scholarly journals Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering

2020 ◽  
Vol 34 (05) ◽  
pp. 8449-8456 ◽  
Author(s):  
Shangwen Lv ◽  
Daya Guo ◽  
Jingjing Xu ◽  
Duyu Tang ◽  
Nan Duan ◽  
...  
Keyword(s):  
Question Answering ◽  
Structural Information ◽  
Representation Learning ◽  
Knowledge Bases ◽  
Knowledge Sources ◽  
Convolutional Network ◽  
External Knowledge ◽  
Relational Structures ◽  
Word Representation ◽  
Final Answer

Commonsense question answering aims to answer questions which require background knowledge that is not explicitly expressed in the question. The key challenge is how to obtain evidence from external knowledge and make predictions based on the evidence. Recent studies either learn to generate evidence from human-annotated evidence which is expensive to collect, or extract evidence from either structured or unstructured knowledge bases which fails to take advantages of both sources simultaneously. In this work, we propose to automatically extract evidence from heterogeneous knowledge sources, and answer questions based on the extracted evidence. Specifically, we extract evidence from both structured knowledge base (i.e. ConceptNet) and Wikipedia plain texts. We construct graphs for both sources to obtain the relational structures of evidence. Based on these graphs, we propose a graph-based approach consisting of a graph-based contextual word representation learning module and a graph-based inference module. The first module utilizes graph structural information to re-define the distance between words for learning better contextual word representations. The second module adopts graph convolutional network to encode neighbor information into the representations of nodes, and aggregates evidence with graph attention mechanism for predicting the final answer. Experimental results on CommonsenseQA dataset illustrate that our graph-based approach over both knowledge sources brings improvement over strong baselines. Our approach achieves the state-of-the-art accuracy (75.3%) on the CommonsenseQA dataset.

scholarly journals Contextualized Knowledge-aware Attentive Neural Network: Enhancing Answer Selection with Knowledge

2022 ◽  
Vol 40 (1) ◽  
pp. 1-33
Author(s):  
Yang Deng ◽  
Yuexiang Xie ◽  
Yaliang Li ◽  
Min Yang ◽  
Wai Lam ◽  
...  
Keyword(s):  
Neural Network ◽  
Language Processing ◽  
Question Answering ◽  
Representation Learning ◽  
Attention Mechanism ◽  
Convolutional Network ◽  
Structure Information ◽  
Dialog Systems ◽  
External Knowledge ◽  
Knowledge Based

Answer selection, which is involved in many natural language processing applications, such as dialog systems and question answering (QA), is an important yet challenging task in practice, since conventional methods typically suffer from the issues of ignoring diverse real-world background knowledge. In this article, we extensively investigate approaches to enhancing the answer selection model with external knowledge from knowledge graph (KG). First, we present a context-knowledge interaction learning framework, Knowledge-aware Neural Network, which learns the QA sentence representations by considering a tight interaction with the external knowledge from KG and the textual information. Then, we develop two kinds of knowledge-aware attention mechanism to summarize both the context-based and knowledge-based interactions between questions and answers. To handle the diversity and complexity of KG information, we further propose a Contextualized Knowledge-aware Attentive Neural Network, which improves the knowledge representation learning with structure information via a customized Graph Convolutional Network and comprehensively learns context-based and knowledge-based sentence representation via the multi-view knowledge-aware attention mechanism. We evaluate our method on four widely used benchmark QA datasets, including WikiQA, TREC QA, InsuranceQA, and Yahoo QA. Results verify the benefits of incorporating external knowledge from KG and show the robust superiority and extensive applicability of our method.

scholarly journals A Novel Method to Predict Drug-Target Interactions Based on Large-Scale Graph Representation Learning

