Domain Adaptive Training BERT for Response Selection
By Taesun Whang, Dongyub Lee, Chanhee Lee, Kisu Yang, Dongsuk Oh, Heuiseok Lim. 2019
26 citations recorded by the source corpus.
We focus on multi-turn response selection in a retrieval-based dialog system. In this paper, we utilize the powerful pre-trained language model Bi-directional Encoder Representations from Transformer (BERT) for a multi-turn dialog system and propose a highly effective post-training method on domain-specific corpus. Although BERT is easily adopted to various NLP tasks and outperforms previous baselines of each task, it still has limitations if a task corpus is too focused on a certain domain. Post-training on domain-specific corpus (e.g., Ubuntu Corpus) helps the model to train contextualized representations and words that do not appear in general corpus (e.g.,English Wikipedia). Experiment results show that our approach achieves new state-of-the-art on two response selection benchmark datasets (i.e.,Ubuntu Corpus V1, Advising Corpus) performance improvement by 5.9% and 6% on Recall@1.
Subfields: Natural Language Processing, Dialogue & Conversational AI
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Natural Language Processing
In Dialogue & Conversational AI
Citations in the corpus
- VD-BERT: A Unified Vision and Dialog Transformer with BERT (2020, methodology): “Concretely, we sample an answer ˆ A t from the candidate pool and append it to the input sequence, and ask the NSP head to distinguish whether the sampled answer is correct or not.”
- MuTual: A Dataset for Multi-Turn Dialogue Reasoning (2020, methodology): “BERT (Devlin et al., 2019): Pre-training models have shown promising results on various multi-choice and reasoning tasks (Whang et al., 2019; Xu et al., 2019).”