Hiroki Iida


2022

pdf bib
Unsupervised Domain Adaptation for Sparse Retrieval by Filling Vocabulary and Word Frequency Gaps
Hiroki Iida | Naoaki Okazaki
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

IR models using a pretrained language model significantly outperform lexical approaches like BM25. In particular, SPLADE, which encodes texts to sparse vectors, is an effective model for practical use because it shows robustness to out-of-domain datasets. However, SPLADE still struggles with exact matching of low-frequency words in training data. In addition, domain shifts in vocabulary and word frequencies deteriorate the IR performance of SPLADE. Because supervision data are scarce in the target domain, addressing the domain shifts without supervision data is necessary. This paper proposes an unsupervised domain adaptation method by filling vocabulary and word-frequency gaps. First, we expand a vocabulary and execute continual pretraining with a masked language model on a corpus of the target domain. Then, we multiply SPLADE-encoded sparse vectors by inverse document frequency weights to consider the importance of documents with low-frequency words. We conducted experiments using our method on datasets with a large vocabulary gap from a source domain. We show that our method outperforms the present state-of-the-art domain adaptation method. In addition, our method achieves state-of-the-art results, combined with BM25.

2021

pdf bib
Incorporating Semantic Textual Similarity and Lexical Matching for Information Retrieval
Hiroki Iida | Naoaki Okazaki
Proceedings of the 35th Pacific Asia Conference on Language, Information and Computation