Cancers ◽  
2021 ◽  
Vol 13 (9) ◽  
pp. 2111
Author(s):  
Bo-Wei Zhao ◽  
Zhu-Hong You ◽  
Lun Hu ◽  
Zhen-Hao Guo ◽  
Lei Wang ◽  
...  
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Computational Models ◽  
Structural Information ◽  
Characteristic Curve ◽  
Representation Learning ◽  
Graph Representation ◽  
Convolutional Network ◽  
Novel Method

Identification of drug-target interactions (DTIs) is a significant step in the drug discovery or repositioning process. Compared with the time-consuming and labor-intensive in vivo experimental methods, the computational models can provide high-quality DTI candidates in an instant. In this study, we propose a novel method called LGDTI to predict DTIs based on large-scale graph representation learning. LGDTI can capture the local and global structural information of the graph. Specifically, the first-order neighbor information of nodes can be aggregated by the graph convolutional network (GCN); on the other hand, the high-order neighbor information of nodes can be learned by the graph embedding method called DeepWalk. Finally, the two kinds of feature are fed into the random forest classifier to train and predict potential DTIs. The results show that our method obtained area under the receiver operating characteristic curve (AUROC) of 0.9455 and area under the precision-recall curve (AUPR) of 0.9491 under 5-fold cross-validation. Moreover, we compare the presented method with some existing state-of-the-art methods. These results imply that LGDTI can efficiently and robustly capture undiscovered DTIs. Moreover, the proposed model is expected to bring new inspiration and provide novel perspectives to relevant researchers.

scholarly journals Masking Orchestration: Multi-Task Pretraining for Multi-Role Dialogue Representation Learning

2020 ◽  
Vol 34 (05) ◽  
pp. 9217-9224
Author(s):  
Tianyi Wang ◽  
Yating Zhang ◽  
Xiaozhong Liu ◽  
Changlong Sun ◽  
Qiong Zhang
Keyword(s):  
Knowledge Integration ◽  
Question Answering ◽  
Representation Learning ◽  
Essential Information ◽  
External Knowledge ◽  
Learning Tasks ◽  
Wide Range ◽  
Specific Learning

Multi-role dialogue understanding comprises a wide range of diverse tasks such as question answering, act classification, dialogue summarization etc. While dialogue corpora are abundantly available, labeled data, for specific learning tasks, can be highly scarce and expensive. In this work, we investigate dialogue context representation learning with various types unsupervised pretraining tasks where the training objectives are given naturally according to the nature of the utterance and the structure of the multi-role conversation. Meanwhile, in order to locate essential information for dialogue summarization/extraction, the pretraining process enables external knowledge integration. The proposed fine-tuned pretraining mechanism is comprehensively evaluated via three different dialogue datasets along with a number of downstream dialogue-mining tasks. Result shows that the proposed pretraining mechanism significantly contributes to all the downstream tasks without discrimination to different encoders.

scholarly journals Dynamic Language Binding in Relational Visual Reasoning

2020 ◽  
Author(s):  
Thao Minh Le ◽  
Vuong Le ◽  
Svetha Venkatesh ◽  
Truyen Tran
Keyword(s):  
Question Answering ◽  
Compact Representation ◽  
Common Assumption ◽  
Relational Structures ◽  
The Common ◽  
Object Graph ◽  
Evolving Context ◽  
Dynamic Structures ◽  
Final Answer ◽  
Dual Domain

We present Language-binding Object Graph Network, the first neural reasoning method with dynamic relational structures across both visual and textual domains with applications in visual question answering. Relaxing the common assumption made by current models that the object predicates pre-exist and stay static, passive to the reasoning process, we propose that these dynamic predicates expand across the domain borders to include pair-wise visual-linguistic object binding. In our method, these contextualized object links are actively found within each recurrent reasoning step without relying on external predicative priors. These dynamic structures reflect the conditional dual-domain object dependency given the evolving context of the reasoning through co-attention. Such discovered dynamic graphs facilitate multi-step knowledge combination and refinements that iteratively deduce the compact representation of the final answer. The effectiveness of this model is demonstrated on image question answering demonstrating favorable performance on major VQA datasets. Our method outperforms other methods in sophisticated question-answering tasks wherein multiple object relations are involved. The graph structure effectively assists the progress of training, and therefore the network learns efficiently compared to other reasoning models.

