Related papers: IndoToD: A Multi-Domain Indonesian Benchmark For E…
End-to-end (E2E) task-oriented dialogue (ToD) systems are prone to fall into the so-called "likelihood trap", resulting in generated responses which are dull, repetitive, and often inconsistent with dialogue history. Comparing ranked lists…
The training of task-oriented dialogue systems is often confronted with the lack of annotated data. In contrast to previous work which augments training data through expensive crowd-sourcing efforts, we propose four different automatic…
A commonly observed problem of the state-of-the-art natural language technologies, such as Amazon Alexa and Apple Siri, is that their services do not extend to most developing countries' citizens due to language barriers. Such populations…
The performance of a text-to-speech (TTS) synthesis model depends on various factors, of which the quality of the training data is of utmost importance. Millions of data are collected around the globe for various languages, but resources…
The development of Open-Domain Dialogue Systems (ODS)is a trending topic due to the large number of research challenges, large societal and business impact, and advances in the underlying technology. However, the development of these kinds…
Task-oriented dialogue systems are designed to achieve specific goals while conversing with humans. In practice, they may have to handle simultaneously several domains and tasks. The dialogue manager must therefore be able to take into…
In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback…
Recent model-based reference-free metrics for open-domain dialogue evaluation exhibit promising correlations with human judgment. However, they either perform turn-level evaluation or look at a single dialogue quality dimension. One would…
Despite the surging demands for multilingual task-oriented dialog systems (e.g., Alexa, Google Home), there has been less research done in multilingual or cross-lingual scenarios. Hence, we propose a zero-shot adaptation of task-oriented…
Modeling voices for multiple speakers and multiple languages in one text-to-speech system has been a challenge for a long time. This paper presents an extension on Tacotron2 to achieve bilingual multispeaker speech synthesis when there are…
Attention-based pre-trained language models such as GPT-2 brought considerable progress to end-to-end dialogue modelling. However, they also present considerable risks for task-oriented dialogue, such as lack of knowledge grounding or…
In Task Oriented Dialogue (TOD) system, detecting and inducing new intents are two main challenges to apply the system in the real world. In this paper, we suggest the semantic multi-view model to resolve these two challenges: (1) SBERT for…
Building Task-Oriented Dialogue (TOD) systems that generalize across different tasks remains a challenging problem. Data-driven approaches often struggle to transfer effectively to unseen tasks. While recent schema-based TOD frameworks…
Data availability is crucial for advancing artificial intelligence applications, including voice-based technologies. As content creation, particularly in social media, experiences increasing demand, translation and text-to-speech (TTS)…
Most task-oriented dialogue (TOD) benchmarks assume users that know exactly how to use the system by constraining the user behaviors within the system's capabilities via strict user goals, namely "user familiarity" bias. This data bias…
Goal oriented dialogue systems were originally designed as a natural language interface to a fixed data-set of entities that users might inquire about, further described by domain, slots, and values. As we move towards adaptable dialogue…
Despite advancements in on-topic dialogue systems, effectively managing topic shifts within dialogues remains a persistent challenge, largely attributed to the limited availability of training datasets. To address this issue, we propose…
Indonesian, spoken by over 200 million people, remains underserved in multimodal emotion recognition research despite its dominant presence on Southeast Asian social media platforms. We introduce IndoMER, the first multimodal emotion…
Tip-of-the-Tongue (ToT) retrieval benchmarks have largely focused on English, limiting their applicability to multilingual information access. In this work, we construct multilingual ToT test collections for Chinese, Japanese, Korean, and…
End-to-end design of dialogue systems has recently become a popular research topic thanks to powerful tools such as encoder-decoder architectures for sequence-to-sequence learning. Yet, most current approaches cast human-machine dialogue…