Cognitive research indicates that abstraction ability is essential in human intelligence, which
remains under-explored in language models. In this paper, we present AbsPyramid, a …

Typed entailment graphs try to learn the entailment relations between predicates from text
and model them as edges between predicate nodes. The construction of entailment graphs …

The diversity and Zipfian frequency distribution of natural language predicates in corpora
leads to sparsity in Entailment Graphs (EGs) built by Open Relation Extraction (ORE). EGs …

We examine LMs' competence of directional predicate entailments by supervised fine-tuning
with prompts. Our analysis shows that contrary to their apparent success on standard NLI …

Abstraction ability is crucial in human intelligence, which can also benefit various tasks in
NLP study. Existing work shows that LLMs are deficient in abstract ability, and how to …

Drawing inferences between open-domain natural language predicates is a necessity for
true language understanding. There has been much progress in unsupervised learning of …

An open-domain knowledge graph (KG) has entities as nodes and natural language
relations as edges, and is constructed by extracting (subject, relation, object) triples from …

Lexical inference in context (LIiC) is the task of recognizing textual entailment between two
very similar sentences, ie, sentences that only differ in one expression. It can therefore be …

We present a novel method for injecting temporality into entailment graphs to address the
problem of spurious entailments, which may arise from similar but temporally distinct events …

The interpretation of the lexical aspect of verbs in English plays a crucial role for recognizing
textual entailment and learning discourse-level inferences. We show that two elementary …