Related papers: Subword Semantic Hashing for Intent Classification…
Word embeddings typically represent different meanings of a word in a single conflated vector. Empirical analysis of embeddings of ambiguous words is currently limited by the small size of manually annotated resources and by the fact that…
Numerous embedding models have been recently explored to incorporate semantic knowledge into visual recognition. Existing methods typically focus on minimizing the distance between the corresponding images and texts in the embedding space…
Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed…
Semantically meaningful sentence embeddings are important for numerous tasks in natural language processing. To obtain such embeddings, recent studies explored the idea of utilizing synthetically generated data from pretrained language…
Intent detection is a text classification task whose aim is to recognize and label the semantics behind a users query. It plays a critical role in various business applications. The output of the intent detection module strongly conditions…
Intelligence Quotient (IQ) Test is a set of standardized questions designed to evaluate human intelligence. Verbal comprehension questions appear very frequently in IQ tests, which measure human's verbal ability including the understanding…
Being able to recognize words as slots and detect the intent of an utterance has been a keen issue in natural language understanding. The existing works either treat slot filling and intent detection separately in a pipeline manner, or…
Word embeddings capture syntactic and semantic information about words. Definition modeling aims to make the semantic content in each embedding explicit, by outputting a natural language definition based on the embedding. However, existing…
The surge of social media use brings huge demand of multilingual sentiment analysis (MSA) for unveiling cultural difference. So far, traditional methods resorted to machine translation---translating texts in other languages to English, and…
Understanding search queries is critical for shopping search engines to deliver a satisfying customer experience. Popular shopping search engines receive billions of unique queries yearly, each of which can depict any of hundreds of user…
Domestic Violence against women is now recognized to be a serious and widespread problem worldwide. Domestic Violence and Abuse is at the root of so many issues in society and considered as the societal tabooed topic. Fortunately, with the…
The vocabulary mismatch problem is a long-standing problem in information retrieval. Semantic matching holds the promise of solving the problem. Recent advances in language technology have given rise to unsupervised neural models for…
Current neural network-based methods to the problem of document summarisation struggle when applied to datasets containing large inputs. In this paper we propose a new approach to the challenge of content-selection when dealing with…
Supervised learning methods can solve the given problem in the presence of a large set of labeled data. However, the acquisition of a dataset covering all the target classes typically requires manual labeling which is expensive and…
Efficient label acquisition processes are key to obtaining robust classifiers. However, data labeling is often challenging and subject to high levels of label noise. This can arise even when classification targets are well defined, if…
We present hash embeddings, an efficient method for representing words in a continuous vector form. A hash embedding may be seen as an interpolation between a standard word embedding and a word embedding created using a random hash function…
Semantic sentence embeddings are usually supervisedly built minimizing distances between pairs of embeddings of sentences labelled as semantically similar by annotators. Since big labelled datasets are rare, in particular for non-English…
Almost all existing deep learning approaches for semantic segmentation tackle this task as a pixel-wise classification problem. Yet humans understand a scene not in terms of pixels, but by decomposing it into perceptual groups and…
Learning to recognize new keywords with just a few examples is essential for personalizing keyword spotting (KWS) models to a user's choice of keywords. However, modern KWS models are typically trained on large datasets and restricted to a…
In this paper, we aim to address the challenging task of semantic matching where matching ambiguity is difficult to resolve even with learned deep features. We tackle this problem by taking into account the confidence in predictions and…