scholarly journals Guided Generation of Cause and Effect

2020 ◽  
Author(s):  
Zhongyang Li ◽  
Xiao Ding ◽  
Ting Liu ◽  
J. Edward Hu ◽  
Benjamin Van Durme
Keyword(s):  
Causal Reasoning ◽  
Large Scale ◽  
State Of The Art ◽  
Prior Work ◽  
Text Generation ◽  
Causal Knowledge ◽  
High Quality ◽  
Cause And Effect ◽  
Knowledge Graphs ◽  
Human Assessment

We present a conditional text generation framework that posits sentential expressions of possible causes and effects. This framework depends on two novel resources we develop in the course of this work: a very large-scale collection of English sentences expressing causal patterns (CausalBank); and a refinement over previous work on constructing large lexical causal knowledge graphs (Cause Effect Graph). Further, we extend prior work in lexically-constrained decoding to support disjunctive positive constraints. Human assessment confirms that our approach gives high-quality and diverse outputs. Finally, we use CausalBank to perform continued training of an encoder supporting a recent state-of-the-art model for causal reasoning, leading to a 3-point improvement on the COPA challenge set, with no change in model architecture.

scholarly journals End-to-End Argumentation Knowledge Graph Construction

2020 ◽  
Vol 34 (05) ◽  
pp. 7367-7374
Author(s):  
Khalid Al-Khatib ◽  
Yufang Hou ◽  
Henning Wachsmuth ◽  
Charles Jochim ◽  
Francesca Bonin ◽  
...  
Keyword(s):  
Large Scale ◽  
Question Answering ◽  
Knowledge Graph ◽  
Exploratory Search ◽  
Text Generation ◽  
Fake News ◽  
High Quality ◽  
Web Based ◽  
Knowledge Graphs ◽  
End To End

This paper studies the end-to-end construction of an argumentation knowledge graph that is intended to support argument synthesis, argumentative question answering, or fake news detection, among others. The study is motivated by the proven effectiveness of knowledge graphs for interpretable and controllable text generation and exploratory search. Original in our work is that we propose a model of the knowledge encapsulated in arguments. Based on this model, we build a new corpus that comprises about 16k manual annotations of 4740 claims with instances of the model's elements, and we develop an end-to-end framework that automatically identifies all modeled types of instances. The results of experiments show the potential of the framework for building a web-based argumentation graph that is of high quality and large scale.

Thermal Laser Separation – A Novel Dicing Technology Fulfilling the Demands of Volume Manufacturing of 4H-SiC Devices

2015 ◽  
Vol 821-823 ◽  
pp. 528-532 ◽  
Author(s):  
Dirk Lewke ◽  
Karl Otto Dohnke ◽  
Hans Ulrich Zühlke ◽  
Mercedes Cerezuela Barret ◽  
Martin Schellenberger ◽  
...  
Keyword(s):  
Experimental Data ◽  
Process Control ◽  
Tool Wear ◽  
Large Scale ◽  
State Of The Art ◽  
Scale Production ◽  
High Quality ◽  
Large Scale Production ◽  
Laser Separation

One challenge for volume manufacturing of 4H-SiC devices is the state-of-the-art wafer dicing technology – the mechanical blade dicing which suffers from high tool wear and low feed rates. In this paper we discuss Thermal Laser Separation (TLS) as a novel dicing technology for large scale production of SiC devices. We compare the latest TLS experimental data resulting from fully processed 4H-SiC wafers with results obtained by mechanical dicing technology. Especially typical product relevant features like process control monitoring (PCM) structures and backside metallization, quality of diced SiC-devices as well as productivity are considered. It could be shown that with feed rates up to two orders of magnitude higher than state-of-the-art, no tool wear and high quality of diced chips, TLS has a very promising potential to fulfill the demands of volume manufacturing of 4H-SiC devices.

High-Quality Knowledge Graphs Generation: R2RML and RML Comparison, Rules Validation and Inconsistency Resolution

2020 ◽  
Author(s):  
Anastasia Dimou
Keyword(s):  
State Of The Art ◽  
The State ◽  
Knowledge Graph ◽  
High Quality ◽  
Inconsistency Resolution ◽  
Knowledge Graphs ◽  
Rdf Graphs ◽  
Graph Generation

In this chapter, an overview of the state of the art on knowledge graph generation is provided, with focus on the two prevalent mapping languages: the W3C recommended R2RML and its generalisation RML. We look into details on their differences and explain how knowledge graphs, in the form of RDF graphs, can be generated with each one of the two mapping languages. Then we assess if the vocabulary terms were properly applied to the data and no violations occurred on their use, either using R2RML or RML to generate the desired knowledge graph.

scholarly journals AI-Sketcher : A Deep Generative Model for Producing High-Quality Sketches

2019 ◽  
Vol 33 ◽  
pp. 2564-2571 ◽  
Author(s):  
Nan Cao ◽  
Xin Yan ◽  
Yang Shi ◽  
Chaoran Chen
Keyword(s):  
Artificial Intelligence ◽  
Large Scale ◽  
State Of The Art ◽  
Positional Information ◽  
Generative Model ◽  
Training Data ◽  
Creative Design ◽  
High Quality ◽  
User Input ◽  
Variational Autoencoder

