Related papers: Can Eye Movement Data Be Used As Ground Truth For …
The field of cross-lingual sentence embeddings has recently experienced significant advancements, but research concerning low-resource languages has lagged due to the scarcity of parallel corpora. This paper shows that cross-lingual word…
Distributed representations of words and paragraphs as semantic embeddings in high dimensional data are used across a number of Natural Language Understanding tasks such as retrieval, translation, and classification. In this work, we…
Distributional models learn representations of words from text, but are criticized for their lack of grounding, or the linking of text to the non-linguistic world. Grounded language models have had success in learning to connect concrete…
Similarity query is the family of queries based on some similarity metrics. Unlike the traditional database queries which are mostly based on value equality, similarity queries aim to find targets "similar enough to" the given data objects,…
We extend the SKIP-GRAM model of Mikolov et al. (2013a) by taking visual information into account. Like SKIP-GRAM, our multimodal models (MMSKIP-GRAM) build vector-based word representations by learning to predict linguistic contexts in…
Pre-trained language models have been found to capture a surprisingly rich amount of lexical knowledge, ranging from commonsense properties of everyday concepts to detailed factual knowledge about named entities. Among others, this makes it…
Recent advances in vision-language foundational models have enabled development of systems that can perform visual understanding and reasoning tasks. However, it is unclear if these models are robust to distribution shifts, and how their…
This paper presents a new approach for measuring semantic similarity/distance between words and concepts. It combines a lexical taxonomy structure with corpus statistical information so that the semantic distance between nodes in the…
In natural language processing, most models try to learn semantic representations merely from texts. The learned representations encode the distributional semantics but fail to connect to any knowledge about the physical world. In contrast,…
Most modern computational approaches to lexical semantic change detection (LSC) rely on embedding-based distributional word representations with neural networks. Despite the strong performance on LSC benchmarks, they are often opaque. We…
End-to-end acoustic-to-word speech recognition models have recently gained popularity because they are easy to train, scale well to large amounts of training data, and do not require a lexicon. In addition, word models may also be easier to…
The goal of this paper is to learn more about how idiomatic information is structurally encoded in embeddings, using a structural probing method. We repurpose an existing English verbal multi-word expression (MWE) dataset to suit the…
Semantic vector embedding techniques have proven useful in learning semantic representations of data across multiple domains. A key application enabled by such techniques is the ability to measure semantic similarity between given data…
Diachronic word embeddings -- vector representations of words over time -- offer remarkable insights into the evolution of language and provide a tool for quantifying sociocultural change from text documents. Prior work has used such…
Dense word embeddings, which encode semantic meanings of words to low dimensional vector spaces have become very popular in natural language processing (NLP) research due to their state-of-the-art performances in many NLP tasks. Word…
The automatic ranking of word pairs as per their semantic relatedness and ability to mimic human notions of semantic relatedness has widespread applications. Measures that rely on raw data (distributional measures) and those that use…
Neural language models, particularly large-scale ones, have been consistently proven to be most effective in predicting brain neural activity across a range of studies. However, previous research overlooked the comparison of these models…
Cognitively inspired Natural Language Pro-cessing uses human-derived behavioral datalike eye-tracking data, which reflect the seman-tic representations of language in the humanbrain to augment the neural nets to solve arange of tasks…
Does the grammatical gender of a language interfere when measuring the semantic gender information captured by its word embeddings? A number of anomalous gender bias measurements in the embeddings of gendered languages suggest this…
Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then…