Related papers: Novel Word Embedding and Translation-based Languag…

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…

The representation space of pretrained Language Models (LMs) encodes rich information about words and their relationships (e.g., similarity, hypernymy, polysemy) as well as abstract semantic notions (e.g., intensity). In this paper, we…

Recent advances in cross-lingual word embeddings have primarily relied on mapping-based methods, which project pretrained word embeddings from different languages into a shared space through a linear transformation. However, these…

Word embedding is central to neural machine translation (NMT), which has attracted intensive research interest in recent years. In NMT, the source embedding plays the role of the entrance while the target embedding acts as the terminal.…

Most state-of-the-art approaches for named-entity recognition (NER) use semi supervised information in the form of word clusters and lexicons. Recently neural network-based language models have been explored, as they as a byproduct generate…

We propose Vec2Summ, a novel method for abstractive summarization that frames the task as semantic compression. Vec2Summ represents a document collection using a single mean vector in the semantic embedding space, capturing the central…

Word embeddings capture semantic relationships based on contextual information and are the basis for a wide variety of natural language processing applications. Notably these relationships are solely learned from the data and subsequently…

We propose two novel model architectures for computing continuous vector representations of words from very large data sets. The quality of these representations is measured in a word similarity task, and the results are compared to the…

Semantic representations of words have been successfully extracted from unlabeled corpuses using neural network models like word2vec. These representations are generally high quality and are computationally inexpensive to train, making them…

We address the problem of tuning word embeddings for specific use cases and domains. We propose a new method that automatically combines multiple domain-specific embeddings, selected from a wide range of pre-trained domain-specific…

Word embedding is designed to represent the semantic meaning of a word with low dimensional vectors. The state-of-the-art methods of learning word embeddings (word2vec and GloVe) only use the word co-occurrence information. The learned…

While word embeddings have been shown to implicitly encode various forms of attributional knowledge, the extent to which they capture relational information is far more limited. In previous work, this limitation has been addressed by…

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…

Traditional neural word embeddings are usually dependent on a richer diversity of vocabulary. However, the language models recline to cover major vocabularies via the word embedding parameters, in particular, for multilingual language…

In many modern day systems such as information extraction and knowledge management agents, ontologies play a vital role in maintaining the concept hierarchies of the selected domain. However, ontology population has become a problematic…

The recent tremendous success of unsupervised word embeddings in a multitude of applications raises the obvious question if similar methods could be derived to improve embeddings (i.e. semantic representations) of word sequences as well. We…

Search behaviour is characterised using synonymy and polysemy as users often want to search information based on meaning. Semantic representation strategies represent a move towards richer associative connections that can adequately capture…

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…

In recent years, machine learning has been widely adopted to automate the audio mixing process. Automatic mixing systems have been applied to various audio effects such as gain-adjustment, equalization, and reverberation. These systems can…

Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval. However, the non-linear structures present inside the networks make these models largely inscrutable. A significant…