Sketch drawings play an important role in assisting humans in communication and creative design since ancient period. This situation has motivated the development of artificial intelligence (AI) techniques for automatically generating sketches based on user input. Sketch-RNN, a sequence-to-sequence variational autoencoder (VAE) model, was developed for this purpose and known as a state-of-the-art technique. However, it suffers from limitations, including the generation of lowquality results and its incapability to support multi-class generations. To address these issues, we introduced AI-Sketcher, a deep generative model for generating high-quality multiclass sketches. Our model improves drawing quality by employing a CNN-based autoencoder to capture the positional information of each stroke at the pixel level. It also introduces an influence layer to more precisely guide the generation of each stroke by directly referring to the training data. To support multi-class sketch generation, we provided a conditional vector that can help differentiate sketches under various classes. The proposed technique was evaluated based on two large-scale sketch datasets, and results demonstrated its power in generating high-quality sketches.

scholarly journals A Co-Embedding Model with Variational Auto-Encoder for Knowledge Graphs

2022 ◽  
Vol 12 (2) ◽  
pp. 715
Author(s):  
Luodi Xie ◽  
Huimin Huang ◽  
Qing Du
Keyword(s):  
State Of The Art ◽  
Relation Extraction ◽  
Semantic Space ◽  
Knowledge Graph ◽  
High Quality ◽  
Gaussian Distributions ◽  
Benchmark Datasets ◽  
Semantic Spaces ◽  
Knowledge Graphs ◽  
Low Dimensional

Knowledge graph (KG) embedding has been widely studied to obtain low-dimensional representations for entities and relations. It serves as the basis for downstream tasks, such as KG completion and relation extraction. Traditional KG embedding techniques usually represent entities/relations as vectors or tensors, mapping them in different semantic spaces and ignoring the uncertainties. The affinities between entities and relations are ambiguous when they are not embedded in the same latent spaces. In this paper, we incorporate a co-embedding model for KG embedding, which learns low-dimensional representations of both entities and relations in the same semantic space. To address the issue of neglecting uncertainty for KG components, we propose a variational auto-encoder that represents KG components as Gaussian distributions. In addition, compared with previous methods, our method has the advantages of high quality and interpretability. Our experimental results on several benchmark datasets demonstrate our model’s superiority over the state-of-the-art baselines.

scholarly journals PARABANK: Monolingual Bitext Generation and Sentential Paraphrasing via Lexically-Constrained Neural Machine Translation

2019 ◽  
Vol 33 ◽  
pp. 6521-6528
Author(s):  
J. Edward Hu ◽  
Rachel Rudinger ◽  
Matt Post ◽  
Benjamin Van Durme
Keyword(s):  
Machine Translation ◽  
Semantic Similarity ◽  
Large Scale ◽  
Prior Work ◽  
High Quality ◽  
Lexical Diversity ◽  
Neural Machine Translation ◽  
Source Sentence ◽  
Lexical Constraints

We present PARABANK, a large-scale English paraphrase dataset that surpasses prior work in both quantity and quality. Following the approach of PARANMT (Wieting and Gimpel, 2018), we train a Czech-English neural machine translation (NMT) system to generate novel paraphrases of English reference sentences. By adding lexical constraints to the NMT decoding procedure, however, we are able to produce multiple high-quality sentential paraphrases per source sentence, yielding an English paraphrase resource with more than 4 billion generated tokens and exhibiting greater lexical diversity. Using human judgments, we also demonstrate that PARABANK’s paraphrases improve over PARANMT on both semantic similarity and fluency. Finally, we use PARABANK to train a monolingual NMT model with the same support for lexically-constrained decoding for sentence rewriting tasks.

scholarly journals KEPLER: A Unified Model for Knowledge Embedding and Pre-trained Language Representation

2021 ◽  
Vol 9 ◽  
pp. 176-194
Author(s):  
Xiaozhi Wang ◽  
Tianyu Gao ◽  
Zhaocheng Zhu ◽  
Zhengyan Zhang ◽  
Zhiyuan Liu ◽  
...  
Keyword(s):  
Link Prediction ◽  
Large Scale ◽  
State Of The Art ◽  
Source Code ◽  
Language Modeling ◽  
Unified Model ◽  
Factual Knowledge ◽  
Textual Information ◽  
Language Representation ◽  
Knowledge Graphs

Abstract Pre-trained language representation models (PLMs) cannot well capture factual knowledge from text. In contrast, knowledge embedding (KE) methods can effectively represent the relational facts in knowledge graphs (KGs) with informative entity embeddings, but conventional KE models cannot take full advantage of the abundant textual information. In this paper, we propose a unified model for Knowledge Embedding and Pre-trained LanguagERepresentation (KEPLER), which can not only better integrate factual knowledge into PLMs but also produce effective text-enhanced KE with the strong PLMs. In KEPLER, we encode textual entity descriptions with a PLM as their embeddings, and then jointly optimize the KE and language modeling objectives. Experimental results show that KEPLER achieves state-of-the-art performances on various NLP tasks, and also works remarkably well as an inductive KE model on KG link prediction. Furthermore, for pre-training and evaluating KEPLER, we construct Wikidata5M1 , a large-scale KG dataset with aligned entity descriptions, and benchmark state-of-the-art KE methods on it. It shall serve as a new KE benchmark and facilitate the research on large KG, inductive KE, and KG with text. The source code can be obtained from https://github.com/THU-KEG/KEPLER.

