no code implementations • ACL (RepL4NLP) 2021 • Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin
We present an efficient training approach to text retrieval with dense representations that applies knowledge distillation using the ColBERT late-interaction ranking model.
1 code implementation • 26 Apr 2023 • Jia-Huei Ju, Sheng-Chieh Lin, Ming-Feng Tsai, Chuan-Ju Wang
This paper presents ConvRerank, a conversational passage re-ranker that employs a newly developed pseudo-labeling approach.
1 code implementation • 15 Feb 2023 • Sheng-Chieh Lin, Akari Asai, Minghan Li, Barlas Oguz, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen
We hence propose a new DA approach with diverse queries and sources of supervision to progressively train a generalizable DR. As a result, DRAGON, our dense retriever trained with diverse augmentation, is the first BERT-base-sized DR to achieve state-of-the-art effectiveness in both supervised and zero-shot evaluations and even competes with models using more complex late interaction (ColBERTv2 and SPLADE++).
1 code implementation • 13 Feb 2023 • Minghan Li, Sheng-Chieh Lin, Xueguang Ma, Jimmy Lin
Multi-vector retrieval methods have demonstrated their effectiveness on various retrieval datasets, and among them, ColBERT is the most established method based on the late interaction of contextualized token embeddings of pre-trained language models.
1 code implementation • 18 Nov 2022 • Minghan Li, Sheng-Chieh Lin, Barlas Oguz, Asish Ghoshal, Jimmy Lin, Yashar Mehdad, Wen-tau Yih, Xilun Chen
In this paper, we unify different multi-vector retrieval models from a token routing viewpoint and propose conditional token interaction via dynamic lexical routing, namely CITADEL, for efficient and effective multi-vector retrieval.
1 code implementation • 9 Oct 2022 • Kuan-Wei Huang, Geoff Chih-Fan Chen, Po-Wen Chang, Sheng-Chieh Lin, Chia-Jung Hsu, Vishal Thengane, Joshua Yao-Yu Lin
Quantifying the parameters and corresponding uncertainties of hundreds of strongly lensed quasar systems holds the key to resolving one of the most important scientific questions: the Hubble constant ($H_{0}$) tension.
1 code implementation • 31 Jul 2022 • Sheng-Chieh Lin, Minghan Li, Jimmy Lin
Pre-trained language models have been successful in many knowledge-intensive NLP tasks.
1 code implementation • 20 Jun 2022 • Sheng-Chieh Lin, Jimmy Lin
In contrast, our work integrates lexical representations with dense semantic representations by densifying high-dimensional lexical representations into what we call low-dimensional dense lexical representations (DLRs).
1 code implementation • 9 Dec 2021 • Sheng-Chieh Lin, Jimmy Lin
Learned sparse and dense representations capture different successful approaches to text retrieval and the fusion of their results has proven to be more effective and robust.
no code implementations • EMNLP 2021 • Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin
This paper describes a compact and effective model for low-latency passage retrieval in conversational search based on learned dense representations.
4 code implementations • 14 Apr 2021 • Sebastian Hofstätter, Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin, Allan Hanbury
A vital step towards the widespread adoption of neural retrieval models is their resource efficiency throughout the training, indexing and query workflows.
Ranked #15 on Zero-shot Text Search on BEIR
1 code implementation • 19 Feb 2021 • Jimmy Lin, Xueguang Ma, Sheng-Chieh Lin, Jheng-Hong Yang, Ronak Pradeep, Rodrigo Nogueira
Pyserini is an easy-to-use Python toolkit that supports replicable IR research by providing effective first-stage retrieval in a multi-stage ranking architecture.
Cultural Vocal Bursts Intensity Prediction Information Retrieval +1
no code implementations • 22 Dec 2020 • Teppei Okumura, Masao Hayashi, I-Non Chiu, Yen-Ting Lin, Ken Osato, Bau-Ching Hsieh, Sheng-Chieh Lin
From the constrained HOD model, the average mass of halos hosting the [OII] emitters is derived to be $\log{M_{eff}/(h^{-1}M_\odot)}=12. 70^{+0. 09}_{-0. 07}$ and $12. 61^{+0. 09}_{-0. 05}$ at z=1. 19 and 1. 47, respectively, which will become halos with the present-day mass, $M\sim 1. 5 \times 10^{13}h^{-1}M_\odot$.
Astrophysics of Galaxies Cosmology and Nongalactic Astrophysics
no code implementations • 4 Dec 2020 • Gongbo Liang, Yuanyuan Su, Sheng-Chieh Lin, Yu Zhang, Yuanyuan Zhang, Nathan Jacobs
We believe the proposed method will benefit astronomy and cosmology, where a large number of unlabeled multi-band images are available, but acquiring image labels is costly.
no code implementations • COLING 2020 • Jheng-Hong Yang, Sheng-Chieh Lin, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
While internalized {``}implicit knowledge{''} in pretrained transformers has led to fruitful progress in many natural language understanding tasks, how to most effectively elicit such knowledge remains an open question.
2 code implementations • 22 Oct 2020 • Sheng-Chieh Lin, Jheng-Hong Yang, Jimmy Lin
We present an approach to ranking with dense representations that applies knowledge distillation to improve the recently proposed late-interaction ColBERT model.
no code implementations • 30 Aug 2020 • Sheng-Chieh Lin, Ting-Wei Lin, Jing-Kai Lou, Ming-Feng Tsai, Chuan-Ju Wang
In this paper, we propose a two-stage ranking approach for recommending linear TV programs.
no code implementations • 5 May 2020 • Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
Conversational search plays a vital role in conversational information seeking.
no code implementations • 4 Apr 2020 • Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
This paper presents an empirical study of conversational question reformulation (CQR) with sequence-to-sequence architectures and pretrained language models (PLMs).
no code implementations • 18 Mar 2020 • Sheng-Chieh Lin, Jheng-Hong Yang, Rodrigo Nogueira, Ming-Feng Tsai, Chuan-Ju Wang, Jimmy Lin
We applied the T5 sequence-to-sequence model to tackle the AI2 WinoGrande Challenge by decomposing each example into two input text strings, each containing a hypothesis, and using the probabilities assigned to the "entailment" token as a score of the hypothesis.
Ranked #17 on Coreference Resolution on Winograd Schema Challenge