10.9k citations
- University of MichiganUS43 papers
- Massachusetts Institute of TechnologyUS42 papers
- University of Illinois Urbana-ChampaignUS42 papers
- Joint Institute for Nuclear ResearchRU41 papers
- University of PennsylvaniaUS41 papers
- Michigan State UniversityUS40 papers
- University of New MexicoUS40 papers
- University of TsukubaJP40 papers
- University of Wisconsin–MadisonUS40 papers
- Waseda UniversityJP40 papers
- Institute of Physics, Academia SinicaTW39 papers
- National and Kapodistrian University of AthensGR39 papers
13 papers · 1 filter
FlanEC: Exploring Flan-T5 for Post-ASR Error Correction
Moreno La Quatra, Valerio Mario Salerno, Yu Tsao +1
In this paper, we present an encoder-decoder model leveraging Flan-T5 for post-Automatic Speech Recognition (ASR) Generative Speech Error Correction (GenSEC), and we refer to it as…
Answering Chinese Elementary School Social Study Multiple Choice Questions
Daniel Lee, Chao-Chun Liang, Keh-Yih Su
We present a novel approach to answer the Chinese elementary school Social Study Multiple Choice questions. Although BERT has demonstrated excellent performance on Reading Comprehe…
Happy Dance, Slow Clap: Using Reaction GIFs to Predict Induced Affect on Twitter
Boaz Shmueli, Soumya Ray, Lun-Wei Ku
Datasets with induced emotion labels are scarce but of utmost importance for many NLP tasks. We present a new, automated method for collecting texts along with their induced reacti…
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Jhih-Wei Chen, Tsu-Jui Fu, Chen-Kang Lee +1
Although distant supervision automatically generates training data for relation extraction, it also introduces false-positive (FP) and false-negative (FN) training instances to the…
Attractive or Faithful? Popularity-Reinforced Learning for Inspired Headline Generation
Yun-Zhu Song, Hong-Han Shuai, Sung-Lin Yeh +3
With the rapid proliferation of online media sources and published news, headlines have become increasingly important for attracting readers to news articles, since users may be ov…
Multi-step Joint-Modality Attention Network for Scene-Aware Dialogue System
Yun-Wei Chu, Kuan-Yen Lin, Chao-Chun Hsu +1
Understanding dynamic scenes and dialogue contexts in order to converse with users has been challenging for multimodal dialogue systems. The 8-th Dialog System Technology Challenge…