Papers by Bonnie Dorr

4 papers
The Effect of Data Partitioning Strategy on Model Generalizability: A Case Study of Morphological Segmentation (2024.naacl-long)

Copied to clipboard

Challenge: Recent work to enhance data partitioning strategies for more realistic model evaluations faces challenges in providing a clear optimal choice.
Approach: They analyze morphological segmentation and morphology of ten languages from 19 languages . they use multiple datasets and splits to evaluate models .
Outcome: The proposed model training and evaluation sets and new test data show that models trained from random splits can achieve higher numerical scores and model rankings tend to generalize more consistently.
BeSt: The Belief and Sentiment Corpus (2022.lrec-1)

Copied to clipboard

Challenge: a corpus of propositional content is a set of cognitive attitudes of different agents towards a text . propositional attitudes are a cognitive attitude, including belief and sentiment, towards .
Approach: They propose a corpus which records cognitive state: who believes what, who has what sentiment . they use newswire and discussion forums in Chinese, English, and Spanish .
Outcome: The proposed corpus records who believes what (i.e., factuality) and who has what sentiment towards what.
Learning to Plan and Realize Separately for Open-Ended Dialogue Systems (2020.findings-emnlp)

Copied to clipboard

Challenge: Existing approaches to natural language generation are construed as end-to-end systems . however, some issues persist, such as coherence of output and repetition/hallucination of tokens .
Approach: They propose to decouple natural language generation into two phases: planning and realization.
Outcome: The proposed approach performs better than an end-to-end approach.
From Stance to Concern: Adaptation of Propositional Analysis to New Tasks and Domains (2022.findings-acl)

Copied to clipboard

Challenge: Existing paradigms for propositional analysis use stances and concerns to generate explanatory representations.
Approach: They propose a generalized paradigm for adaptation of propositional analysis to new tasks and domains by using an analogy between stances and concerns.
Outcome: The proposed model yields 231% improvement in recall over baseline, with only 10% loss in precision.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations