Goal-Oriented Multi-Task BERT-Based Dialogue State Tracker

2020-02-05 · Pavel Gulyaev, Eugenia Elistratova, Vasily Konovalov, Yuri Kuratov, Leonid Pugachev, Mikhail Burtsev

Dialogue State Tracking (DST) is a core component of virtual assistants such as Alexa or Siri. To accomplish various tasks, these assistants need to support an increasing number of services and APIs. The Schema-Guided State Tracking track of the 8th Dialogue System Technology Challenge highlighted the DST problem for unseen services. The organizers introduced the Schema-Guided Dialogue (SGD) dataset with multi-domain conversations and released a zero-shot dialogue state tracking model. In this work, we propose a GOaL-Oriented Multi-task BERT-based dialogue state tracker (GOLOMB) inspired by architectures for reading comprehension question answering systems. The model "queries" dialogue history with descriptions of slots and services as well as possible values of slots. This allows to transfer slot values in multi-domain dialogues and have a capability to scale to unseen slot types. Our model achieves a joint goal accuracy of 53.97% on the SGD dataset, outperforming the baseline model.

📄 PDF Abstract BibTeX arXiv:2002.02450

Code (0)

등록된 구현이 없습니다.

Tasks

Dialogue State Tracking Question Answering Reading Comprehension

Methods 이 논문이 사용한 방법론

DST Dynamic sparse training methods train neural networks in a sparse manner, starting with an initial sparse mask, and periodically updating the mask based on some criteria.

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Algorithms for automatic intents extraction and utterances classification for goal-oriented dialogue systems

2023-12-15 · Leonid Legashev, Alexander Shukhman, Vadim Badikov

Modern machine learning techniques in the natural language processing domain can be used to automatically generate scripts for goal-oriented dialogue systems. The current article presents a general framework for studying…

Goal-Oriented Dialogue Systems

DialoGLUE: A Natural Language Understanding Benchmark for Task-Oriented Dialogue

2020-09-28 · Shikib Mehri, Mihail Eric, Dilek Hakkani-Tur

A long-standing goal of task-oriented dialogue research is the ability to flexibly adapt dialogue models to new domains. To progress research in this direction, we introduce DialoGLUE (Dialogue Language Understanding Eva…

Domain Adaptation Multi-domain Dialogue State Tracking Natural Language Understanding

TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue

2020-04-15 · EMNLP 2020 11 · Chien-Sheng Wu, Steven Hoi, Richard Socher, Caiming Xiong

The underlying difference of linguistic patterns between general text and task-oriented dialogue makes existing pre-trained language models less useful in practice. In this work, we unify nine human-human and multi-turn …

Dialogue State Tracking Intent Detection Language Modeling Language Modelling+2

Grounding Dialogue Systems via Knowledge Graph Aware Decoding with Pre-trained Transformers

2021-03-30 · Debanjan Chaudhuri, Md Rashad Al Hasan Rony, Jens Lehmann

Generating knowledge grounded responses in both goal and non-goal oriented dialogue systems is an important research challenge. Knowledge Graphs (KG) can be viewed as an abstraction of the real world, which can potential…

Dialogue Generation Goal-Oriented Dialogue Systems Knowledge Graphs Response Generation

Ontology-Enhanced Slot Filling

2021-08-25 · Yuhao Ding, Yik-Cheung Tam

Slot filling is a fundamental task in dialog state tracking in task-oriented dialog systems. In multi-domain task-oriented dialog system, user utterances and system responses may mention multiple named entities and attri…

dialog state tracking GPU slot-filling Slot Filling