output
20032025
most citedComplex organic molecules in protoplanetary disks

256 citations

Showing cs.CLShow all

25 papers · 1 filter

cs.CL2021

An Approach to Inference-Driven Dialogue Management within a Social Chatbot

Sarah E. Finch, James D. Finch, Daniil Huryn +4

We present a chatbot implementing a novel dialogue management approach based on logical inference. Instead of framing conversation a sequence of response generation tasks, we model…

cs.CL2021

Semi-Supervised Text Classification via Self-Pretraining

Payam Karisani, Negin Karisani

We present a neural semi-supervised learning model termed Self-Pretraining. Our model is inspired by the classic self-training algorithm. However, as opposed to self-training, Self…

cs.CL2021

Intensionalizing Abstract Meaning Representations: Non-Veridicality and Scope

Gregor Williamson, Patrick Elliott, Yuxin Ji +1

Abstract Meaning Representation (AMR) is a graphical meaning representation language designed to represent propositional information about argument structure. However, at present i…

cs.CL20211 cited

StreamSide: A Fully-Customizable Open-Source Toolkit for Efficient Annotation of Meaning Representations

Jinho D. Choi, Gregor Williamson

This demonstration paper presents StreamSide, an open-source toolkit for annotating multiple kinds of meaning representations. StreamSide supports frame-based annotation schemes e.…

cs.CL2021

The Stem Cell Hypothesis: Dilemma behind Multi-Task Learning with Transformer Encoders

Han He, Jinho D. Choi

Multi-task learning with transformer encoders (MTL) has emerged as a powerful technique to improve performance on closely-related tasks for both accuracy and efficiency while a que…

cs.CL20213 cited

ELIT: Emory Language and Information Toolkit

Han He, Liyan Xu, Jinho D. Choi

We introduce ELIT, the Emory Language and Information Toolkit, which is a comprehensive NLP framework providing transformer-based end-to-end models for core tasks with a special fo…