Papers by Sam Davidson
ErAConD: Error Annotated Conversational Dialog Dataset for Grammatical Error Correction (2022.naacl-main)
Copied to clipboard
| Challenge: | Currently available grammatical error correction datasets focus on written essays . a novel dataset is presented to improve the accuracy of existing educational chatbots . |
| Approach: | They propose a novel grammatical error correction dataset using essays and other long-form text written by language learners. |
| Outcome: | The proposed dataset improves the performance of a conversational chatbot in a human-machine conversational setting. |
Developing NLP Tools with a New Corpus of Learner Spanish (2020.lrec-1)
Copied to clipboard
Sam Davidson, Aaron Yamada, Paloma Fernandez Mira, Agustina Carando, Claudia H. Sanchez Gutierrez, Kenji Sagae
| Challenge: | Currently, there is little research on the development of effective NLP tools for the L2 classroom. |
| Approach: | They propose to use an annotated corpus of Spanish learner text to analyze developmental patterns and to develop a grammatical error correction system for Spanish learners. |
| Outcome: | The proposed system is based on annotated learner corpus of Spanish learners and includes error annotations and corrected text. |
Gunrock: A Social Bot for Complex and Engaging Long Conversations (D19-3)
Copied to clipboard
Dian Yu, Michelle Cohn, Yi Mang Yang, Chun Yen Chen, Weiming Wen, Jiaping Zhang, Mingyang Zhou, Kevin Jesse, Austin Chau, Antara Bhowmick, Shreenath Iyer, Giritheja Sreenivasulu, Sam Davidson, Ashwin Bhandare, Zhou Yu
| Challenge: | Gunrock is a speech-based social chatbot that can be used to understand complex sentences and have in-depth conversations. |
| Approach: | They propose a system that allows users to understand complex sentences and have in-depth conversations in open domains. |
| Outcome: | The proposed system produces longer sentences, which are directly related to user engagement (e.g., ratings, number of turns). |
Dependency Parsing for Spoken Dialog Systems (D19-1)
Copied to clipboard
| Challenge: | Dependency parsing of conversational input can help to understand dialogs . currently available annotation schemes do not adapt well to spoken human-machine dialogs. |
| Approach: | They propose an annotation scheme that extends Universal Dependencies guidelines to spoken dialogs. |
| Outcome: | The proposed scheme disambiguates relationships between entities extracted from dialogs . it is better than existing models on public datasets and fine-tuned on ConvBank data . |