A knowledge graph-based content selection model for data-driven text generation
1
Citation
0
Reference
10
Related Paper
Citation Trend
Abstract:
Content selection is a critical task for natural language generation. A novel approach based on knowledge graph is proposed. Structure data is mapping to the graph and combined with user defined knowledge. The model analyses the content selection features on the graph, and automatically learns the content selection rules. The model was evaluated in the domain of weather forecasting.Keywords:
Knowledge graph
Content (measure theory)
Text generation
Abstract The development of knowledge management and service enlightens the upgrading of traditional vocational education and work assistance. This work focuses on the field of substation and proposes a novel knowledge service method based on the domain knowledge graph. Specifically, a systematic three-layer knowledge graph is constructed, reflecting the physical entity, specialized knowledge and basic knowledge in substations. Furthermore, a domain model is established to translate the user’s demand into a node set derived from the knowledge graph, and a path model is established to give a sequence of the derived nodes for recommendation. The results have been validated logical and reasonable in different scenarios of learning, training and getting assistance. Taking advantage of the structure and precision of our knowledge graph, more applications can be added into the substation-related services.
Knowledge graph
Cite
Citations (0)
Knowledge graph
Cite
Citations (3)
As an efficient and intelligent means of knowledge organization, knowledge graph has developed rapidly in recent years because it can help users to obtain the information they care about quickly and accurately. Knowledge extraction is a key link in the process of knowledge graph construction, which directly affects the construction quality and subsequent application effect of knowledge graph, and is also one of the criteria for evaluating the merits of knowledge graph. Knowledge extraction has become an important research branch in the field of natural language processing. This paper systematically introduces the knowledge extraction technology for knowledge graph construction, analyzes the key technologies of knowledge extraction in each domain for different data types, and summarizes them at last.
Knowledge graph
Cite
Citations (1)
Knowledge graphs in education are a hot topic for research and application in the era of artificial intelligence and big data. Based on the systematic review of the existing research on the construction of knowledge graphs in education, the article proposes a knowledge graph framework for education domain - construction of a corpus of knowledge graphs in education domain - automatic recognition of named entities - parallel mining of entity relations - fusion of disciplinary knowledge graphs in education domain under the view of artificial intelligence using deep learning algorithms. This paper proposes a method for automatic construction of knowledge graphs in the education domain, with a view to promoting the development of knowledge graph research in the education domain in China.
Knowledge graph
Conceptual graph
Discipline
Cite
Citations (0)
Content (measure theory)
Cite
Citations (73)
Existing data-driven methods can well handle short text generation. However, when applied to the long-text generation scenarios such as story generation or advertising text generation in the commercial scenario, these methods may generate illogical and uncontrollable texts. To address these aforementioned issues, we propose a graph-based grouping planner(GGP) following the idea of first-plan-then-generate. Specifically, given a collection of key phrases, GGP firstly encodes these phrases into an instance-level sequential representation and a corpus-level graph-based representation separately. With these two synergic representations, we then regroup these phrases into a fine-grained plan, based on which we generate the final long text. We conduct our experiments on three long text generation datasets and the experimental results reveal that GGP significantly outperforms baselines, which proves that GGP can control the long text generation by knowing how to say and in what order.
Text generation
Planner
Representation
Cite
Citations (0)
The debate about mental content is not well framed as internalists versus externalists, because there is both internal and external mental content. There is also a question about how best to draw the line between them, and this paper argues that this line is not usually drawn in the right place. It proposes a new alignment: the expression ‘internal content’ is to be taken to denote actually occurring, concrete, immediately phenomenologically given content. Absolutely everything else that can be said to be the content of experience is to be classified as external content. It turns out, under this new alignment, that internal content can be external content; this is the case when I think about your pain, or indeed my own pain. But this is as it should be.
Content (measure theory)
Line (geometry)
Internal forces
Cite
Citations (0)
In the field of military equipment knowledge, there are a large number of equipment models, weapon types, operating parameters and other time-frequency domain and airspace data information, which potentially contains a lot of valuable information. At present, in the face of these massive domain knowledge, combat related personnel cannot efficiently acquire the key knowledge, which means that they cannot provide effective guidance according to the potential key knowledge. In order to solve this problem, based on the investigation and analysis of the construction methods of the existing knowledge graph, this paper mined and extracted the knowledge of military equipment, instantiated and correlated different weapons and equipment, and constructed the knowledge graph of military equipment and question answering system. The construction of military equipment knowledge graph and question answering system can not only deeply study the key technical difficulties of domain graph, but also has strong strategic support significance for the development of related fields.
Knowledge graph
Cite
Citations (7)
Narrow mental content, if there is such a thing, is content that is entirely determined by the goings-on inside the head of the thinker. A central topic in the philosophy of mind since the mid-1970s has been whether there is a kind of mental content that is narrow in this sense. It is widely conceded, thanks to famous thought experiments by Hilary Putnam and Tyler Burge, that there is a kind of mental content that is not narrow. But it is often maintained that there is also a kind of mental content that is narrow, and that such content can play various key explanatory roles relating, inter alia , to epistemology and the explanation of action. This book argues that this is a forlorn hope. It carefully distinguishes a variety of conceptions of narrow content and a variety of explanatory roles that might be assigned to narrow content. It then argues that, once we pay sufficient attention to the details, there is no promising theory of narrow content in the offing.
Content (measure theory)
Cite
Citations (29)
In recent years, the size of big linked data has grown rapidly and this number is still rising. Big linked data and knowledge bases come from different domains such as life sciences, publications, media, social web, and so on. However, with the rapid increasing of data, it is very challenging for people to acquire a comprehensive collection of cross domain knowledge to meet their needs. Under this circumstance, it is extremely difficult for people without expertise to extract knowledge from various domains. Therefore, nowadays human limited knowledge can't feed the high requirement for discovering large amount of cross domain knowledge. In this research, we present a big graph analytics framework aims at addressing this issue by providing semantic methods to facilitate the management of big graph data from close domains in order to discover cross domain knowledge in a more accurate and efficient way.
Knowledge graph
Linked Data
Cite
Citations (0)