Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task

Md Tahmid Rahman Laskar, Jimmy Xiangji Huang, Enamul Hoque


Abstract
Word embeddings that consider context have attracted great attention for various natural language processing tasks in recent years. In this paper, we utilize contextualized word embeddings with the transformer encoder for sentence similarity modeling in the answer selection task. We present two different approaches (feature-based and fine-tuning-based) for answer selection. In the feature-based approach, we utilize two types of contextualized embeddings, namely the Embeddings from Language Models (ELMo) and the Bidirectional Encoder Representations from Transformers (BERT) and integrate each of them with the transformer encoder. We find that integrating these contextual embeddings with the transformer encoder is effective to improve the performance of sentence similarity modeling. In the second approach, we fine-tune two pre-trained transformer encoder models for the answer selection task. Based on our experiments on six datasets, we find that the fine-tuning approach outperforms the feature-based approach on all of them. Among our fine-tuning-based models, the Robustly Optimized BERT Pretraining Approach (RoBERTa) model results in new state-of-the-art performance across five datasets.
Anthology ID:
2020.lrec-1.676
Volume:
Proceedings of the Twelfth Language Resources and Evaluation Conference
Month:
May
Year:
2020
Address:
Marseille, France
Editors:
Nicoletta Calzolari, Frédéric Béchet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, Hélène Mazo, Asuncion Moreno, Jan Odijk, Stelios Piperidis
Venue:
LREC
SIG:
Publisher:
European Language Resources Association
Note:
Pages:
5505–5514
Language:
English
URL:
https://aclanthology.org/2020.lrec-1.676
DOI:
Bibkey:
Cite (ACL):
Md Tahmid Rahman Laskar, Jimmy Xiangji Huang, and Enamul Hoque. 2020. Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task. In Proceedings of the Twelfth Language Resources and Evaluation Conference, pages 5505–5514, Marseille, France. European Language Resources Association.
Cite (Informal):
Contextualized Embeddings based Transformer Encoder for Sentence Similarity Modeling in Answer Selection Task (Laskar et al., LREC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.lrec-1.676.pdf