scholarly journals Neural Entity Summarization with Joint Encoding and Weak Supervision

2020 ◽  
Author(s):  
Junyou Li ◽  
Gong Cheng ◽  
Qingxia Liu ◽  
Wen Zhang ◽  
Evgeny Kharlamov ◽  
...  
Keyword(s):  
Large Scale ◽  
State Of The Art ◽  
Neural Model ◽  
Knowledge Graph ◽  
Graph Structure ◽  
High Quality ◽  
Manual Work ◽  
Weak Supervision ◽  
Entity Summarization ◽  
Joint Encoding

In a large-scale knowledge graph (KG), an entity is often described by a large number of triple-structured facts. Many applications require abridged versions of entity descriptions, called entity summaries. Existing solutions to entity summarization are mainly unsupervised. In this paper, we present a supervised approach NEST that is based on our novel neural model to jointly encode graph structure and text in KGs and generate high-quality diversified summaries. Since it is costly to obtain manually labeled summaries for training, our supervision is weak as we train with programmatically labeled data which may contain noise but is free of manual work. Evaluation results show that our approach significantly outperforms the state of the art on two public benchmarks.

scholarly journals To hop or not, that is the question: Towards effective multi-hop reasoning over knowledge graphs

2021 ◽  
Author(s):  
Jinzhi Liao ◽  
Xiang Zhao ◽  
Jiuyang Tang ◽  
Weixin Zeng ◽  
Zhen Tan
Keyword(s):  
Decision Making ◽  
Reinforcement Learning ◽  
Supervised Learning ◽  
Large Scale ◽  
State Of The Art ◽  
False Negative ◽  
Stop Signal ◽  
Knowledge Graph ◽  
Overall Performance ◽  
Knowledge Graphs

AbstractWith the proliferation of large-scale knowledge graphs (KGs), multi-hop knowledge graph reasoning has been a capstone that enables machines to be able to handle intelligent tasks, especially where some explicit reasoning path is appreciated for decision making. To train a KG reasoner, supervised learning-based methods suffer from false-negative issues, i.e., unseen paths during training are not to be found in prediction; in contrast, reinforcement learning (RL)-based methods do not require labeled paths, and can explore to cover many appropriate reasoning paths. In this connection, efforts have been dedicated to investigating several RL formulations for multi-hop KG reasoning. Particularly, current RL-based methods generate rewards at the very end of the reasoning process, due to which short paths of hops less than a given threshold are likely to be overlooked, and the overall performance is impaired. To address the problem, we propose , a revised RL formulation of multi-hop KG reasoning that is characterized by two novel designs—the stop signal and the worth-trying signal. The stop signal instructs the agent of RL to stay at the entity after finding the answer, preventing from hopping further even if the threshold is not reached; meanwhile, the worth-trying signal encourages the agent to try to learn some partial patterns from the paths that fail to lead to the answer. To validate the design of our model , comprehensive experiments are carried out on three benchmark knowledge graphs, and the results and analysis suggest the superiority of over state-of-the-art methods.

scholarly journals Conversation Concepts: Understanding Topics and Building Taxonomies for Financial Services

Information ◽  
2021 ◽  
Vol 12 (4) ◽  
pp. 160
Author(s):  
John P. McCrae ◽  
Pranab Mohanty ◽  
Siddharth Narayanan ◽  
Bianca Pereira ◽  
Paul Buitelaar ◽  
...  
Keyword(s):  
Language Processing ◽  
Financial Services ◽  
State Of The Art ◽  
Knowledge Graph ◽  
Financial Industry ◽  
High Quality ◽  
Processing Technologies ◽  
Knowledge Graphs ◽  
Graph System ◽  
New Applications

Knowledge graphs are proving to be an increasingly important part of modern enterprises, and new applications of such enterprise knowledge graphs are still being found. In this paper, we report on the experience with the use of an automatic knowledge graph system called Saffron in the context of a large financial enterprise and show how this has found applications within this enterprise as part of the “Conversation Concepts Artificial Intelligence” tool. In particular, we analyse the use cases for knowledge graphs within this enterprise, and this led us to a new extension to the knowledge graph system. We present the results of these adaptations, including the introduction of a semi-supervised taxonomy extraction system, which includes analysts in-the-loop. Further, we extend the kinds of relations extracted by the system and show how the use of the BERTand ELMomodels can produce high-quality results. Thus, we show how this tool can help realize a smart enterprise and how requirements in the financial industry can be realised by state-of-the-art natural language processing technologies.

Sign in / Sign up

Export Citation Format

Share Document