scholarly journals Introducing External Knowledge to Answer Questions with Implicit Temporal Constraints over Knowledge Base

2020 ◽  
Vol 12 (3) ◽  
pp. 45
Author(s):  
Wenqing Wu ◽  
Zhenfang Zhu ◽  
Qiang Lu ◽  
Dianyuan Zhang ◽  
Qiangqiang Guo
Keyword(s):  
Natural Language ◽  
Knowledge Base ◽  
Question Answering ◽  
Knowledge Bases ◽  
Temporal Information ◽  
Temporal Constraints ◽  
External Knowledge ◽  
Question Answering Systems ◽  
Natural Language Question ◽  
Applied Knowledge

Knowledge base question answering (KBQA) aims to analyze the semantics of natural language questions and return accurate answers from the knowledge base (KB). More and more studies have applied knowledge bases to question answering systems, and when using a KB to answer a natural language question, there are some words that imply the tense (e.g., original and previous) and play a limiting role in questions. However, most existing methods for KBQA cannot model a question with implicit temporal constraints. In this work, we propose a model based on a bidirectional attentive memory network, which obtains the temporal information in the question through attention mechanisms and external knowledge. Specifically, we encode the external knowledge as vectors, and use additive attention between the question and external knowledge to obtain the temporal information, then further enhance the question vector to increase the accuracy. On the WebQuestions benchmark, our method not only performs better with the overall data, but also has excellent performance regarding questions with implicit temporal constraints, which are separate from the overall data. As we use attention mechanisms, our method also offers better interpretability.

scholarly journals Neural Program Induction for KBQA Without Gold Programs or Query Annotations

2019 ◽  
Author(s):  
Ghulam Ahmed Ansari ◽  
Amrita Saha ◽  
Vishwajeet Kumar ◽  
Mohan Bhambhani ◽  
Karthik Sankaranarayanan ◽  
...  
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Knowledge Bases ◽  
Neural Models ◽  
Input Program ◽  
Correct Program ◽  
Final Answer ◽  
High Level ◽  
Executable Programs ◽  
Complex Question

Neural Program Induction (NPI) is a paradigm for decomposing high-level tasks such as complex question-answering over knowledge bases (KBQA) into executable programs by employing neural models. Typically, this involves two key phases: i) inferring input program variables from the high-level task description, and ii) generating the correct program sequence involving these variables. Here we focus on NPI for Complex KBQA with only the final answer as supervision, and not gold programs. This raises major challenges; namely, i) noisy query annotation in the absence of any supervision can lead to catastrophic forgetting while learning, ii) reward becomes extremely sparse owing to the noise. To deal with these, we propose a noise-resilient NPI model, Stable Sparse Reward based Programmer (SSRP) that evades noise-induced instability through continual retrospection and its comparison with current learning behavior. On complex KBQA datasets, SSRP performs at par with hand-crafted rule-based models when provided with gold program input, and in the noisy settings outperforms state-of-the-art models by a significant margin even with a noisier query annotator.

scholarly journals Knowledge and Cross-Pair Pattern Guided Semantic Matching for Question Answering

2020 ◽  
Vol 34 (05) ◽  
pp. 9370-9377
Author(s):  
Zihan Xu ◽  
Hai-Tao Zheng ◽  
Shaopeng Zhai ◽  
Dong Wang
Keyword(s):  
Language Processing ◽  
Question Answering ◽  
Knowledge Bases ◽  
Matching Task ◽  
Specific Information ◽  
Semantic Matching ◽  
Convolutional Network ◽  
Domain Specific ◽  
Pair Matching ◽  
Selection Tasks

