Related papers: Pre-Trained and Attention-Based Neural Networks fo…
Open-domain retrieval-based dialogue systems require a considerable amount of training data to learn their parameters. However, in practice, the negative samples of training data are usually selected from an unannotated conversation data…
This work investigates the task-oriented dialogue problem in mixed-domain settings. We study the effect of alternating between different domains in sequences of dialogue turns using two related state-of-the-art dialogue systems. We first…
Sequence-to-Sequence (seq2seq) models have become overwhelmingly popular in building end-to-end trainable dialogue systems. Though highly efficient in learning the backbone of human-computer communications, they suffer from the problem of…
Despite the rapid progress of open-domain generation-based conversational agents, most deployed systems treat dialogue contexts as single-turns, while systems dealing with multi-turn contexts are less studied. There is a lack of a reliable…
In multi-modal dialogue systems, it is important to allow the use of images as part of a multi-turn conversation. Training such dialogue systems generally requires a large-scale dataset consisting of multi-turn dialogues that involve…
Spoken Dialogue Models (SDMs) have advanced rapidly, yet their ability to sustain genuinely interactive multi-turn conversations remains underexplored, as most benchmarks focus on single-turn exchanges. We introduce Multi-Bench, the first…
Most uses of machine learning today involve training a model from scratch for a particular task, or sometimes starting with a model pretrained on a related task and then fine-tuning on a downstream task. Both approaches offer limited…
Recently, utilizing deep neural networks to build the opendomain dialogue models has become a hot topic. However, the responses generated by these models suffer from many problems such as responses not being contextualized and tend to…
We tackle the Dialogue Belief State Tracking(DST) problem of task-oriented conversational systems. Recent approaches to this problem leveraging Transformer-based models have yielded great results. However, training these models is…
Voice controlled applications can be a great aid to society, especially for physically challenged people. However this requires robustness to all kinds of variations in speech. A spoken language understanding system that learns from…
In this thesis, we leverage the neural copy mechanism and memory-augmented neural networks (MANNs) to address existing challenge of neural task-oriented dialogue learning. We show the effectiveness of our strategy by achieving good…
Most prior work in dialogue modeling has been on written conversations mostly because of existing data sets. However, written dialogues are not sufficient to fully capture the nature of spoken conversations as well as the potential speech…
Fine-tuning pretrained language models has shown promising results on a wide range of tasks, but when encountering a novel task, do they rely more on generic pretrained representation, or develop brand new task-specific solutions? Here, we…
We introduce a dialogue policy based on a transformer architecture, where the self-attention mechanism operates over the sequence of dialogue turns. Recent work has used hierarchical recurrent neural networks to encode multiple utterances…
Deep learning (DL) techniques have been used to support several code-related tasks such as code summarization and bug-fixing. In particular, pre-trained transformer models are on the rise, also thanks to the excellent results they achieved…
This paper investigates different pretraining approaches to spoken language identification. The paper is based on our submission to the Oriental Language Recognition 2021 Challenge. We participated in two tracks of the challenge:…
Recent years have seen significant advances in end-to-end (E2E) spoken language understanding (SLU) systems, which directly predict intents and slots from spoken audio. While dialogue history has been exploited to improve conventional…
The Dialog State Tracking Challenge 4 (DSTC 4) differentiates itself from the previous three editions as follows: the number of slot-value pairs present in the ontology is much larger, no spoken language understanding output is given, and…
There is an increasing demand for task-oriented dialogue systems which can assist users in various activities such as booking tickets and restaurant reservations. In order to complete dialogues effectively, dialogue policy plays a key role…
While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three…