Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
By Haitian Sun, Bhuwan Dhingra, Manzil Zaheer, Kathryn Mazaitis, Ruslan Salakhutdinov, William W. Cohen. 2018
516 citations recorded by the source corpus.
Open Domain Question Answering (QA) is evolving from complex pipelined systems to end-to-end deep neural networks. Specialized neural models have been developed for extracting answers from either text alone or Knowledge Bases (KBs) alone. In this paper we look at a more practical setting, namely QA over the combination of a KB and entity-linked text, which is appropriate when an incomplete KB is available with a large text corpus. Building on recent advances in graph representation learning we propose a novel model, GRAFT-Net, for extracting answers from a question-specific subgraph containing text and KB entities and relations. We construct a suite of benchmark tasks for this problem, varying the difficulty of questions, the amount of training data, and KB completeness. We show that GRAFT-Net is competitive with the state-of-the-art when tested using either KBs or text alone, and vastly outperforms existing methods in the combined setting.
Subfields: Artificial Intelligence, Information Retrieval & Search, Question Answering & Reading Comprehension
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
- Mohit Bansal
- Percy Liang
- Luke S. Zettlemoyer
- Jianfeng Gao
- Hannaneh Hajishirzi
- Graham Neubig
- Yejin Choi
- Caiming Xiong
In Information Retrieval & Search
- Hannaneh Hajishirzi
- Wen-tau Yih
- Danqi Chen
- Jinhyuk Lee
- Sewon Min
- William W. Cohen
- Jamie Callan
- Sebastian Riedel
In Question Answering & Reading Comprehension
- William W. Cohen
- Haitian Sun
- Percy Liang
- Antoine Bordes
- Partha P. Talukdar
- Apoorv Saxena
- Hannaneh Hajishirzi
- Mo Yu
Citations in the corpus
- Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering (2019, background): “l. ,2013;Kwiatkowski et al. 2013;Yih et al.,2015), typically without using any external text collections. However, recent work has augmented knowledge bases with text from Wikipedia (Das et al. ,2017;Sun et al. 2018 2019), to increase factual coverage. In this paper, we study what can be loosely see”
- Knowledge Enhanced Contextual Word Representations (2019, background): “Task-specific KB architectures Other work has focused on integrating KBs into neural architectures for specific downstream tasks (Yang and Mitchell, 2017; Sun et al., 2018; Chen et al., 2018; Bauer et al., 2018; Mihaylov and Frank, 2018; Wang and Jiang, 2019; Yang et al., 2019).”
- Differentiable Reasoning over a Virtual Knowledge Base (2020, methodology): “Even with only 50% edges retained, we see good performance—better than PullNet and the state-of-the-art for a KB-only method (in italics ).”
- Facts as Experts: Adaptable and Interpretable Neural Memory over Symbolic Knowledge (2020, background): “…has also been extended with works looking at ways of incorporating raw text and symbolic KGs into a shared embedding space (Riedel et al., 2013; Verga et al., 2016), to be jointly reasoned over (Sun et al., 2018, 2019a), or to treat text as a replacement for a knowledge base (Dhingra et al., 2019).”
- HybridQA: A Dataset of Multi-Hop Question Answering over Tabular and Textual Data (2020, methodology): “There has been some pioneering work on building hybrid QA systems (Sun et al., 2019, 2018; Xiong et al., 2019).”
- E-BERT: Efficient-Yet-Effective Entity Embeddings for BERT (2019, methodology): “QA has typically been tackled as a supervised problem (e.g., Das et al. (2017); Sun et al. (2018)).”
- On-The-Fly Information Retrieval Augmentation for Language Models (2020, background): “…demonstrated for NLP tasks such as natural language inference (Chen et al., 2018; Yang et al., 2019), language generation (Parthasarathi and Pineau, 2018), knowledge base completion (Toutanova et al., 2015; Das et al., 2017) and question answering (Sun et al., 2019, 2018; Dhingra et al., 2017).”
- QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering (2021, methodology): “Previous works (Bao et al., 2016; Sun et al., 2018; Lin et al., 2019) retrieve a subgraph from the KG by taking topic entities (KG entities mentioned in the given QA context) and their few-hop neighbors.”
- Retrieving and Reading: A Comprehensive Survey on Open-domain Question Answering (2021, background): “For example, [119] construct a question-specific sub-graph containing sentences from the corpus, and entities and relations from the KB.”
- Think about it! Improving defeasible reasoning by first modeling the question scenario. (2021, methodology): “Encoding Graph Representations Several existing methods use graphs as an additional input for commonsense reasoning (Sun et al., 2018; Lin et al., 2019; Lv et al., 2020; Feng et al., 2020; Bosselut et al., 2021; Ma et al., 2021; Kapani-pathi et al., 2020).”
- Augmenting Neural Machine Translation with Knowledge Graphs (2019, background): “, 2018), Question Answering (QA) (Sorokin and Gurevych, 2018; Sun et al., 2018) and Machine Reading (MR) (Yang and Mitchell, 2017) successfully.”
- UniK-QA: Unified Representations of Structured and Unstructured Knowledge for Open-Domain Question Answering (2020, methodology): “The latest in this line are the works of (Sun et al., 2018, 2019), which augments the knowledge graph with text nodes and applies graph methods to identify candidate answers.”
- Neural, symbolic and neural-symbolic reasoning on knowledge graphs (2021, methodology): “Although some models such as Graft-Net (Sun et al., 2018) and PullNet (Sun et al., 2019a) are the state-of-the-art reasoning models on both the structural and the textual information, it is still challenging to determine the correct evidence to be linked to the incomplete graph structure from the la”
- Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations (2019, background): “…Pineau, 2018; Liu et al., 2018; Moghe et al., 2018; Dinan et al., 2019; Zhong et al., 2019), task-oriented dialogue systems (Madotto et al., 2018; Wu et al., 2019; He et al., 2019) and question answering systems (Kiddon et al., 2016; Hao et al., 2017; Sun et al., 2018; Mihaylov and Frank, 2018).”
- PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text (2019, methodology): “For GRAFT-Net (Sun et al., 2018), we use the implementation published by the author 5 ; however, we run it on somewhat different data as described in Section 4.4.”
- RNG-KBQA: Generation Augmented Iterative Ranking for Knowledge Base Question Answering (2021, methodology): “using heuristic rules (Sun et al., 2018), or iteratively built using learned models (Sun et al.”
- Improving Question Answering over Incomplete KBs with Knowledge-Aware Reader (2019, methodology): “To build a scalable system, we follow Sun et al. (2018) and only consider a subgraph for each question.”