Search Results for author: Sopan Khosla

Found 17 papers, 3 papers with code

FanfictionNLP: A Text Processing Pipeline for Fanfiction

1 code implementation NAACL (NUSE) 2021 Michael Yoder, Sopan Khosla, Qinlan Shen, Aakanksha Naik, Huiming Jin, Hariharan Muralidharan, Carolyn Rosé

The pipeline includes modules for character identification and coreference, as well as the attribution of quotes and narration to those characters.

Bring Your Own KG: Self-Supervised Program Synthesis for Zero-Shot KGQA

1 code implementation14 Nov 2023 Dhruv Agarwal, Rajarshi Das, Sopan Khosla, Rashmi Gangadharaiah

We present BYOKG, a universal question-answering (QA) system that can operate on any knowledge graph (KG), requires no human-annotated training data, and can be ready to use within a day -- attributes that are out-of-scope for current KGQA systems.

In-Context Learning Program Synthesis +2

MedFilter: Improving Extraction of Task-relevant Utterances from Doctor-Patient Conversations through Integration of Discourse Structure and Ontological Knowledge

1 code implementation EMNLP 2020 Sopan Khosla, Shikhar Vashishth, Jill Fain Lehman, Carolyn Rose

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.

EmotionX-AR: CNN-DCNN autoencoder based Emotion Classifier

no code implementations WS 2018 Sopan Khosla

In this paper, we model emotions in EmotionLines dataset using a convolutional-deconvolutional autoencoder (CNN-DCNN) framework.

Emotion Classification Emotion Recognition +1

Surveys without Questions: A Reinforcement Learning Approach

no code implementations11 Jun 2020 Atanu R. Sinha, Deepali Jain, Nikhil Sheoran, Sopan Khosla, Reshmi Sasidharan

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).

reinforcement-learning Reinforcement Learning (RL)

Evaluating the Impact of a Hierarchical Discourse Representation on Entity Coreference Resolution Performance

no code implementations NAACL 2021 Sopan Khosla, James Fiacco, Carolyn Rose

Recent work on entity coreference resolution (CR) follows current trends in Deep Learning applied to embeddings and relatively simple task-related features.

coreference-resolution

Counterfactuals to Control Latent Disentangled Text Representations for Style Transfer

no code implementations ACL 2021 Sharmila Reddy Nangi, Niyati Chhaya, Sopan Khosla, Nikhil Kaushik, Harshit Nyati

Disentanglement of latent representations into content and style spaces has been a commonly employed method for unsupervised text style transfer.

Attribute counterfactual +5

The Universal Anaphora Scorer

no code implementations LREC 2022 Juntao Yu, Sopan Khosla, Nafise Sadat Moosavi, Silviu Paun, Sameer Pradhan, Massimo Poesio

It also supports the evaluation of split antecedent anaphora and discourse deixis, for which no tools existed.

The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue

no code implementations COLING (CODI, CRAC) 2022 Juntao Yu, Sopan Khosla, Ramesh Manuvinakurike, Lori Levin, Vincent Ng, Massimo Poesio, Michael Strube, Carolyn Rosé

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.

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