Normunds Gruzitis

FrameNet Resource Grammar Library for GF

In this paper we present an ongoing research investigating the possibility and potential of integrating frame semantics, particularly FrameNet, in the Grammatical Framework (GF) application grammar development. An important component of GF is its Resource Grammar Library (RGL) that encapsulates the low-level linguistic knowledge about morphology and syntax of currently more than 20 languages facilitating rapid development of multilingual applications. In the ideal case, porting a GF application grammar to a new language would only require introducing the domain lexicon – translation equivalents that are interlinked via common abstract terms. While it is possible for a highly restricted CNL, developing and porting a less restricted CNL requires above average linguistic knowledge about the particular language, and above average GF experience. Specifying a lexicon is mostly straightforward in the case of nouns (incl. multi-word units), however, verbs are the most complex category (in terms of both inflectional paradigms and argument structure), and adding them to a GF application grammar is not a straightforward task. In this paper we are focusing on verbs, investigating the possibility of creating a multilingual FrameNet-based GF library. We propose 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. We demonstrate our approach by reengineering the MOLTO Phrasebook application grammar.

Polysemy in controlled natural language texts

Computational semantics and logic-based controlled natural languages (CNL) do not address systematically the word sense disambiguation problem of content words, i.e., they tend to interpret only some functional words that are crucial for construction of discourse representation structures. We show 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. The proposed approach is demonstrated by extending the Attempto Controlled English (ACE) with polysemous and procedural constructs resulting in a more natural CNL named PAO covering narrative multi-domain texts.

Extracting Formal Models from Normative Texts

Normative texts are documents based on the deontic notions of obligation, permission, and prohibition. Our goal is to model such texts using the C-O Diagram formalism, making them amenable to formal analysis, in particular verifying that a text satisfies properties concerning causality of actions and timing constraints. We present an experimental, semi-automatic aid to bridge the gap between a normative text and its formal representation. Our approach uses dependency trees combined with our own rules and heuristics for extracting the relevant components. The resulting tabular data can then be converted into a C-O Diagram.

Extracting Semantic Knowledge from Unstructured Text Using Embedded Controlled Language

Nowadays, most of the data on the Web is still in the form of unstructured text. Knowledge extraction from unstructured text is highly desirable but extremely challenging due to the inherent ambiguity of natural language. In this article, we present an architecture of an information extraction system based on the concept of Embedded Controlled Language that allows for extracting formal semantic knowledge from an unstructured text corpus. Moreover, the presented approach has a potential to support multilingual input and output.

The Role of CNL and AMR in Scalable Abstractive Summarization for Multilingual Media Monitoring.

Addressing tax fraud has been taken increasingly seriously, but most attempts to uncover it involve the use of human fraud experts to identify and audit suspicious cases. To identify such cases, they come up with patterns which an IT team then implements to extract matching instances. The process, starting from the communication of the patterns to the developers, the debugging of the implemented code, and the refining of the rules, results in a lengthy and error-prone iterative methodology. In this paper, we present a framework where the fraud expert is empowered to independently design tax fraud patterns through a controlled natural language implemented in GF, enabling immediate feedback reported back to the fraud expert. This allows multiple refinements of the rules until optimised, all within a timely manner. The approach has been evaluated by a number of fraud experts working with the Maltese Inland Revenue Department.In the era of Big Data and Deep Learning, there is a common view that machine learning approaches are the only way to cope with the robust and scalable information extraction and summarization. It has been recently proposed that the CNL approach could be scaled up, building on the concept of embedded CNL and, thus, allowing for CNL-based information extraction from e.g. normative or medical texts that are rather controlled by nature but still infringe the boundaries of CNL. Although it is arguable if CNL can be exploited to approach the robust wide-coverage semantic parsing for use cases like media monitoring, its potential becomes much more obvious in the opposite direction: generation of story highlights from the summarized AMR graphs, which is in the focus of this position paper.

Embedded controlled language to facilitate information extraction from eGov policies

The goal of this paper is to propose a system that can extract formal semantic knowledge representation from natural language eGov policies. We present an architecture that allows for extracting Controlled Natural Language (CNL) statements from heterogeneous natural language texts with the ability to support multilinguality. The approach is based on the concept of embedded CNLs.