More Like this

1. QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering

   Yasunaga, Michihiro; Ren, Hongyu; Bosselut, Antoine; Liang, Percy; Leskovec, Jure (January 2021, North American Chapter of the Association for Computational Linguistics (NAACL))

   null (Ed.)

   The problem of answering questions using knowledge from pre-trained language models (LMs) and knowledge graphs (KGs) presents two challenges: given a QA context (question and answer choice), methods need to (i) identify relevant knowledge from large KGs, and (ii) perform joint reasoning over the QA context and KG. Here we propose a new model, QA-GNN, which addresses the above challenges through two key innovations: (i) relevance scoring, where we use LMs to estimate the importance of KG nodes relative to the given QA context, and (ii) joint reasoning, where we connect the QA context and KG to form a joint graph, and mutually update their representations through graph-based message passing. We evaluate QA-GNN on the CommonsenseQA and OpenBookQA datasets, and show its improvement over existing LM and LM+KG models, as well as its capability to perform interpretable and structured reasoning, e.g., correctly handling negation in questions. 

   more » « less
2. Deep Bidirectional Language-Knowledge Graph Pretraining

   Yasunaga, Michihiro; Bosselut, Antoine; Ren, Hongyu; Zhang, Xikun; Manning, Christopher D.; Liang, Percy; Leskovec, Jure (January 2022, Advances in neural information processing systems)

   Pretraining a language model (LM) on text has been shown to help various downstream NLP tasks. Recent works show that a knowledge graph (KG) can complement text data, offering structured background knowledge that provides a useful scaffold for reasoning. However, these works are not pretrained to learn a deep fusion of the two modalities at scale, limiting the potential to acquire fully joint representations of text and KG. Here we propose DRAGON (Deep Bidirectional Language-Knowledge Graph Pretraining), a self-supervised approach to pretraining a deeply joint language-knowledge foundation model from text and KG at scale. Specifically, our model takes pairs of text segments and relevant KG subgraphs as input and bidirectionally fuses information from both modalities. We pretrain this model by unifying two self-supervised reasoning tasks, masked language modeling and KG link prediction. DRAGON outperforms existing LM and LM+KG models on diverse downstream tasks including question answering across general and biomedical domains, with +5% absolute gain on average. In particular, DRAGON achieves notable performance on complex reasoning about language and knowledge (+10% on questions involving long contexts or multi-step reasoning) and low-resource QA (+8% on OBQA and RiddleSense), and new state-of-the-art results on various BioNLP tasks. Our code and trained models are available at https://github.com/michiyasunaga/dragon. 

   more » « less
3. GreaseLM: Graph REASoning Enhanced Language Models for Question Answering

   https://doi.org/10.48550/arXiv.2201.08860  

   Zhang, X; Bosselut, A; Yasunaga, M; Ren, H; Liang, P; Manning, C; Leskovec, J (January 2022, International Conference on Representation Learning (ICLR))

   Answering complex questions about textual narratives requires reasoning over both stated context and the world knowledge that underlies it. However, pretrained language models (LM), the foundation of most modern QA systems, do not robustly represent latent relationships between concepts, which is necessary for reasoning. While knowledge graphs (KG) are often used to augment LMs with structured representations of world knowledge, it remains an open question how to effectively fuse and reason over the KG representations and the language context, which provides situational constraints and nuances. In this work, we propose GreaseLM, a new model that fuses encoded representations from pretrained LMs and graph neural networks over multiple layers of modality interaction operations. Information from both modalities propagates to the other, allowing language context representations to be grounded by structured world knowledge, and allowing linguistic nuances (e.g., negation, hedging) in the context to inform the graph representations of knowledge. Our results on three benchmarks in the commonsense reasoning (i.e., CommonsenseQA, OpenbookQA) and medical question answering (i.e., MedQA-USMLE) domains demonstrate that GreaseLM can more reliably answer questions that require reasoning over both situational constraints and structured knowledge, even outperforming models 8x larger. 

   more » « less
4. Context-aware Multimodal Auditory BCI Classification through Graph Neural Networks

   https://doi.org/10.1109/EMBC40787.2023.10339984  

   Kumar, Chetan; Rahimi, Neela; Gonjari, Rohan; McLinden, John; Hosni, Sarah Ismail; Shahriari, Yalda; Shao, Ming (July 2023, IEEE)

   The prospect of electroencephalography (EEG) and functional near-infrared spectroscopy (fNIRS) in the presence of topological information of participants is often left unexplored in most of the brain-computer interface (BCI) systems. Additionally, the usage of these modalities together in the field of multimodality analysis to support multiple brain signals toward improving BCI performance is not fully examined. This study first presents a multimodal data fusion framework to exploit and decode the complementary synergistic properties in multimodal neural signals. Moreover, the relations among different subjects and their observations also play critical roles in classifying unknown subjects. We developed a context-aware graph neural network (GNN) model utilizing the pairwise relationship among participants to investigate the performance on an auditory task classification. We explored standard and deviant auditory EEG and fNIRS data where each subject was asked to perform an auditory oddball task and has multiple trials regarded as context-aware nodes in our graph construction. In experiments, our multimodal data fusion strategy showed an improvement up to 8.40% via SVM and 2.02% via GNN, compared to the single-modal EEG or fNIRS. In addition, our context-aware GNN achieved 5.3%, 4.07% and 4.53% higher accuracy for EEG, fNIRS and multimodal data based experiments, compared to the baseline models. 

   more » « less
5. Visual Query Answering by Entity-Attribute Graph Matching and Reasoning

   Xiong, Peixi; Zhan, Huayi; Wang, Xin; Shinha, Baivab; Wu, Ying (June 2019, Proc. IEEE/CVF Conf. on Computer Vision and Pattern Recognition)

   Visual Query Answering (VQA) is of great significance in offering people convenience: one can raise a question for details of objects, or high-level understanding about the scene, over an image. This paper proposes a novel method to address the VQA problem. In contrast to prior works, our method that targets single scene VQA, replies on graph-based techniques and involves reasoning. In a nutshell, our approach is centered on three graphs. The first graph, referred to as inference graph GI , is constructed via learning over labeled data. The other two graphs, referred to as query graph Q and entity-attribute graph GEA, are generated from natural language query Qnl and image Img, that are issued from users, respectively. As GEA often does not take sufficient information to answer Q, we develop techniques to infer missing information of GEA with GI . Based on GEA and Q, we provide techniques to find matches of Q in GEA, as the answer of Qnl in Img. Unlike commonly used VQA methods that are based on end-to-end neural networks, our graph-based method shows well-designed reasoning capability, and thus is highly interpretable. We also create a dataset on soccer match (Soccer-VQA) with rich annotations. The experimental results show that our approach outperforms the state-of-the-art method and has high potential for future investigation. 

   more » « less