Related papers: Encoding Syntactic Knowledge in Transformer Encode…

We consider the design of two-pass voice trigger detection systems. We focus on the networks in the second pass that are used to re-score candidate segments obtained from the first-pass. Our baseline is an acoustic model(AM), with BiLSTM…

Despite its original goal to jointly learn to align and translate, prior researches suggest that Transformer captures poor word alignments through its attention mechanism. In this paper, we show that attention weights DO capture accurate…

In conventional target tracking systems, human operators use the estimated target tracks to make higher level inference of the target behaviour/intent. This paper develops syntactic filtering algorithms that assist human operators by…

Recent advances in End-to-End (E2E) Spoken Language Understanding (SLU) have been primarily due to effective pretraining of speech representations. One such pretraining paradigm is the distillation of semantic knowledge from…

While different neural models often exhibit latent spaces that are alike when exposed to semantically related data, this intrinsic similarity is not always immediately discernible. Towards a better understanding of this phenomenon, our work…

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…

Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transformer Construction (ETC), that addresses two key challenges of…

Recently, the attention-enhanced multi-layer encoder, such as Transformer, has been extensively studied in Machine Reading Comprehension (MRC). To predict the answer, it is common practice to employ a predictor to draw information only from…

Detecting and identifying user intent from text, both written and spoken, plays an important role in modelling and understand dialogs. Existing research for intent discovery model it as a classification task with a predefined set of known…

Recent graph-based models for joint multiple intent detection and slot filling have obtained promising results through modeling the guidance from the prediction of intents to the decoding of slot filling. However, existing methods (1) only…

The self-attention module is a key component of Transformer-based models, wherein each token pays attention to every other token. Recent studies have shown that these heads exhibit syntactic, semantic, or local behaviour. Some studies have…

Natural language understanding typically maps single utterances to a dual level semantic frame, sentence level intent and slot labels at the word level. The best performing models force explicit interaction between intent detection and slot…

With the advent of conversational assistants, like Amazon Alexa, Google Now, etc., dialogue systems are gaining a lot of traction, especially in industrial setting. These systems typically consist of Spoken Language understanding component…

We propose an attention-based approach for multimodal image patch matching using a Transformer encoder attending to the feature maps of a multiscale Siamese CNN. Our encoder is shown to efficiently aggregate multiscale image embeddings…

Neural sequence-to-sequence networks with attention have achieved remarkable performance for machine translation. One of the reasons for their effectiveness is their ability to capture relevant source-side contextual information at each…

Comprehending the overall intent of an utterance helps a listener recognize the individual words spoken. Inspired by this fact, we perform a novel study of the impact of explicitly incorporating intent representations as additional…

Natural language understanding includes the tasks of intent detection (identifying a user's objectives) and slot filling (extracting the entities relevant to those objectives). Prior slot filling methods assume that each intent type cannot…

This paper investigates automatic piano transcription based on computationally-efficient yet high-performant variants of the Transformer that can capture longer-term dependency over the whole musical piece. Recently, transformer-based…

In this paper, we propose an efficient and accurate streaming speech recognition model based on the FastConformer architecture. We adapted the FastConformer architecture for streaming applications through: (1) constraining both the…

Existing methods enhance the training of detection transformers by incorporating an auxiliary one-to-many assignment. In this work, we treat the model as a multi-task framework, simultaneously performing one-to-one and one-to-many…