Papers by Kevin Stowe
Metaphor Generation with Conceptual Mappings (2021.acl-long)
Copied to clipboard
| Challenge: | Existing models for metaphor generation lack conceptualization of meaning of the metaphors . recent neural models have led to advances in many areas of natural language generation . |
| Approach: | They propose to encode conceptual mappings between cognitive domains to generate metaphoric expressions by embedding verbs into a literal expression and deriving source/target pairs to train a controlled seq-to-seq generation model. |
| Outcome: | The proposed method outperforms existing models in automatic and human evaluations for basic metaphoricity and conceptual metaphor presence. |
Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing (2024.acl-short)
Copied to clipboard
| Challenge: | Existing methods for Cross-Document Event Coreference Resolution (CDEC) are biased towards lexical similarities, limiting a crucial avenue of research in event comprehension. |
| Approach: | They propose a lexically rich variant of Event Coref Bank Plus (ECB+) for CDEC on symbolic and metaphoric language. |
| Outcome: | The proposed method avoids the reannotation of expensive coreference links on symbolic and metaphoric language. |
Identifying Bias in Machine-generated Text Detection (2026.acl-long)
Copied to clipboard
| Challenge: | a growing number of generative AI systems are detecting text generated by a model or written by . humans perform poorly at the detection task, but show no significant biases on the studied attributes. |
| Approach: | They examine gender, race/ethnicity, English-language learner status, and economic status . they find several models tend to classify disadvantaged groups as machine-generated . |
| Outcome: | The proposed models show strong performance but can cause negative impacts . the models classify disadvantaged groups as machine-generated, while economically disadvantaged students' essays are less likely to be classified as machine generated . |
The challenges of temporal alignment on Twitter during crises (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing models consider data spanning years to decades, but shorter time spans are critical for crisis data. |
| Approach: | They propose to use domain adaptation techniques to cope with performance degradation by leveraging domain adaptation. |
| Outcome: | The proposed models outperform baseline models under conditions of natural and human-induced disasters while highlighting the limitations of current models. |
Controlled Language Generation for Language Learning Items (2022.emnlp-industry)
Copied to clipboard
| Challenge: | Recent advances in pre-trained language models have resulted in success in generating fluent English text. |
| Approach: | They propose to employ natural language generation to rapidly generate English language items . they experiment with deep pretrained models and develop methods for controlling items for factors relevant in language learning . |
| Outcome: | The proposed framework shows high grammatically scores for all models and higher complexity over baseline models. |
Lessons Learned from a Citizen Science Project for Natural Language Processing (2023.eacl-main)
Copied to clipboard
Jan-Christoph Klie, Ji-Ung Lee, Kevin Stowe, Gözde Şahin, Nafise Sadat Moosavi, Luke Bates, Dominic Petrak, Richard Eckart De Castilho, Iryna Gurevych
| Challenge: | Annotations are expensive and difficult to obtain, which is why many NLP systems outsource their work to paid crowdworkers. |
| Approach: | They propose to use Citizen Science to re-annotate parts of a pre-existing crowdsourced dataset to gain high-quality annotations. |
| Outcome: | The proposed approach yields high-quality annotations and motivated volunteers, but requires consideration of scalability, participation over time, and legal and ethical issues. |
IMPLI: Investigating NLI Models’ Performance on Figurative Language (2022.acl-long)
Copied to clipboard
| Challenge: | Understanding figurative language is a difficult area in NLP but is essential for proper understanding. |
| Approach: | They propose to use a dataset to generate 24k semiautomatic pairs and manually create 1.8k gold pairs to evaluate NLI models. |
| Outcome: | The proposed models can detect entailment relationship between figurative phrases and their literal counterparts, but perform poorly on similar structured examples. |