no code implementations • NLPerspectives (LREC) 2022 • Parker Glenn, Cassandra L. Jacobs, Marvin Thielk, Yi Chu
We identify several shortcomings of BWS relative to traditional categorical annotation: (1) When compared to categorical annotation, we estimate BWS takes approximately 4. 5x longer to complete; (2) BWS does not scale well to large annotation tasks with sparse target phenomena; (3) The high correlation between BWS and the traditional task shows that the benefits of BWS can be recovered from a simple categorically annotated, non-aggregated dataset.
1 code implementation • 27 Feb 2024 • Parker Glenn, Parag Pravin Dakle, Liang Wang, Preethi Raghavan
Many existing end-to-end systems for hybrid question answering tasks can often be boiled down to a "prompt-and-pray" paradigm, where the user has limited control and insight into the intermediate reasoning steps used to achieve the final result.
1 code implementation • 31 May 2023 • Parker Glenn, Parag Pravin Dakle, Preethi Raghavan
In addressing the task of converting natural language to SQL queries, there are several semantic and syntactic challenges.
no code implementations • 12 May 2021 • James Pustejovsky, Eben Holderness, Jingxuan Tu, Parker Glenn, Kyeongmin Rim, Kelley Lynch, Richard Brutti
In this paper, we argue that the design and development of multimodal datasets for natural language processing (NLP) challenges should be enhanced in two significant respects: to more broadly represent commonsense semantic inferences; and to better reflect the dynamics of actions and events, through a substantive alignment of textual and visual information.