Search Results for author: Nanjiang Jiang

Found 7 papers, 1 papers with code

He Thinks He Knows Better than the Doctors: BERT for Event Factuality Fails on Pragmatics

1 code implementation2 Jul 2021 Nanjiang Jiang, Marie-Catherine de Marneffe

We investigate how well BERT performs on predicting factuality in several existing English datasets, encompassing various linguistic constructions.

Do You Know That Florence Is Packed with Visitors? Evaluating State-of-the-art Models of Speaker Commitment

no code implementations ACL 2019 Nanjiang Jiang, Marie-Catherine de Marneffe

Here, we explore the hypothesis that linguistic deficits drive the error patterns of existing speaker commitment models by analyzing the linguistic correlates of model error on a challenging naturalistic dataset.

Negation Question Answering

THOMAS: The Hegemonic OSU Morphological Analyzer using Seq2seq

no code implementations WS 2019 Byung-Doh Oh, Pranav Maneriker, Nanjiang Jiang

This paper describes the OSU submission to the SIGMORPHON 2019 shared task, Crosslinguality and Context in Morphology.

Morphological Analysis Sentence +2

Evaluating BERT for natural language inference: A case study on the CommitmentBank

no code implementations IJCNLP 2019 Nanjiang Jiang, Marie-Catherine de Marneffe

Natural language inference (NLI) datasets (e. g., MultiNLI) were collected by soliciting hypotheses for a given premise from annotators.

Natural Language Inference Negation

Graph-Based Decoding for Task Oriented Semantic Parsing

no code implementations Findings (EMNLP) 2021 Jeremy R. Cole, Nanjiang Jiang, Panupong Pasupat, Luheng He, Peter Shaw

The dominant paradigm for semantic parsing in recent years is to formulate parsing as a sequence-to-sequence task, generating predictions with auto-regressive sequence decoders.

Dependency Parsing Semantic Parsing

Cross-TOP: Zero-Shot Cross-Schema Task-Oriented Parsing

no code implementations DeepLo 2022 Melanie Rubino, Nicolas Guenon des Mesnards, Uday Shah, Nanjiang Jiang, Weiqi Sun, Konstantine Arkoudas

However, a single model is still typically trained and deployed for each task separately, requiring labeled training data for each, which makes it challenging to support new tasks, even within a single business vertical (e. g., food-ordering or travel booking).

Semantic Parsing

Cannot find the paper you are looking for? You can Submit a new open access paper.