N
Nanjiang Jiang
Researcher at Ohio State University
Publications - 9
Citations - 104
Nanjiang Jiang is an academic researcher from Ohio State University. The author has contributed to research in topics: Computer science & Pragmatics. The author has an hindex of 3, co-authored 8 publications receiving 59 citations. Previous affiliations of Nanjiang Jiang include Google.
Papers
More filters
Proceedings ArticleDOI
Evaluating BERT for natural language inference: A case study on the CommitmentBank
TL;DR: Analysis of model behavior shows that the BERT models still do not capture the full complexity of pragmatic reasoning, nor encode some of the linguistic generalizations, highlighting room for improvement.
Proceedings ArticleDOI
QED: A fact verification system for the FEVER shared task
TL;DR: This paper describes the system submission to the 2018 Fact Extraction and VERification (FEVER) shared task, which uses a heuristics-based approach for evidence extraction and a modified version of the inference model by Parikh et al. (2016) for classification.
Proceedings ArticleDOI
Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment
TL;DR: The hypothesis that linguistic deficits drive the error patterns of existing speaker commitment models is explored by analyzing the linguistic correlates of model error on a challenging naturalistic dataset.
Proceedings ArticleDOI
THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq
TL;DR: Follow-up analyses reveal that the OSU submission to the SIGMORPHON 2019 shared task, Crosslinguality and Context in Morphology, most significantly improves performance on morphologically complex languages whose inflected word forms typically have longer MSD tag sequences.
Proceedings ArticleDOI
Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing
Melanie Rubino,Nicolas Guenon des Mesnards,Uday Shah,Nanjiang Jiang,Weiqiong Sun,Konstantine Arkoudas +5 more
TL;DR: Cross-TOP (Cross-Schema Task-Oriented Parsing), a zero-shot method for complex semantic parsing in a given vertical that can achieve high accuracy on a previously unseen task without requiring any additional training data, thereby providing a scalable way to bootstrap semantic parsers for new tasks.