FrameNet CNL: A Knowledge Representation and Information Extraction Language

  title={FrameNet CNL: A Knowledge Representation and Information Extraction Language},
  author={Guntis Barzdins},
The paper presents a FrameNet-based information extraction and knowledge representation framework, called FrameNet-CNL. The framework is used on natural language documents and represents the extracted knowledge in a tailor-made Frame-ontology from which unambiguous FrameNet-CNL paraphrase text can be generated automatically in multiple languages. This approach brings together the fields of information extraction and CNL, because a source text can be considered belonging to FrameNet-CNL, if… 

A multilingual FrameNet-based grammar and lexicon for controlled natural language

The proposed approach leverages FrameNet-annotated corpora to automatically extract a set of cross-lingual semantico-syntactic valence patterns from a categorial grammar formalism specialized for multilingual grammars.

Controlled Natural Language Generation from a Multilingual FrameNet-Based Grammar

A methodological approach to automatically generate the grammar based on semantico-syntactic valence patterns extracted from FrameNet-annotated corpora to illustrate how the acquired multilingual grammar can be exploited in different CNL applications in the domains of arts and tourism.

Frame Semantics across Languages: Towards a Multilingual FrameNet

This workshop will present current research on aligning Frame Semantic resources across languages and automatic frame semantic parsing in English and other languages, and theoretical issues that have emerged in this area of research.

Mining Knowledge in Storytelling Systems for Narrative Generation

The use of Controlled Natural Language for expressing every storytelling system knowledge as a collection of natural language sentences is proposed and an initial grammar for a CNL is proposed, focusing on certain aspects of this knowledge.

Extracting Formal Models from Normative Texts

This work presents an experimental, semi-automatic aid to bridge the gap between a normative text and its formal representation, using dependency trees combined with his own rules and heuristics for extracting the relevant components.

Human-like Natural Language Generation Using Monte Carlo Tree Search

A model is proposed showing how automatically extracted and manually written association rules can be used to build the structure of a narrative from real-life temporal data. The generated text’s

Learning to Align across Languages: Toward Multilingual FrameNet

Multilingual FrameNet (MLFN) is an attempt to find alignments between the various FrameNets, employing tools from the fields of machine translation and document classification to introduce a new relation of similarity between frames, combining structural and distributional similarity.

Abstract Syntax as Interlingua: Scaling Up the Grammatical Framework from Controlled Languages to Robust Pipelines

An overview of the use of abstract syntax as interlingua through both established and emerging NLP applications involving GF is given.

Semi-supervised Deep Embedded Clustering with Anomaly Detection for Semantic Frame Induction

A two-step frame induction process for lexical units not yet present in Berkeley FrameNet data release 1.7 is proposed and the Semi-supervised Deep Embedded Clustering with Anomaly Detection (SDEC-AD) model is presented—an algorithm that maps high-dimensional contextualized vector representations of Lexical units to a low-dimensional latent space for better frame prediction and uses reconstruction error to identify lexicalunits that cannot evoke frames in FrameNet.



Applying Semantic Frame Theory to Automate Natural Language Template Generation From Ontology Statements

On-going work is presented that provides a starting point for exploiting framenet information for multilingual natural language generation and describes the kind of information offered by modern computational lexical resources and how template-based generation systems can benefit from them.

SemEval-2007 Task 19: Frame Semantic Structure Extraction

This task consists of recognizing words and phrases that evoke semantic frames as defined in the FrameNet project, and their semantic dependents, which are usually, but not always, their syntactic dependents (including subjects).

Using C5.0 and Exhaustive Search for Boosting Frame-Semantic Parsing Accuracy

A novel approach for boosting frame-semantic parsing accuracy through the use of the C5.0 decision tree classifier, a commercial version of the popular C4.5 decision treeclassifier, and manual rule enhancement is reported, which is particularly efficient for languages with small FrameNet annotated corpora.

Attempto Controlled English for Knowledge Representation

Attempto Controlled English (ACE) is a controlled natural language, i.e. a precisely defined subset of English that can automatically and unambiguously be translated into first-order logic. ACE may

Polysemy in Controlled Natural Language Texts

It is shown that micro-ontologies and multi-word units allow integration of the rich and polysemous multi-domain background knowledge into CNL thus providing interpretation for the content words.

FrameNet Resource Grammar Library for GF

This paper proposes an extension to the current RGL, allowing GF application developers to define clauses on the semantic level, thus leaving the language-specific syntactic mapping to this extension, and demonstrates the approach by reengineering the MOLTO Phrasebook application grammar.

Frame-Semantic Parsing

A two-stage statistical model that takes lexical targets in their sentential contexts and predicts frame-semantic structures and results in qualitatively better structures than naïve local predictors, which outperforms the prior state of the art by significant margins.

Improving efficiency and accuracy in multilingual entity extraction

This paper discusses some implementation and data processing challenges encountered while developing a new multilingual version of DBpedia Spotlight that is faster, more accurate and easier to configure, and compares the solution to the previous system.

Abstract Meaning Representation for Sembanking

A sembank of simple, whole-sentence semantic structures will spur new work in statistical natural language understanding and generation, like the Penn Treebank encouraged work on statistical parsing.

A joint model for discovering and linking entities

This work embraces the challenge of jointly modeling entity-linking and entity-discovery as a single entity resolution problem and presents a model that reasons over compact hierarchical entity representations, and proposes a novel distributed inference architecture that does not suffer from the synchronicity bottleneck which is inherent in map-reduce architectures.