Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills

• URL: http://arxiv.org/abs/2004.08449v1
• Date: Fri, 17 Apr 2020 20:51:40 GMT
• Title: Can You Put it All Together: Evaluating Conversational Agents' Ability to Blend Skills
• Authors: Eric Michael Smith, Mary Williamson, Kurt Shuster, Jason Weston, Y-Lan Boureau
• Abstract summary: We investigate ways to combine models trained towards isolated capabilities. We propose a new dataset, BlendedSkillTalk, to analyze how these capabilities would mesh together in a natural conversation. Our experiments show that multi-tasking over several tasks that focus on particular capabilities results in better blended conversation performance.
• Score: 31.42833993937429
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Being engaging, knowledgeable, and empathetic are all desirable general qualities in a conversational agent. Previous work has introduced tasks and datasets that aim to help agents to learn those qualities in isolation and gauge how well they can express them. But rather than being specialized in one single quality, a good open-domain conversational agent should be able to seamlessly blend them all into one cohesive conversational flow. In this work, we investigate several ways to combine models trained towards isolated capabilities, ranging from simple model aggregation schemes that require minimal additional training, to various forms of multi-task training that encompass several skills at all training stages. We further propose a new dataset, BlendedSkillTalk, to analyze how these capabilities would mesh together in a natural conversation, and compare the performance of different architectures and training schemes. Our experiments show that multi-tasking over several tasks that focus on particular capabilities results in better blended conversation performance compared to models trained on a single skill, and that both unified or two-stage approaches perform well if they are constructed to avoid unwanted bias in skill selection or are fine-tuned on our new task.

Related papers

• Musketeer: Joint Training for Multi-task Vision Language Model with Task Explanation Prompts [75.75548749888029]
  We present a vision-language model whose parameters are jointly trained on all tasks and fully shared among multiple heterogeneous tasks. With a single model, Musketeer achieves results comparable to or better than strong baselines trained on single tasks, almost uniformly across multiple tasks.
  arXiv  Detail & Related papers  (2023-05-11T17:57:49Z)
• Friend-training: Learning from Models of Different but Related Tasks [44.25961408685873]
  Friend-training is a cross-task self-training framework. Models trained to do different tasks are used in an iterative training, pseudo-labeling, and retraining process. We show that the models trained with the friend-training framework achieve the best performance compared to strong baselines.
  arXiv  Detail & Related papers  (2023-01-31T15:00:56Z)
• Learning Options via Compression [62.55893046218824]
  We propose a new objective that combines the maximum likelihood objective with a penalty on the description length of the skills. Our objective learns skills that solve downstream tasks in fewer samples compared to skills learned from only maximizing likelihood.
  arXiv  Detail & Related papers  (2022-12-08T22:34:59Z)
• Modular Adaptive Policy Selection for Multi-Task Imitation Learning through Task Division [60.232542918414985]
  Multi-task learning often suffers from negative transfer, sharing information that should be task-specific. This is done by using proto-policies as modules to divide the tasks into simple sub-behaviours that can be shared. We also demonstrate its ability to autonomously divide the tasks into both shared and task-specific sub-behaviours.
  arXiv  Detail & Related papers  (2022-03-28T15:53:17Z)
• Combining Modular Skills in Multitask Learning [149.8001096811708]
  A modular design encourages neural models to disentangle and recombine different facets of knowledge to generalise more systematically to new tasks. In this work, we assume each task is associated with a subset of latent discrete skills from a (potentially small) inventory. We find that the modular design of a network significantly increases sample efficiency in reinforcement learning and few-shot generalisation in supervised learning.
  arXiv  Detail & Related papers  (2022-02-28T16:07:19Z)
• Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks [73.63892022944198]
  We present a generic perception architecture named Uni-Perceiver. It processes a variety of modalities and tasks with unified modeling and shared parameters. Results show that our pre-trained model without any tuning can achieve reasonable performance even on novel tasks.
  arXiv  Detail & Related papers  (2021-12-02T18:59:50Z)
• Towards More Generalizable One-shot Visual Imitation Learning [81.09074706236858]
  A general-purpose robot should be able to master a wide range of tasks and quickly learn a novel one by leveraging past experiences. One-shot imitation learning (OSIL) approaches this goal by training an agent with (pairs of) expert demonstrations. We push for a higher level of generalization ability by investigating a more ambitious multi-task setup.
  arXiv  Detail & Related papers  (2021-10-26T05:49:46Z)
• Boosting a Model Zoo for Multi-Task and Continual Learning [15.110807414130923]
  "Model Zoo" is an algorithm that builds an ensemble of models, each of which is very small, and it is trained on a smaller set of tasks. Model Zoo achieves large gains in prediction accuracy compared to state-of-the-art methods in multi-task and continual learning.
  arXiv  Detail & Related papers  (2021-06-06T04:25:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.