Word embeddings are vectorial semantic representations built with either counting or predicting techniques aimed at capturing shades of meaning from word co-occurrences …
Commonsense knowledge acquisition is a key problem for artificial intelligence. Conventional methods of acquiring commonsense knowledge generally require laborious …
The Winograd Schema (WS) has been proposed as a test for measuring commonsense capabilities of models. Recently, pre-trained language model-based approaches have …
Commonsense knowledge acquisition and reasoning have long been a core artificial intelligence problem. However, in the past, there has been a lack of scalable methods to …
In this paper, we present the first comprehensive categorization of essential commonsense knowledge for answering the Winograd Schema Challenge (WSC). For each of the …
Z Li, A Mao, D Stephens, P Goel… - Proceedings of the …, 2024 - aclanthology.org
Topic models are a popular tool for understanding text collections, but their evaluation has been a point of contention. Automated evaluation metrics such as coherence are often used …
Distributional semantics develops theories and methods to represent the meaning of natural language expressions, with vectors encoding their statistical distribution in linguistic …
Prior research has explored the ability of computational models to predict a word semantic fit with a given predicate. While much work has been devoted to modeling the typicality relation …
Y Zhao, J Yin, J Zhang, L Wu - Scientometrics, 2023 - Springer
This study aims to investigate and identify the driving factors of word co-occurrence from the perspective of semantic relations between frequently co-occurring words. Natural sentences …