Related papers: ValNorm Quantifies Semantics to Reveal Consistent …
Meaning is the foundation stone of intercultural communication. Languages are continuously changing, and words shift their meanings for various reasons. Semantic divergence in related languages is a key concern of historical linguistics. In…
The Word Embedding Association Test shows that GloVe and word2vec word embeddings exhibit human-like implicit biases based on gender, race, and other social constructs (Caliskan et al., 2017). Meanwhile, research on learning reusable text…
The notions of concreteness and imageability, traditionally important in psycholinguistics, are gaining significance in semantic-oriented natural language processing tasks. In this paper we investigate the predictability of these two…
Vector space models of words have long been claimed to capture linguistic regularities as simple vector translations, but problems have been raised with this claim. We decompose and empirically analyze the classic arithmetic word analogy…
As Large language models (LLMs) become increasingly integrated into our lives, their inherent social biases remain a pressing concern. Detecting and evaluating these biases can be challenging because they are often implicit rather than…
We approach the problem of generalizing pre-trained word embeddings beyond fixed-size vocabularies without using additional contextual information. We propose a subword-level word vector generation model that views words as bags of…
Word embeddings have been widely used in sentiment classification because of their efficacy for semantic representations of words. Given reviews from different domains, some existing methods for word embeddings exploit sentiment…
To extract essential information from complex data, computer scientists have been developing machine learning models that learn low-dimensional representation mode. From such advances in machine learning research, not only computer…
Recent research has shown that static word embeddings can encode word frequency information. However, little has been studied about this phenomenon and its effects on downstream tasks. In the present work, we systematically study the…
The vector representation of words, known as word embeddings, has opened a new research approach in linguistic studies. These representations can capture different types of information about words. The grammatical gender of nouns is a…
Multilingual Large Language Models (LLMs) exhibit remarkable cross-lingual abilities, yet often exhibit a systematic bias toward the representations from other languages, resulting in semantic interference when generating content in…
Vision-language models (VLM) align images and text in a shared representation space that is useful for retrieval and zero-shot transfer. Yet, this alignment can encode and amplify social stereotypes in subtle ways that are not obvious from…
Neural word representations have proven useful in Natural Language Processing (NLP) tasks due to their ability to efficiently model complex semantic and syntactic word relationships. However, most techniques model only one representation…
Investigating linguistic relationships on a global scale requires analyzing diverse features such as syntax, phonology and prosody, which evolve at varying rates influenced by internal diversification, language contact, and sociolinguistic…
Artificial intelligence and machine learning are in a period of astounding growth. However, there are concerns that these technologies may be used, either with or without intention, to perpetuate the prejudice and unfairness that…
In recent years, word embeddings have been widely used to measure biases in texts. Even if they have proven to be effective in detecting a wide variety of biases, metrics based on word embeddings lack transparency and interpretability. We…
Most popular word embedding techniques involve implicit or explicit factorization of a word co-occurrence based matrix into low rank factors. In this paper, we aim to generalize this trend by using numerical methods to factor higher-order…
Factor analysis studies have shown that the primary dimensions of word meaning are Valence (V), Arousal (A), and Dominance (D). Existing lexicons such as the NRC VAD Lexicon, published in 2018, include VAD association ratings for words.…
Multilingual representations embed words from many languages into a single semantic space such that words with similar meanings are close to each other regardless of the language. These embeddings have been widely used in various settings,…
Neural machine translation has significantly pushed forward the quality of the field. However, there are remaining big issues with the output translations and one of them is fairness. Neural models are trained on large text corpora which…