Neural Assistant: Joint Action Prediction, Response Generation, and Latent Knowledge Reasoning

By Arvind Neelakantan, Semih Yavuz, Sharan Narang, V. Prasad, Prasanna Parthasarathi, Ben Goodrich, Daniel Duckworth, Chinnadhurai Sankar, Xifeng Yan. 2019

15 citations recorded by the source corpus.

Task-oriented dialog presents a difficult challenge encompassing multiple problems including multi-turn language understanding and generation, knowledge retrieval and reasoning, and action prediction. Modern dialog systems typically begin by converting conversation history to a symbolic object referred to as belief state by using supervised learning. The belief state is then used to reason on an external knowledge source whose result along with the conversation history is used in action prediction and response generation tasks independently. Such a pipeline of individually optimized components not only makes the development process cumbersome but also makes it non-trivial to leverage session-level user reinforcement signals. In this paper, we develop Neural Assistant: a single neural network model that takes conversation history and an external knowledge source as input and jointly produces both text response and action to be taken by the system as output. The model learns to reason on the provided knowledge source with weak supervision signal coming from the text generation and the action prediction tasks, hence removing the need for belief state annotations. In the MultiWOZ dataset, we study the effect of distant supervision, and the size of knowledge base on model performance. We find that the Neural Assistant without belief states is able to incorporate external knowledge information achieving higher factual accuracy scores compared to Transformer. In settings comparable to reported baseline systems, Neural Assistant when provided with oracle belief state significantly improves language generation performance.

Subfields: Natural Language Processing, LLM Agents & Tool Use

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Natural Language Processing

In LLM Agents & Tool Use

Citations in the corpus

A Simple Language Model for Task-Oriented Dialogue (2020, background): “[33] modeled dialogue management and response generation jointly, incorporating latent knowledge reasoning through attention without using belief states.”
Learning Knowledge Bases with Parameters for Task-Oriented Dialogue Systems (2020, methodology): “, 2019), end-to-end models struggle when the input becomes too large (Neelakantan et al., 2019).”
Task-Oriented Dialogue as Dataflow Synthesis (2020, background): “Neelakantan et al. (2019) report greater success on a generation-focused task, and promising results have also been obtained from hybrid neuro-symbolic dialogue systems (Zhao and Eske-nazi, 2016; Williams et al., 2017; Wen et al., 2017; Gao et al., 2019).”
BiToD: A Bilingual Multi-Domain Dataset For Task-Oriented Dialogue Modeling (2021, background): “[8] Arvind Neelakantan, Semih Yavuz, Sharan Narang, Vishaal Prasad, Ben Goodrich, Daniel 350 Duckworth, Chinnadhurai Sankar, and Xifeng Yan.”
MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems (2020, background): “To simplify the system design and reduce human supervision, several end-to-end trainable systems have been proposed (Bordes et al., 2016; Wen et al., 2017; Lei et al., 2018; Neelakantan et al., 2019; Eric and Manning, 2017; Eric et al., 2017; Madotto et al., 2018).”