Semantic matching is a basic problem in natural language processing, but it is far from solved because of the differences between the pairs for matching. In question answering (QA), answer selection (AS) is a popular semantic matching task, usually reformulated as a paraphrase identification (PI) problem. However, QA is different from PI because the question and the answer are not synonymous sentences and not strictly comparable. In this work, a novel knowledge and cross-pair pattern guided semantic matching system (KCG) is proposed, which considers both knowledge and pattern conditions for QA. We apply explicit cross-pair matching based on Graph Convolutional Network (GCN) to help KCG recognize general domain-independent Q-to-A patterns better. And with the incorporation of domain-specific information from knowledge bases (KB), KCG is able to capture and explore various relations within Q-A pairs. Experiments show that KCG is robust against the diversity of Q-A pairs and outperforms the state-of-the-art systems on different answer selection tasks.

scholarly journals Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering

2020 ◽  
Author(s):  
Zihao Zhu ◽  
Jing Yu ◽  
Yujing Wang ◽  
Yajing Sun ◽  
Yue Hu ◽  
...  
Keyword(s):  
Question Answering ◽  
State Of The Art ◽  
Relevant Information ◽  
Convolutional Network ◽  
Graph Representations ◽  
Fine Grained ◽  
Visual Question Answering ◽  
Knowledge Reasoning ◽  
Final Answer ◽  
The Given

Fact-based Visual Question Answering (FVQA) requires external knowledge beyond the visible content to answer questions about an image. This ability is challenging but indispensable to achieve general VQA. One limitation of existing FVQA solutions is that they jointly embed all kinds of information without fine-grained selection, which introduces unexpected noises for reasoning the final answer. How to capture the question-oriented and information-complementary evidence remains a key challenge to solve the problem. In this paper, we depict an image by a multi-modal heterogeneous graph, which contains multiple layers of information corresponding to the visual, semantic and factual features. On top of the multi-layer graph representations, we propose a modality-aware heterogeneous graph convolutional network to capture evidence from different layers that is most relevant to the given question. Specifically, the intra-modal graph convolution selects evidence from each modality and cross-modal graph convolution aggregates relevant information across different graph layers. By stacking this process multiple times, our model performs iterative reasoning across three modalities and predicts the optimal answer by analyzing all question-oriented evidence. We achieve a new state-of-the-art performance on the FVQA task and demonstrate the effectiveness and interpretability of our model with extensive experiments.

scholarly journals EmbedDTI: Enhancing the Molecular Representations via Sequence Embedding and Graph Convolutional Network for the Prediction of Drug-Target Interaction

Biomolecules ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1783
Author(s):  
Yuan Jin ◽  
Jiarui Lu ◽  
Runhan Shi ◽  
Yang Yang
Keyword(s):  
Drug Target ◽  
Large Scale ◽  
Structural Information ◽  
Representation Learning ◽  
Convolutional Network ◽  
Drug Discovery And Development ◽  
Target Proteins ◽  
Target Interaction ◽  
Drug Databases ◽  
Benchmark Datasets

The identification of drug-target interaction (DTI) plays a key role in drug discovery and development. Benefitting from large-scale drug databases and verified DTI relationships, a lot of machine-learning methods have been developed to predict DTIs. However, due to the difficulty in extracting useful information from molecules, the performance of these methods is limited by the representation of drugs and target proteins. This study proposes a new model called EmbedDTI to enhance the representation of both drugs and target proteins, and improve the performance of DTI prediction. For protein sequences, we leverage language modeling for pretraining the feature embeddings of amino acids and feed them to a convolutional neural network model for further representation learning. For drugs, we build two levels of graphs to represent compound structural information, namely the atom graph and substructure graph, and adopt graph convolutional network with an attention module to learn the embedding vectors for the graphs. We compare EmbedDTI with the existing DTI predictors on two benchmark datasets. The experimental results show that EmbedDTI outperforms the state-of-the-art models, and the attention module can identify the components crucial for DTIs in compounds.

Sign in / Sign up

Export Citation Format

Share Document