Open English Wordnet is a key resource published in OntoLex-lemon as part of the linguistic linked open data cloud. There are, however, many links missing in the resource, and in this paper, we look at how we can establish hypernymy between adjectives. We present a theoretical discussion of the hypernymy relation and how it differs for adjectives in contrast to nouns and verbs. We develop a new resource for adjective hypernymy and fine-tune large language models to predict adjective hypernymy, showing that the methodology of TaxoLLaMa can be adapted to this task.

WordNet provides a carefully constructed repository of semantic relations, created by specialists. But there is another source of information on semantic relations, the intuition of language users. We present the first systematic study of the degree to which these two sources are aligned. Investigating the cases of misalignment could make proper use of WordNet and facilitate its improvement. Our analysis which uses templates to elicit responses from human participants, reveals a general misalignment of semantic relation knowledge between WordNet and human intuition. Further analyses find a systematic pattern of mismatch among synonymy and taxonomic relations~(hypernymy and hyponymy), together with the fact that WordNet path length does not serve as a reliable indicator of human intuition regarding hypernymy or hyponymy relations.

Recently, much work has concerned itself with the enigma of what exactly PLMs (pretrained language models) learn about different aspects of language, and how they learn it. One stream of this type of research investigates the knowledge that PLMs have about semantic relations. However, many aspects of semantic relations were left unexplored. Only one relation was considered, namely hypernymy. Furthermore, previous work did not measure humans' performance on the same task as that solved by the PLMs. This means that at this point in time, there is only an incomplete view of models' semantic relation knowledge. To address this gap, we introduce a comprehensive evaluation framework covering five relations beyond hypernymy, namely hyponymy, holonymy, meronymy, antonymy, and synonymy. We use six metrics (two newly introduced here) for recently untreated aspects of semantic relation knowledge, namely soundness, completeness, symmetry, asymmetry, prototypicality, and distinguishability and fairly compare humans and models on the same task. Our extensive experiments involve 16 PLMs, eight masked and eight causal language models. Up to now only masked language models had been tested although causal and masked language models treat context differently. Our results reveal a significant knowledge gap between humans and models for almost all semantic relations. Antonymy is the outlier relation where all models perform reasonably well. In general, masked language models perform significantly better than causal language models. Nonetheless, both masked and causal language models are likely to confuse non-antonymy relations with antonymy.

We present a novel approach to detecting noun abstraction within a large language model (LLM). Starting from a psychologically motivated set of noun pairs in taxonomic relationships, we instantiate surface patterns indicating hypernymy and analyze the attention matrices produced by BERT. We compare the results to two sets of counterfactuals and show that we can detect hypernymy in the abstraction mechanism, which cannot solely be related to the distributional similarity of noun pairs. Our findings are a first step towards the explainability of conceptual abstraction in LLMs.

Then, we describe how hypernymy can be represented in FDS in 3. In 4, we discuss how Functional Distributional Semantics (FDS; Emerson existential and universal quantifications support or and Copestake, 2016; Emerson, 2018) suggests undermine the Distributional Inclusion Hypothesis that the meaning of a word can be modelled as a (DIH), how FDS can handle both quantifications, truth-conditional function, whose parameters can and how FDS models can learn hypernymy under be learnt using the distributional information in a the DIH, and the reverse of it when equipped with corpus (Emerson, 2020a; Lo et al., 2023).

Current breakthroughs in natural language processing have benefited dramatically from neural language models, through which distributional semantics can leverage neural data representations to facilitate downstream applications. Since neural embeddings use context prediction on word co-occurrences to yield dense vectors, they are inevitably prone to capture more semantic association than semantic similarity. To improve vector space models in deriving semantic similarity, we post-process neural word embeddings through deep metric learning, through which we can inject lexical-semantic relations, including syn/antonymy and hypo/hypernymy, into a distributional space. We introduce hierarchy-fitting, a novel semantic specialization approach to modelling semantic similarity nuances inherently stored in the IS-A hierarchies. Hierarchy-fitting attains state-of-the-art results on the common- and rare-word benchmark datasets for deriving semantic similarity from neural word embeddings. It also incorporates an asymmetric distance function to specialize hypernymy's directionality explicitly, through which it significantly improves vanilla embeddings in multiple evaluation tasks of detecting hypernymy and directionality without negative impacts on semantic similarity judgement. The results demonstrate the efficacy of hierarchy-fitting in specializing neural embeddings with semantic relations in late fusion, potentially expanding its applicability to aggregating heterogeneous data and various knowledge resources for learning multimodal semantic spaces.

Natural language processing and statistical methods were used to identify linguistic features associated with the quality of student-generated paragraphs. Linguistic features were assessed using Coh-Metrix. The resulting computational models demonstrated small to medium effect sizes for predicting paragraph quality: introduction quality r2 = .25, body quality r2 = .10, and conclusion quality r2 = .11. Although the variance explained was somewhat low, the linguistic features identified were consistent with the rhetorical goals of paragraph types. Avenues for bolstering this approach by considering individual writing styles and techniques are considered.