3. Rada Mihalcea
4. Soujanya Poria
5. Ming Yan
6. Songfang Huang
7. Zhiting Hu
8. Wei Wang

In Natural Language Processing

1. Soujanya Poria
2. Rada Mihalcea
3. Devamanyu Hazarika
4. Andrea Madotto
5. Pascale Fung
6. Navonil Majumder
7. Nayeon Lee
8. Chenguang Zhu

Citations in the corpus

• PALM: Pre-training an Autoencoding&autoregressive Language Model for Context-conditioned Generation (2020, background): “…neural machine translation (Bahdanau et al., 2015; Vaswani et al., 2017), abstractive summarization (Rush et al., 2015; See et al., 2017a; Gehrmann et al., 2018), generative question answering (QA) (Tan et al., 2017; Bi et al., 2019) and conversational response generation (Vinyals and Le, 2015).”
• Survey of Hallucination in Natural Language Generation (2022, methodology): “[11] propose the Knowledge-Enriched Answer Generator (KEAG) to generate a natural answer by integrating facts from four different information sources, namely, questions, passages, vocabulary, and knowledge.”
• KinGDOM: Knowledge-Guided DOMain Adaptation for Sentiment Analysis (2020, background): “Augmenting neural models with external knowledge bases (KB) has shown benefits across a range of NLP applications (Peters et al., 2019; Li et al., 2019; IV et al., 2019; liu et al., 2019; Bi et al., 2019).”
• Addressing Semantic Drift in Generative Question Answering with Auxiliary Extraction (2021, background): “Part of the results in the Table 2 are from (Bi et al., 2019), which re-running other researchers’ code.”
• A Survey of Knowledge-enhanced Text Generation (2020, methodology): “, utterance) [151, 179] [85, 144, 154] [138, 173] [96, 114, 121] Question Sentence - - - [10, 44] [7, 26, 40] - - [11, 23, 48] answering (i.”