Interactive Learning of Hierarchical Tasks from Dialog with GPT

2023-05-17 · Lane Lawley, Christopher J. MacLellan

We present a system for interpretable, symbolic, interactive task learning from dialog using a GPT model as a conversational front-end. The learned tasks are represented as hierarchical decompositions of predicate-argument structures with scoped variable arguments. By using a GPT model to convert interactive dialog into a semantic representation, and then recursively asking for definitions of unknown steps, we show that hierarchical task knowledge can be acquired and re-used in a natural and unrestrained conversational environment. We compare our system to a similar architecture using a more conventional parser and show that our system tolerates a much wider variety of linguistic variance.

📄 PDF Abstract BibTeX arXiv:2305.10349

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음

Attention 설명 없음

Cosine Annealing Cosine Annealing is a type of learning rate schedule that has the effect of starting with a large learning rate that is relatively rapidly decreased to a minimum value before…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Adam 설명 없음

Linear Warmup With Cosine Annealing Linear Warmup With Cosine Annealing is a learning rate schedule where we increase the learning rate linearly for $n$ updates and then anneal according to a cosine schedule…

Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…

Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…

MULTI-Bench: A Multi-Turn Interactive Benchmark for Assessing Emotional Intelligence ability of Spoken Dialogue Models

2025-11-02 · Yayue Deng, Guoqiang Hu, Haiyang Sun, Xiangyu Zhang 외 arxiv

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 Mult…

Emotional Intelligence Emotion Recognition

Incorporating Dual-Aware with Hierarchical Interactive Memory Networks for Task-Oriented Dialogue

2021-11-16 · ACL ARR November 2021 11 · Anonymous

Recent years, end-to-end task-oriented dialogue systems have made a remarkable breakthrough. However, existing dialogue models tend to equally summarize all the history as the context representation and apply memory netw…

Task-Oriented Dialogue Systems

Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems

2019-06-21 · NeurIPS 2019 12 · Asma Ghandeharioun, Judy Hanwen Shen, Natasha Jaques, Craig Ferguson 외

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context.…

Dialogue Evaluation Knowledge Distillation Open-Domain Dialog

Overview of the Ninth Dialog System Technology Challenge: DSTC9

2020-11-12 · Chulaka Gunasekara, Seokhwan Kim, Luis Fernando D'Haro, Abhinav Rastogi 외

This paper introduces the Ninth Dialog System Technology Challenge (DSTC-9). This edition of the DSTC focuses on applying end-to-end dialog technologies for four distinct tasks in dialog systems, namely, 1. Task-oriented…

Interactive Evaluation of Dialog

Interactive Evaluation of Dialog Track at DSTC9

2022-07-28 · LREC 2022 6 · Shikib Mehri, Yulan Feng, Carla Gordon, Seyed Hossein Alavi 외

The ultimate goal of dialog research is to develop systems that can be effectively used in interactive settings by real users. To this end, we introduced the Interactive Evaluation of Dialog Track at the 9th Dialog Syste…

Interactive Evaluation of Dialog Open-Domain Dialog Response Generation