Search Results for author:
Found 16 papers, 2 papers with code
The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
The CODI-CRAC 2022 Shared Task on Anaphora Resolution in Dialogues is the second edition of an initiative focused on detecting different types of anaphoric relations in conversations of different kinds.
The Universal Anaphora Scorer
It also supports the evaluation of split antecedent anaphora and discourse deixis, for which no tools existed.
Evaluating the Practical Utility of Confidence-score based Techniques for Unsupervised Open-world Classification
Open-world classification in dialog systems require models to detect open intents, while ensuring the quality of in-domain (ID) intent classification.
Team JARS: DialDoc Subtask 1 - Improved Knowledge Identification with Supervised Out-of-Domain Pretraining
In this paper, we discuss our submission for DialDoc subtask 1.
FanfictionNLP: A Text Processing Pipeline for Fanfiction
The pipeline includes modules for character identification and coreference, as well as the attribution of quotes and narration to those characters.
The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue
In this paper, we provide an overview of the CODI-CRAC 2021 Shared-Task: Anaphora Resolution in Dialogue.
Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer
Disentanglement of latent representations into content and style spaces has been a commonly employed method for unsupervised text style transfer.
Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance
Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features.
Using Type Information to Improve Entity Coreference Resolution
Coreference resolution (CR) is an essential part of discourse analysis.
MedFilter: Improving Extraction of Task-relevant Utterances from Doctor-Patient Conversations through Integration of Discourse Structure and Ontological Knowledge
In this paper, we propose the novel modeling approach MedFilter, which addresses these insights in order to increase performance at identifying and categorizing task-relevant utterances, and in so doing, positively impacts performance at a downstream information extraction task.
LTIatCMU at SemEval-2020 Task 11: Incorporating Multi-Level Features for Multi-Granular Propaganda Span Identification
In this paper we describe our submission for the task of Propaganda Span Identification in news articles.
Surveys without Questions: A Reinforcement Learning Approach
To overcome these deficiencies we extract proxy ratings from clickstream data, typically collected for every customer's online interactions, by developing an approach based on Reinforcement Learning (RL).
Generating SOAP Notes from Doctor-Patient Conversations Using Modular Summarization Techniques
Following each patient visit, physicians draft long semi-structured clinical summaries called SOAP notes.
EmotionX-AR: CNN-DCNN autoencoder based Emotion Classifier
In this paper, we model emotions in EmotionLines dataset using a convolutional-deconvolutional autoencoder (CNN-DCNN) framework.
Aff2Vec: Affect--Enriched Distributional Word Representations
Human communication includes information, opinions, and reactions.
Towards Building Affect sensitive Word Distributions
Our work addresses the question: can affect lexica improve the word representations learnt from a corpus?
