Related papers: Inducing Multilingual Text Analysis Tools Using Bi…

Named-entities are inherently multilingual, and annotations in any given language may be limited. This motivates us to consider polyglot named-entity recognition (NER), where one model is trained using annotated data drawn from more than…

Multilingual generative models obtain remarkable cross-lingual in-context learning capabilities through pre-training on large-scale corpora. However, they still exhibit a performance bias toward high-resource languages and learn isolated…

Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image. While…

Relation extraction (RE) seeks to detect and classify semantic relationships between entities, which provides useful information for many NLP applications. Since the state-of-the-art RE models require large amounts of manually annotated…

Existing zero-shot cross-lingual transfer methods rely on parallel corpora or bilingual dictionaries, which are expensive and impractical for low-resource languages. To disengage from these dependencies, researchers have explored training…

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…

Scaling multilingual representation learning beyond the hundred most frequent languages is challenging, in particular to cover the long tail of low-resource languages. A promising approach has been to train one-for-all multilingual models…

Convolutional neural network (CNN) and recurrent neural network (RNN) are two popular architectures used in text classification. Traditional methods to combine the strengths of the two networks rely on streamlining them or concatenating…

Recurrent neural networks (RNN) are the backbone of many text and speech applications. These architectures are typically made up of several computationally complex components such as; non-linear activation functions, normalization,…

Statistical language models are central to many applications that use semantics. Recurrent Neural Networks (RNN) are known to produce state of the art results for language modelling, outperforming their traditional n-gram counterparts in…

In this paper, we present our first attempts in building a multilingual Neural Machine Translation framework under a unified approach. We are then able to employ attention-based NMT for many-to-many multilingual translation tasks. Our…

Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to…

In the context of neural machine translation, data augmentation (DA) techniques may be used for generating additional training samples when the available parallel data are scarce. Many DA approaches aim at expanding the support of the…

Intent detection and slot filling are two main tasks for building a spoken language understanding(SLU) system. Multiple deep learning based models have demonstrated good results on these tasks . The most effective algorithms are based on…

Named Entity Recognition (NER) is a fundamental problem in natural language processing (NLP). However, the task of extracting longer entity spans (e.g., awards) from extended texts (e.g., homepages) is barely explored. Current NER methods…

Establishing retrieval-based dialogue systems that can select appropriate responses from the pre-built index has gained increasing attention from researchers. For this task, the adoption of pre-trained language models (such as BERT) has led…

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection,…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Binary Neural Networks (BNNs) show great promise for real-world embedded devices. As one of the critical steps to achieve a powerful BNN, the scale factor calculation plays an essential role in reducing the performance gap to their…

For endangered languages, data collection campaigns have to accommodate the challenge that many of them are from oral tradition, and producing transcriptions is costly. Therefore, it is fundamental to translate them into a widely spoken…