Related papers: PiC: A Phrase-in-Context Dataset for Phrase Unders…
By design, word embeddings are unable to model the dynamic nature of words' semantics, i.e., the property of words to correspond to potentially different meanings. To address this limitation, dozens of specialized meaning representation…
State-of-the-art pretrained contextualized models (PCM) eg. BERT use tasks such as WiC and WSD to evaluate their word-in-context representations. This inherently assumes that performance in these tasks reflect how well a model represents…
There are many general purpose benchmark datasets for Semantic Textual Similarity but none of them are focused on technical concepts found in patents and scientific publications. This work aims to fill this gap by presenting a new human…
Sentence embedding is an important research topic in natural language processing. It is essential to generate a good embedding vector that fully reflects the semantic meaning of a sentence in order to achieve an enhanced performance for…
State of the art natural language processing tools are built on context-dependent word embeddings, but no direct method for evaluating these representations currently exists. Standard tasks and datasets for intrinsic evaluation of…
Semantic textual similarity is one of the open research challenges in the field of Natural Language Processing. Extensive research has been carried out in this field and near-perfect results are achieved by recent transformer-based models…
Both humans and machines learn the meaning of unknown words through contextual information in a sentence, but not all contexts are equally helpful for learning. We introduce an effective method for capturing the level of contextual…
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…
Current approaches to learning semantic representations of sentences often use prior word-level knowledge. The current study aims to leverage visual information in order to capture sentence level semantics without the need for word…
Contextualized embeddings are the preferred tool for modeling Lexical Semantic Change (LSC). Current evaluations typically focus on a specific task known as Graded Change Detection (GCD). However, performance comparison across work are…
Dense vector representations for sentences made significant progress in recent years as can be seen on sentence similarity tasks. Real-world phrase retrieval applications, on the other hand, still encounter challenges for effective use of…
We present models for embedding words in the context of surrounding words. Such models, which we refer to as token embeddings, represent the characteristics of a word that are specific to a given context, such as word sense, syntactic…
The ability to correctly model distinct meanings of a word is crucial for the effectiveness of semantic representation techniques. However, most existing evaluation benchmarks for assessing this criterion are tied to sense inventories…
In this paper, we focus on training and evaluating effective word embeddings with both text and visual information. More specifically, we introduce a large-scale dataset with 300 million sentences describing over 40 million images crawled…
Idiomatic expressions can be problematic for natural language processing applications as their meaning cannot be inferred from their constituting words. A lack of successful methodological approaches and sufficiently large datasets prevents…
Most words are ambiguous--i.e., they convey distinct meanings in different contexts--and even the meanings of unambiguous words are context-dependent. Both phenomena present a challenge for NLP. Recently, the advent of contextualized word…
Word sense disambiguation (WSD) methods identify the most suitable meaning of a word with respect to the usage of that word in a specific context. Neural network-based WSD approaches rely on a sense-annotated corpus since they do not…
Traditional semantic similarity models often fail to encapsulate the external context in which texts are situated. However, textual datasets generated on mobile platforms can help us build a truer representation of semantic similarity by…
While word embeddings are currently predominant for natural language processing, most of existing models learn them solely from their contexts. However, these context-based word embeddings are limited since not all words' meaning can be…
Cosine similarity is a widely used measure of the relatedness of pre-trained word embeddings, trained on a language modeling goal. Datasets such as WordSim-353 and SimLex-999 rate how similar words are according to human annotators, and as…