Building an Efficient and Effective Retrieval-based Dialogue System via
Mutual Learning
- URL: http://arxiv.org/abs/2110.00159v1
- Date: Fri, 1 Oct 2021 01:32:33 GMT
- Title: Building an Efficient and Effective Retrieval-based Dialogue System via
Mutual Learning
- Authors: Chongyang Tao, Jiazhan Feng, Chang Liu, Juntao Li, Xiubo Geng, Daxin
Jiang
- Abstract summary: We propose to combine the best of both worlds to build a retrieval system.
We employ a fast bi-encoder to replace the traditional feature-based pre-retrieval model.
We train the pre-retrieval model and the re-ranking model at the same time via mutual learning.
- Score: 27.04857039060308
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Establishing retrieval-based dialogue systems that can select appropriate
responses from the pre-built index has gained increasing attention from
researchers. For this task, the adoption of pre-trained language models (such
as BERT) has led to remarkable progress in a number of benchmarks. There exist
two common approaches, including cross-encoders which perform full attention
over the inputs, and bi-encoders that encode the context and response
separately. The former gives considerable improvements in accuracy but is often
inapplicable in practice for large-scale retrieval given the cost of the full
attention required for each sample at test time. The latter is efficient for
billions of indexes but suffers from sub-optimal performance. In this work, we
propose to combine the best of both worlds to build a retrieval system.
Specifically, we employ a fast bi-encoder to replace the traditional
feature-based pre-retrieval model (such as BM25) and set the response
re-ranking model as a more complicated architecture (such as cross-encoder). To
further improve the effectiveness of our framework, we train the pre-retrieval
model and the re-ranking model at the same time via mutual learning, which
enables two models to learn from each other throughout the training process. We
conduct experiments on two benchmarks and evaluation results demonstrate the
efficiency and effectiveness of our proposed framework.
Related papers
- Think-then-Act: A Dual-Angle Evaluated Retrieval-Augmented Generation [3.2134014920850364]
Large language models (LLMs) often face challenges such as temporal misalignment and generating hallucinatory content.
We propose a dual-angle evaluated retrieval-augmented generation framework textitThink-then-Act'
arXiv Detail & Related papers (2024-06-18T20:51:34Z) - Beyond Two-Tower Matching: Learning Sparse Retrievable
Cross-Interactions for Recommendation [80.19762472699814]
Two-tower models are a prevalent matching framework for recommendation, which have been widely deployed in industrial applications.
It suffers two main challenges, including limited feature interaction capability and reduced accuracy in online serving.
We propose a new matching paradigm named SparCode, which supports not only sophisticated feature interactions but also efficient retrieval.
arXiv Detail & Related papers (2023-11-30T03:13:36Z) - REINFOREST: Reinforcing Semantic Code Similarity for Cross-Lingual Code Search Models [11.78036105494679]
This paper introduces a novel code-to-code search technique that enhances the performance of Large Language Models (LLMs)
We present the first-ever code search method that encodes dynamic information during training without the need to execute either the corpus under search or the search query at inference time.
arXiv Detail & Related papers (2023-05-05T20:46:56Z) - CorpusBrain: Pre-train a Generative Retrieval Model for
Knowledge-Intensive Language Tasks [62.22920673080208]
Single-step generative model can dramatically simplify the search process and be optimized in end-to-end manner.
We name the pre-trained generative retrieval model as CorpusBrain as all information about the corpus is encoded in its parameters without the need of constructing additional index.
arXiv Detail & Related papers (2022-08-16T10:22:49Z) - Benchopt: Reproducible, efficient and collaborative optimization
benchmarks [67.29240500171532]
Benchopt is a framework to automate, reproduce and publish optimization benchmarks in machine learning.
Benchopt simplifies benchmarking for the community by providing an off-the-shelf tool for running, sharing and extending experiments.
arXiv Detail & Related papers (2022-06-27T16:19:24Z) - HyperImpute: Generalized Iterative Imputation with Automatic Model
Selection [77.86861638371926]
We propose a generalized iterative imputation framework for adaptively and automatically configuring column-wise models.
We provide a concrete implementation with out-of-the-box learners, simulators, and interfaces.
arXiv Detail & Related papers (2022-06-15T19:10:35Z) - Retrieve Fast, Rerank Smart: Cooperative and Joint Approaches for
Improved Cross-Modal Retrieval [80.35589927511667]
Current state-of-the-art approaches to cross-modal retrieval process text and visual input jointly, relying on Transformer-based architectures with cross-attention mechanisms that attend over all words and objects in an image.
We propose a novel fine-tuning framework which turns any pretrained text-image multi-modal model into an efficient retrieval model.
Our experiments on a series of standard cross-modal retrieval benchmarks in monolingual, multilingual, and zero-shot setups, demonstrate improved accuracy and huge efficiency benefits over the state-of-the-art cross-encoders.
arXiv Detail & Related papers (2021-03-22T15:08:06Z) - Few-Shot Named Entity Recognition: A Comprehensive Study [92.40991050806544]
We investigate three schemes to improve the model generalization ability for few-shot settings.
We perform empirical comparisons on 10 public NER datasets with various proportions of labeled data.
We create new state-of-the-art results on both few-shot and training-free settings.
arXiv Detail & Related papers (2020-12-29T23:43:16Z)
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.