paper-with-me

Papers

An Effective Domain Adaptive Post-Training Method for BERT in Response Selection

2019-08-13 · Taesun Whang, Dongyub Lee, Chanhee Lee, Kisu Yang, Dongsuk Oh, Heuiseok Lim

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). Experimental results show that our approach achieves new state-of-the-art on two response selection benchmarks (i.e., Ubuntu Corpus V1, Advising Corpus) performance improvement by 5.9% and 6% on R@1.

📄 PDF Abstract BibTeX arXiv:1908.04812

Code (1)

taesunwhang/BERT-ResSel pytorch

Tasks

Conversational Response SelectionLanguage ModelingLanguage ModellingRetrieval

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Position-Wise Feed-Forward Layer 설명 없음
Residual Connection 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Linear Warmup With Linear Decay Linear Warmup With Linear Decay is a learning rate schedule in which we increase the learning rate linearly for $n$ updates and then linearly decay afterwards.
Weight Decay 설명 없음
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Similar Papers 제목 키워드 기반

Domain-Specific Language Model Post-Training for Indonesian Financial NLP

2023-10-15 · Ni Putu Intan Maharani, Yoga Yustiawan, Fauzy Caesar Rochim, Ayu Purwarianti

BERT and IndoBERT have achieved impressive performance in several NLP tasks. There has been several investigation on its adaption in specialized domains especially for English language. We focus on financial domain and I…

Language ModelingLanguage ModellingSentiment AnalysisTopic Classification

ST-BERT: Cross-modal Language Model Pre-training For End-to-end Spoken Language Understanding

2020-10-23 · Minjeong Kim, Gyuwan Kim, Sang-Woo Lee, Jung-Woo Ha

Language model pre-training has shown promising results in various downstream tasks. In this context, we introduce a cross-modal pre-trained language model, called Speech-Text BERT (ST-BERT), to tackle end-to-end spoken …

cross-modal alignmentLanguage ModelingLanguage ModellingMasked Language Modeling+1

Domain-Adaptive Pretraining Methods for Dialogue Understanding

2021-05-28 · ACL 2021 5 · Han Wu, Kun Xu, Linfeng Song, Lifeng Jin 외

Language models like BERT and SpanBERT pretrained on open-domain data have obtained impressive gains on various NLP tasks. In this paper, we probe the effectiveness of domain-adaptive pretraining objectives on downstream…

Dialogue Understanding

A Robustly Optimized BERT Pre-training Approach with Post-training

2021-08-01 · CCL 2021 8 · Liu Zhuang, Lin Wayne, Shi Ya, Zhao Jun

“In the paper we present a ‘pre-training’+‘post-training’+‘fine-tuning’ three-stage paradigm which is a supplementary framework for the standard ‘pre-training’+‘fine-tuning’ languagemodel approach. Furthermore based on t…

Extractive Question-AnsweringQuestion Answering

MentalMARBERT: Domain-Adaptive Pre-training and Two-Stage Fine-Tuning for Arabic Mental Health Disorders Detection

2026-06-10 · Fatimah Almalki, Areej Alhothali, Lulwah Alharigy, Abdulrahman Aladeem arxiv

Detecting mental health disorders from Arabic social media text remains challenging due to dialectal variation, informal language, limited high-quality annotated resources, and severe class imbalance. While English menta…

Text Classification