Extracting causation knowledge from natural language texts

Abstract

SEKE is a semantic expectation-based knowledge extraction system for extracting causation knowledge from natural language texts. It is inspired by human behavior on analyzing texts and capturing information with semantic expectations. The framework of SEKE consists of different kinds of generic templates organized in a hierarchical fashion. There are semantic templates, sentence templates, reason templates, and consequence templates. The design of templates is based on the expected semantics of causation knowledge. They are robust and flexible. The semantic template represents the target relation. The sentence templates act as a middle layer to reconcile the semantic templates with natural language texts. With the designed templates, SEKE is able to extract causation knowledge from complex sentences. Another characteristic of SEKE is that it can discover unseen knowledge for reason and consequence by means of pattern discovery. Using simple linguistic information, SEKE can discover extraction pattern from previously extracted causation knowledge and apply the newly generated patterns for knowledge discovery. To demonstrate the adaptability of SEKE for different domains, we investigate the application of SEKE on two domain areas of news articles, namely the Hong Kong stock market movement domain and the global warming domain. Although these two domain areas are completely different, in respect to their expected semantics in reason and consequence, SEKE can effectively handle the natural language texts in these two domains for causation knowledge extraction.

Learning causality for news events prediction

“…However, representing the events "U.S army bombs a warehouse in Iraq", "Iraq attacks the U.S base" and "Terrorist base was attacked by the U.S marines in Kabul" using terms alone might yield that the first two events more similar than the first and last -as it lacks the understanding the actor of both events is a military group and that Kabul and Iraq are the locations of the events. The second approach, describes events in a syntax-driven way, where each element is mapped to a noun phrase [12,19,13,9]. In our example, this representation again will not find the appropriate similarity of the events, as in the syntax level both the second and third event are similar.…”

“…In computational linguistics, many studies deal with extraction of causality relations from text using causality patterns. These patterns are either manually crafted [18,19,13,12], or automatically generated using machine learning techniques [5,36,32,33,1,24,9]. In textual entailment [14], the task is to identify texts that logically follow one another.…”

The Architecture of Mobile Knowledge Service Based on Document Knowledge Base & Its Application

“…Among which the autonomy and adaptive ability of agent can help users obtaining knowledge quickly to finish work intelligently. The method of document classification algorithm [9] based on the concept of agent can calculate it simply, but not involves context. The paper puts forward the document classification algorithm based on the core of clustered context to enhance the value of document knowledge in mobile knowledge service, the specification of which is following:…”

Towards Improving Causality Mining using BERT with Multi-level Feature Networks

“…Understanding causality among event pairs in natural language text (NLT) is the first and fundamental step for text understanding. Causality plays a significant role in diverse NLP applications including, decision making [1], event prediction [2], [3], generating future scenarios and medical text mining [4], [5], and question answering [6], [7] in a wide range of disciplines [8] including Computer Science [9], Environmental Sciences [10], Medicine [11], Philosophy [12], Linguistics [13], [14], and Psychology [15], [16].…”