Large Language Models (LLMs) have shown strong performance in translating natural language into programming languages like Python or Java. However, for niche computer languages, where there is limited training data, fine-tuning a base model is often necessary. A key challenge arises when the pretrained embeddings of natural language terms interfere with the intended syntax and semantics of formal language terms. This issue is especially pronounced in the logical language of SUO-KIF, which is used in the Suggested Upper Merged Ontology (SUMO). SUMO contains thousands of terms that closely resemble everyday English words. As a result, models often produce syntactic errors or hallucinate non-existent terms due to conflicting embeddings learned during base training. This work introduces a tokenization-based technique to mitigate these issues. By altering how formal terms are tokenized, we can decouple their embeddings from similar natural language words, significantly reducing syntax errors and term hallucinations in the generated formal language output.

Concordancers are an accepted and valuable part of the tool set of linguists and lexicographers.They allow the user to see the context of use of a word or phrase in a corpus.A large enough corpus, such as the Corpus Of Contemporary American English, provides the data needed to enumerate all common uses or meanings.One challenge is that there may be too many results for short search phrases or common words when only a specific context is desired.However, finding meaningful groupings of usage may be impractical if it entails enumerating long lists of possible values, such as city names.If a tool existed that could create some semantic abstractions, it would free the lexicographer from the need to resort to customized development of analysis software.To address this need, we have developed a Semantic Concordancer that uses dependency parsing and the Suggested Upper Merged Ontology (SUMO) to support linguistic analysis at a level of semantic abstraction above the original textual elements.We show how this facility can be employed to analyze the use of English prepositions by non-native speakers.We briefly introduce condordancers and then describe the corpora on which we applied this work.Next we provide a detailed description of the NLP pipeline followed by how this captures detailed semantics.We show how the semantics can be used to analyze errors in the use of English prepositions by non-native speakers of English.Then we provide a description of a tool that allows users to build seman-tic search specifications from a set of English examples and how those results can be employed to build rules that translate sentences into logical forms.Finally, we summarize our conclusions and mention future work.

We describe the implementation of a short answer extraction system.It consists of a simple sentence selection front-end and a two phase approach to answer extraction from a sentence.In the first phase sentence classification is performed with a classifier trained with the passive aggressive algorithm utilizing the UIUC dataset and taxonomy and a feature set including word vectors.This phase outperforms the current best published results on that dataset.In the second phase, a sieve algorithm consisting of a series of increasingly general extraction rules is applied, using WordNet to find word types aligned with the UIUC classifications determined in the first phase.Some very preliminary performance metrics are presented.

Ontologies are becoming more and more popular as background knowledge for intelligent applications. Up to now, there has been a schism between manually assembled, highly axiomatic ontologies and large, automatically constructed knowledge bases. This paper discusses how the two worlds can be brought together by combining the high-level axiomatizations from the standard upper merged ontology (SUMO) with the extensive world knowledge of the YAGO ontology. The result is a new large-scale formal ontology, which provides information about millions of entities such as people, cities, organizations, and companies.

Abstract — The Suggested Upper Merged Ontology (SUMO) is an upper level ontology that has been proposed as a starter document for The Standard Upper Ontology Working Group, an IEEE-sanctioned working group of collaborators from the fields of engineering, philosophy, and information science. The SUMO provides definitions for general-purpose terms and acts as a foundation for more specific domain ontologies. In this paper we outline the strategy used to create the current version of the SUMO, discuss some of the challenges that we faced in constructing the ontology, and describe in detail its most general concepts and the relations between them. Categories & Descriptors — I.2.4 [Knowledge Representation Formalisms and