Recently, end-to-end (E2E) trained models for question answering over knowledge graphs (KGQA) have delivered promising results using only a weakly supervised dataset. However, these models are trained and evaluated in a setting where hand-annotated q
uestion entities are supplied to the model, leaving the important and non-trivial task of entity resolution (ER) outside the scope of E2E learning. In this work, we extend the boundaries of E2E learning for KGQA to include the training of an ER component. Our model only needs the question text and the answer entities to train, and delivers a stand-alone QA model that does not require an additional ER component to be supplied during runtime. Our approach is fully differentiable, thanks to its reliance on a recent method for building differentiable KGs (Cohen et al., 2020). We evaluate our E2E trained model on two public datasets and show that it comes close to baseline models that use hand-annotated entities.
Recent transformer-based approaches demonstrate promising results on relational scientific information extraction. Existing datasets focus on high-level description of how research is carried out. Instead we focus on the subtleties of how experimenta
l associations are presented by building SciClaim, a dataset of scientific claims drawn from Social and Behavior Science (SBS), PubMed, and CORD-19 papers. Our novel graph annotation schema incorporates not only coarse-grained entity spans as nodes and relations as edges between them, but also fine-grained attributes that modify entities and their relations, for a total of 12,738 labels in the corpus. By including more label types and more than twice the label density of previous datasets, SciClaim captures causal, comparative, predictive, statistical, and proportional associations over experimental variables along with their qualifications, subtypes, and evidence. We extend work in transformer-based joint entity and relation extraction to effectively infer our schema, showing the promise of fine-grained knowledge graphs in scientific claims and beyond.
Interactive machine reading comprehension (iMRC) is machine comprehension tasks where knowledge sources are partially observable. An agent must interact with an environment sequentially to gather necessary knowledge in order to answer a question. We
hypothesize that graph representations are good inductive biases, which can serve as an agent's memory mechanism in iMRC tasks. We explore four different categories of graphs that can capture text information at various levels. We describe methods that dynamically build and update these graphs during information gathering, as well as neural models to encode graph representations in RL agents. Extensive experiments on iSQuAD suggest that graph representations can result in significant performance improvements for RL agents.
Infusing factual knowledge into pre-trained models is fundamental for many knowledge-intensive tasks. In this paper, we proposed Mixture-of-Partitions (MoP), an infusion approach that can handle a very large knowledge graph (KG) by partitioning it in
to smaller sub-graphs and infusing their specific knowledge into various BERT models using lightweight adapters. To leverage the overall factual knowledge for a target task, these sub-graph adapters are further fine-tuned along with the underlying BERT through a mixture layer. We evaluate our MoP with three biomedical BERTs (SciBERT, BioBERT, PubmedBERT) on six downstream tasks (inc. NLI, QA, Classification), and the results show that our MoP consistently enhances the underlying BERTs in task performance, and achieves new SOTA performances on five evaluated datasets.
Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities. In this paper, we emphasize the importance of incorporating events
in KG representation learning, and propose an event-enhanced KG embedding model EventKE. Specifically, given the original KG, we first incorporate event nodes by building a heterogeneous network, where entity nodes and event nodes are distributed on the two sides of the network inter-connected by event argument links. We then use entity-entity relations from the original KG and event-event temporal links to inner-connect entity and event nodes respectively. We design a novel and effective attention-based message passing method, which is conducted on entity-entity, event-entity, and event-event relations to fuse the event information into KG embeddings. Experimental results on real-world datasets demonstrate that events can greatly improve the quality of the KG embeddings on multiple downstream tasks.
Knowledge graphs (KGs) are widely used to store and access information about entities and their relationships. Given a query, the task of entity retrieval from a KG aims at presenting a ranked list of entities relevant to the query. Lately, an increa
sing number of models for entity retrieval have shown a significant improvement over traditional methods. These models, however, were developed for English KGs. In this work, we build on one such system, named KEWER, to propose SERAG (Semantic Entity Retrieval from Arabic knowledge Graphs). Like KEWER, SERAG uses random walks to generate entity embeddings. DBpedia-Entity v2 is considered the standard test collection for entity retrieval. We discuss the challenges of using it for non-English languages in general and Arabic in particular. We provide an Arabic version of this standard collection, and use it to evaluate SERAG. SERAG is shown to significantly outperform the popular BM25 model thanks to its multi-hop reasoning.
WordNet is the most widely used lexical resource for English, while Wikidata is one of the largest knowledge graphs of entity and concepts available. While, there is a clear difference in the focus of these two resources, there is also a significant
overlap and as such a complete linking of these resources would have many uses. We propose the development of such a linking, first by means of the hapax legomenon links and secondly by the use of natural language processing techniques. We show that these can be done with high accuracy but that human validation is still necessary. This has resulted in over 9,000 links being added between these two resources.
