A comprehensive solution to retrieval-based chatbot construction

• URL: http://arxiv.org/abs/2106.06139v1
• Date: Fri, 11 Jun 2021 02:54:33 GMT
• Title: A comprehensive solution to retrieval-based chatbot construction
• Authors: Kristen Moore, Shenjun Zhong, Zhen He, Torsten Rudolf, Nils Fisher, Brandon Victor, Neha Jindal
• Abstract summary: We present an end-to-end set of solutions to take the reader from an unlabelled chatlogs to a deployed chatbots. This set of solutions includes creating a self-supervised dataset and a weakly labelled dataset from chatlogs, as well as a systematic approach to selecting a fixed list of canned responses. We find that using a self-supervised contrastive learning model outperforms training the binary and multi-class classification models on a weakly labelled dataset.
• Score: 4.807955518532493
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research papers in this area where the focus is on solving just one component of a deployable chatbot, we present an end-to-end set of solutions to take the reader from an unlabelled chatlogs to a deployed chatbot. This set of solutions includes creating a self-supervised dataset and a weakly labelled dataset from chatlogs, as well as a systematic approach to selecting a fixed list of canned responses. We present a hierarchical-based RNN architecture for the response selection model, chosen for its ability to cache intermediate utterance embeddings, which helped to meet deployment inference speed requirements. We compare the performance of this architecture across 3 different learning objectives: self-supervised contrastive learning, binary classification, and multi-class classification. We find that using a self-supervised contrastive learning model outperforms training the binary and multi-class classification models on a weakly labelled dataset. Our results validate that the self-supervised contrastive learning approach can be effectively used for a real-world chatbot scenario.

Related papers

• The OCON model: an old but gold solution for distributable supervised classification [0.28675177318965045]
  This paper introduces a structured application of the One-Class approach and the One-Class-One-Network model for supervised classification tasks. We achieve classification accuracy comparable to nowadays complex architectures (90.0 - 93.7%)
  arXiv  Detail & Related papers  (2024-10-05T09:15:01Z)
• An efficient domain-independent approach for supervised keyphrase extraction and ranking [0.03626013617212666]
  We present a supervised learning approach for automatic extraction of keyphrases from single documents. Our solution uses simple to compute statistical and positional features of candidate phrases. Evaluation on benchmark datasets shows that our approach achieves significantly higher accuracy than several state-of-the-art baseline models.
  arXiv  Detail & Related papers  (2024-03-24T08:33:27Z)
• ALBench: A Framework for Evaluating Active Learning in Object Detection [102.81795062493536]
  This paper contributes an active learning benchmark framework named as ALBench for evaluating active learning in object detection. Developed on an automatic deep model training system, this ALBench framework is easy-to-use, compatible with different active learning algorithms, and ensures the same training and testing protocols.
  arXiv  Detail & Related papers  (2022-07-27T07:46:23Z)
• Systematic Training and Testing for Machine Learning Using Combinatorial Interaction Testing [0.0]
  This paper demonstrates the systematic use of coverage for selecting and characterizing test and training sets for machine learning models. The paper addresses prior criticism of coverage and provides a rebuttal which advocates the use of coverage metrics in machine learning applications.
  arXiv  Detail & Related papers  (2022-01-28T21:33:31Z)
• Multimodal Clustering Networks for Self-supervised Learning from Unlabeled Videos [69.61522804742427]
  This paper proposes a self-supervised training framework that learns a common multimodal embedding space. We extend the concept of instance-level contrastive learning with a multimodal clustering step to capture semantic similarities across modalities. The resulting embedding space enables retrieval of samples across all modalities, even from unseen datasets and different domains.
  arXiv  Detail & Related papers  (2021-04-26T15:55:01Z)
• Conversational Query Rewriting with Self-supervised Learning [36.392717968127016]
  Conversational Query Rewriting (CQR) aims to simplify the multi-turn dialogue modeling into a single-turn problem by explicitly rewriting the conversational query into a self-contained utterance. Existing approaches rely on massive supervised training data, which is labor-intensive to annotate. We propose to construct a large-scale CQR dataset automatically via self-supervised learning, which does not need human annotation.
  arXiv  Detail & Related papers  (2021-02-09T08:57:53Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)
• Enhancing Dialogue Generation via Multi-Level Contrastive Learning [57.005432249952406]
  We propose a multi-level contrastive learning paradigm to model the fine-grained quality of the responses with respect to the query. A Rank-aware (RC) network is designed to construct the multi-level contrastive optimization objectives. We build a Knowledge Inference (KI) component to capture the keyword knowledge from the reference during training and exploit such information to encourage the generation of informative words.
  arXiv  Detail & Related papers  (2020-09-19T02:41:04Z)
• Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues [88.73739515457116]
  We introduce four self-supervised tasks including next session prediction, utterance restoration, incoherence detection and consistency discrimination. We jointly train the PLM-based response selection model with these auxiliary tasks in a multi-task manner. Experiment results indicate that the proposed auxiliary self-supervised tasks bring significant improvement for multi-turn response selection.
  arXiv  Detail & Related papers  (2020-09-14T08:44:46Z)
• The World is Not Binary: Learning to Rank with Grayscale Data for Dialogue Response Selection [55.390442067381755]
  We show that grayscale data can be automatically constructed without human effort. Our method employs off-the-shelf response retrieval models and response generation models as automatic grayscale data generators. Experiments on three benchmark datasets and four state-of-the-art matching models show that the proposed approach brings significant and consistent performance improvements.
  arXiv  Detail & Related papers  (2020-04-06T06:34:54Z)

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.