PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment

• URL: http://arxiv.org/abs/2212.08992v1
• Date: Sun, 18 Dec 2022 02:26:50 GMT
• Title: PoE: a Panel of Experts for Generalized Automatic Dialogue Assessment
• Authors: Chen Zhang, Luis Fernando D'Haro, Qiquan Zhang, Thomas Friedrichs, Haizhou Li
• Abstract summary: A model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. We propose a Panel of Experts (PoE) network that consists of a shared transformer encoder and a collection of lightweight adapters.
• Score: 58.46761798403072
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Chatbots are expected to be knowledgeable across multiple domains, e.g. for daily chit-chat, exchange of information, and grounding in emotional situations. To effectively measure the quality of such conversational agents, a model-based automatic dialogue evaluation metric (ADEM) is expected to perform well across multiple domains. Despite significant progress, an ADEM that works well in one domain does not necessarily generalize to another. This calls for a dedicated network architecture for domain generalization. To tackle the multi-domain dialogue evaluation task, we propose a Panel of Experts (PoE), a multitask network that consists of a shared transformer encoder and a collection of lightweight adapters. The shared encoder captures the general knowledge of dialogues across domains, while each adapter specializes in one specific domain and serves as a domain expert. To validate the idea, we construct a high-quality multi-domain dialogue dataset leveraging data augmentation and pseudo-labeling. The PoE network is comprehensively assessed on 16 dialogue evaluation datasets spanning a wide range of dialogue domains. It achieves state-of-the-art performance in terms of mean Spearman correlation over all the evaluation datasets. It exhibits better zero-shot generalization than existing state-of-the-art ADEMs and the ability to easily adapt to new domains with few-shot transfer learning.

Related papers

• Large-Scale Multi-Domain Recommendation: an Automatic Domain Feature Extraction and Personalized Integration Framework [30.46152832695426]
  We propose an Automatic Domain Feature Extraction and Personalized Integration (DFEI) framework for the large-scale multi-domain recommendation. The framework automatically transforms the behavior of each individual user into an aggregation of all user behaviors within the domain, which serves as the domain features. Experimental results on both public and industrial datasets, consisting of over 20 domains, clearly demonstrate that the proposed framework achieves significantly better performance compared with SOTA baselines.
  arXiv  Detail & Related papers  (2024-04-12T09:57:17Z)
• Role Prompting Guided Domain Adaptation with General Capability Preserve for Large Language Models [55.51408151807268]
  When tailored to specific domains, Large Language Models (LLMs) tend to experience catastrophic forgetting. crafting a versatile model for multiple domains simultaneously often results in a decline in overall performance. We present the RolE Prompting Guided Multi-Domain Adaptation (REGA) strategy.
  arXiv  Detail & Related papers  (2024-03-05T08:22:41Z)
• META: Mimicking Embedding via oThers' Aggregation for Generalizable Person Re-identification [68.39849081353704]
  Domain generalizable (DG) person re-identification (ReID) aims to test across unseen domains without access to the target domain data at training time. This paper presents a new approach called Mimicking Embedding via oThers' Aggregation (META) for DG ReID.
  arXiv  Detail & Related papers  (2021-12-16T08:06:50Z)
• MDD-Eval: Self-Training on Augmented Data for Multi-Domain Dialogue Evaluation [66.60285024216573]
  A dialogue evaluator is expected to conduct assessment across domains as well. Most of the state-of-the-art automatic dialogue evaluation metrics (ADMs) are not designed for multi-domain evaluation. We are motivated to design a general and robust framework, MDD-Eval, to address the problem.
  arXiv  Detail & Related papers  (2021-12-14T07:01:20Z)
• Meta-Context Transformers for Domain-Specific Response Generation [4.377737808397113]
  We present DSRNet, a transformer-based model for dialogue response generation by reinforcing domain-specific attributes. We study the use of DSRNet in a multi-turn multi-interlocutor environment for domain-specific response generation. Our model shows significant improvement over the state-of-the-art for multi-turn dialogue systems supported by better BLEU and semantic similarity (BertScore) scores.
  arXiv  Detail & Related papers  (2020-10-12T09:49:27Z)
• ConCET: Entity-Aware Topic Classification for Open-Domain Conversational Agents [9.870634472479571]
  We introduce ConCET: a Concurrent Entity-aware conversational Topic classifier. We propose a simple and effective method for generating synthetic training data. We evaluate ConCET on a large dataset of human-machine conversations with real users, collected as part of the Amazon Alexa Prize.
  arXiv  Detail & Related papers  (2020-05-28T06:29:08Z)
• UniConv: A Unified Conversational Neural Architecture for Multi-domain Task-oriented Dialogues [101.96097419995556]
  "UniConv" is a novel unified neural architecture for end-to-end conversational systems in task-oriented dialogues. We conduct comprehensive experiments in dialogue state tracking, context-to-text, and end-to-end settings on the MultiWOZ2.1 benchmark.
  arXiv  Detail & Related papers  (2020-04-29T16:28:22Z)
• Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog [70.79442700890843]
  We propose a novel Dynamic Fusion Network (DF-Net) which automatically exploit the relevance between the target domain and each domain. With little training data, we show its transferability by outperforming prior best model by 13.9% on average.
  arXiv  Detail & Related papers  (2020-04-23T08:17:22Z)
• MA-DST: Multi-Attention Based Scalable Dialog State Tracking [13.358314140896937]
  Dialog State Tracking dialog agents provide a natural language interface for users to complete their goal. To enable accurate multi-domain DST, the model needs to encode dependencies between past utterances and slot semantics. We introduce a novel architecture for this task to encode the conversation history and slot semantics.
  arXiv  Detail & Related papers  (2020-02-07T05:34:58Z)

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.