Search Results for author: Ming-Feng Tsai

Found 16 papers, 2 papers with code

Improving Conversational Passage Re-ranking with View Ensemble

1 code implementation26 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.

Conversational Search Passage Re-Ranking +1

Designing Templates for Eliciting Commonsense Knowledge from Pretrained Sequence-to-Sequence Models

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.

Multiple-choice Natural Language Understanding +1

Personalized TV Recommendation: Fusing User Behavior and Preferences

no code implementations30 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.

Skewness Ranking Optimization for Personalized Recommendation

no code implementations23 May 2020 Chuan-Ju Wang, Yu-Neng Chuang, Chih-Ming Chen, Ming-Feng Tsai

In this paper, we propose a novel optimization criterion that leverages features of the skew normal distribution to better model the problem of personalized recommendation.

Conversational Question Reformulation via Sequence-to-Sequence Architectures and Pretrained Language Models

no code implementations4 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).

Task-Oriented Dialogue Systems

TTTTTackling WinoGrande Schemas

no code implementations18 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.

Coreference Resolution

Collaborative Similarity Embedding for Recommender Systems

2 code implementations17 Feb 2019 Chih-Ming Chen, Chuan-Ju Wang, Ming-Feng Tsai, Yi-Hsuan Yang

We present collaborative similarity embedding (CSE), a unified framework that exploits comprehensive collaborative relations available in a user-item bipartite graph for representation learning and recommendation.

Graph Learning Recommendation Systems +1

Representation Learning for Image-based Music Recommendation

no code implementations28 Aug 2018 Chih-Chun Hsia, Kwei-Herng Lai, Yi-An Chen, Chuan-Ju Wang, Ming-Feng Tsai

Image perception is one of the most direct ways to provide contextual information about a user concerning his/her surrounding environment; hence images are a suitable proxy for contextual recommendation.

Music Recommendation Representation Learning +1

Superhighway: Bypass Data Sparsity in Cross-Domain CF

no code implementations28 Aug 2018 Kwei-Herng Lai, Ting-Hsiang Wang, Heng-Yu Chi, Yi-An Chen, Ming-Feng Tsai, Chuan-Ju Wang

Cross-domain collaborative filtering (CF) aims to alleviate data sparsity in single-domain CF by leveraging knowledge transferred from related domains.

Collaborative Filtering

RiskFinder: A Sentence-level Risk Detector for Financial Reports

no code implementations NAACL 2018 Yu-Wen Liu, Liang-Chih Liu, Chuan-Ju Wang, Ming-Feng Tsai

This paper presents a web-based information system, RiskFinder, for facilitating the analyses of soft and hard information in financial reports.

Sentence Sentence Embedding +4

Vertex-Context Sampling for Weighted Network Embedding

no code implementations1 Nov 2017 Chih-Ming Chen, Yi-Hsuan Yang, Yi-An Chen, Ming-Feng Tsai

Many existing methods adopt a uniform sampling method to reduce learning complexity, but when the network is non-uniform (i. e. a weighted network) such uniform sampling incurs information loss.

Information Retrieval Multi-Label Classification +3

Cannot find the paper you are looking for? You can Submit a new open access paper.