Papers by Wonsuk Yang
Generating Sentential Arguments from Diverse Perspectives on Controversial Topic (D19-50)
Copied to clipboard
| Challenge: | ArgDiver model generates high-quality sentential arguments from multiple perspectives . retrieval-based systems do not have sufficient flexibility for input with missing keywords or topics unseen . |
| Approach: | They propose a neural method to generate sentential arguments from multiple perspectives . their model generates high-quality sentential argument, but shows higher diversity . |
| Outcome: | The proposed model generates high-quality sentential arguments from multiple perspectives . it shows that it can provide diverse perspectives on a controversial topic . |
GeezSwitch: Language Identification in Typologically Related Low-resourced East African Languages (2022.lrec-1)
Copied to clipboard
| Challenge: | Low-resourced languages with similar typologies are often confused with each other in real-world applications such as machine translation, affecting the user’s experience. |
| Approach: | They propose to build a dataset for five typologically and phylogenetically related low-resourced East African languages using the Ge’ez script as a writing system. |
| Outcome: | The proposed dataset is built automatically from selected data sources, but also performed a manual evaluation to assess its quality. |
Question-Answering in a Low-resourced Language: Benchmark Dataset and Models for Tigrinya (2023.acl-long)
Copied to clipboard
| Challenge: | Question-Answering (QA) has seen significant advances in recent years, achieving near human-level performance over some benchmarks. |
| Approach: | They propose to use a native QA dataset for an East African language, Tigrinya, to build similar resources for related languages. |
| Outcome: | The proposed method is applicable to constructing similar resources for related languages. |
Computer Assisted Annotation of Tension Development in TED Talks through Crowdsourcing (D19-59)
Copied to clipboard
| Challenge: | Using a neural network, we annotate whether tension is increasing, decreasing, or staying unchanged. |
| Approach: | They propose a machine-assisted method for the identification of tension development using a neural network based prediction model. |
| Outcome: | The proposed method is compared with other methods in in-house and crowdsourced environments. |
Generating Negative Samples by Manipulating Golden Responses for Unsupervised Learning of a Response Evaluation Model (2021.naacl-main)
Copied to clipboard
| Challenge: | Existing metrics that rely on comparisons to a set of known correct responses do not account for the variety of responses and therefore correlate poorly with human judgment. |
| Approach: | They propose a method of manipulating a golden response to create a new negative response that is designed to be inappropriate within the context while maintaining high similarity with the original golden response. |
| Outcome: | The proposed model can be made using unsupervised learning for the next-utterance prediction task on English datasets and shows that using the negative samples alongside random negative samples can increase the model’s correlation with human evaluations. |
Nonsense!: Quality Control via Two-Step Reason Selection for Annotating Local Acceptability and Related Attributes in News Editorials (D19-1)
Copied to clipboard
| Challenge: | Annotation quality control is critical for building reliable corpora through linguistic annotation. |
| Approach: | They propose a method to control annotation quality using two-step reason selection using a crowdsourcing platform. |
| Outcome: | The proposed method retains the annotations with satisfactory quality out of the entire annotations mixed with those of low quality. |