More Like this

1. Complex Factoid Question Answering with a Free-Text Knowledge Graph

   https://doi.org/10.1145/3366423.3380197  

   Zhao, Chen ; Xiong, Chenyan ; Qian, Xin ; Boyd-Graber, Jordan ( April 2020 , WWW '20: Proceedings of The Web Conference 2020)

   null (Ed.)

   We introduce delft, a factoid question answering system which combines the nuance and depth of knowledge graph question answering approaches with the broader coverage of free-text. delft builds a free-text knowledge graph from Wikipedia, with entities as nodes and sentences in which entities co-occur as edges. For each question, delft finds the subgraph linking question entity nodes to candidates using text sentences as edges, creating a dense and high coverage semantic graph. A novel graph neural network reasons over the free-text graph—combining evidence on the nodes via information along edge sentences—to select a final answer. Experiments on three question answering datasets show delft can answer entity-rich questions better than machine reading based models, bert-based answer ranking and memory networks. delft’s advantage comes from both the high coverage of its free-text knowledge graph—more than double that of dbpedia relations—and the novel graph neural network which reasons on the rich but noisy free-text evidence. 

   more » « less
2. A Joint Model for Definition Extraction with Syntactic Connection and Semantic Consistency

   https://doi.org/10.1609/aaai.v34i05.6444  

   Veyseh, Amir ; Dernoncourt, Franck ; Dou, Dejing ; Nguyen, Thien ( June 2020 , Proceedings of the AAAI Conference on Artificial Intelligence)

   null (Ed.)

   Definition Extraction (DE) is one of the well-known topics in Information Extraction that aims to identify terms and their corresponding definitions in unstructured texts. This task can be formalized either as a sentence classification task (i.e., containing term-definition pairs or not) or a sequential labeling task (i.e., identifying the boundaries of the terms and definitions). The previous works for DE have only focused on one of the two approaches, failing to model the inter-dependencies between the two tasks. In this work, we propose a novel model for DE that simultaneously performs the two tasks in a single framework to benefit from their inter-dependencies. Our model features deep learning architectures to exploit the global structures of the input sentences as well as the semantic consistencies between the terms and the definitions, thereby improving the quality of the representation vectors for DE. Besides the joint inference between sentence classification and sequential labeling, the proposed model is fundamentally different from the prior work for DE in that the prior work has only employed the local structures of the input sentences (i.e., word-to-word relations), and not yet considered the semantic consistencies between terms and definitions. In order to implement these novel ideas, our model presents a multi-task learning framework that employs graph convolutional neural networks and predicts the dependency paths between the terms and the definitions. We also seek to enforce the consistency between the representations of the terms and definitions both globally (i.e., increasing semantic consistency between the representations of the entire sentences and the terms/definitions) and locally (i.e., promoting the similarity between the representations of the terms and the definitions). The extensive experiments on three benchmark datasets demonstrate the effectiveness of our approach.1 

   more » « less
3. Dynamic Relevance Graph Network for Knowledge-Aware Question Answering

   Zheng, Chen ; Kordjamshidi, Parisa ( October 2022 , Proceedings of the 29th International Conference on Computational Linguistics)

   This work investigates the challenge of learning and reasoning for Commonsense Question Answering given an external source of knowledge in the form of a knowledge graph (KG). We propose a novel graph neural network architecture, called Dynamic Relevance Graph Network (DRGN). DRGN operates on a given KG subgraph based on the question and answers entities and uses the relevance scores between the nodes to establish new edges dynamically for learning node representations in the graph network. This explicit usage of relevance as graph edges has the following advantages, a) the model can exploit the existing relationships, re-scale the node weights, and influence the way the neighborhood nodes’ representations are aggregated in the KG subgraph, b) It potentially recovers the missing edges in KG that are needed for reasoning. Moreover, as a byproduct, our model improves handling the negative questions due to considering the relevance between the question node and the graph entities. Our proposed approach shows competitive performance on two QA benchmarks, CommonsenseQA and OpenbookQA, compared to the state-of-the-art published results. 

   more » « less
4. ABM: Attention-based Message Passing Network for Knowledge Graph Completion

   https://doi.org/10.1109/BigData55660.2022.10021003  

   Xu, Weikai ; Liu, Lihui ; Tong, Hanghang ( December 2022 , 2022 IEEE International Conference on Big Data (Big Data))

   Knowledge graph is ubiquitous and plays an important role in many real-world applications, including recommender systems, question answering, fact-checking, and so on. However, most of the knowledge graphs are incomplete which can hamper their practical usage. Fortunately, knowledge graph completion (KGC) can mitigate this problem by inferring missing edges in the knowledge graph according to the existing information. In this paper, we propose a novel KGC method named ABM (Attention-Based Message passing) which focuses on predicting the relation between any two entities in a knowledge graph. The proposed ABM consists of three integral parts, including (1) context embedding, (2) structure embedding, and (3) path embedding. In the context embedding, the proposed ABM generalizes the existing message passing neural network to update the node embedding and the edge embedding to assimilate the knowledge of nodes' neighbors, which captures the relative role information of the edge that we want to predict. In the structure embedding, the proposed method overcomes the shortcomings of the existing GNN method (i.e., most methods ignore the structural similarity between nodes.) by assigning different attention weights to different nodes while doing the aggregation. Path embedding generates paths between any two entities and treats these paths as sequences. Then, the sequence can be used as the input of the Transformer to update the embedding of the knowledge graph to gather the global role of the missing edges. By utilizing these three mutually complementary strategies, the proposed ABM is able to capture both the local and global information which in turn leads to a superb performance. Experiment results show that ABM outperforms baseline methods on a wide range of datasets. 

   more » « less
5. The Developmental Origins of Syntactic Bootstrapping

   https://doi.org/10.1111/tops.12447  

   Fisher, Cynthia ; Jin, Kyong‐sun ; Scott, Rose M. ( August 2019 , Topics in Cognitive Science)

   Children use syntax to learn verbs, in a process known as syntactic bootstrapping. The structure‐mapping account proposes that syntactic bootstrapping begins with a universal bias to map each noun phrase in a sentence onto a participant role in a structured conceptual representation of an event. Equipped with this bias, children interpret thenumber of noun phrasesaccompanying a new verb as evidence about the semantic predicate–argument structure of the sentence, and therefore about the meaning of the verb. In this paper, we first review evidence for the structure–mapping account, and then discuss challenges to the account arising from the existence of languages that allow verbs' arguments to be omitted, such as Korean. These challenges prompt us to (a) refine our notion of the distributional learning mechanisms that create representations of sentence structure, and (b) propose that anexpectation of discourse continuityallows children to gather linguistic evidence for each verb’s arguments across sentences in a coherent discourse. Taken together, the proposed learning mechanisms and biases sketch a route whereby simple aspects of sentence structure guide verb learning from the start of multi‐word sentence comprehension, and do so even if some of the new verb’s arguments are omitted due to discourse redundancy.

    

   more » « less