Search Results for author: Aakanksha Naik

Found 13 papers, 7 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.

Literature-Augmented Clinical Outcome Prediction

1 code implementation Findings (NAACL) 2022 Aakanksha Naik, Sravanthi Parasa, Sergey Feldman, Lucy Lu Wang, Tom Hope

We present BEEP (Biomedical Evidence-Enhanced Predictions), a novel approach for clinical outcome prediction that retrieves patient-specific medical literature and incorporates it into predictive models.

Decision Making

Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks

1 code implementation2 Nov 2021 Aakanksha Naik, Jill Lehman, Carolyn Rose

We reflect on the question: have transfer learning methods sufficiently addressed the poor performance of benchmark-trained models on the long tail?

Natural Language Understanding Transfer Learning

STAGE: Tool for Automated Extraction of Semantic Time Cues to Enrich Neural Temporal Ordering Models

no code implementations15 May 2021 Luke Breitfeller, Aakanksha Naik, Carolyn Rose

We demonstrate the utility of extracted cues by integrating them with an event ordering model using a joint BiLSTM and ILP constraint architecture.

Adapting Event Extractors to Medical Data: Bridging the Covariate Shift

no code implementations EACL 2021 Aakanksha Naik, Jill Lehman, Carolyn Rose

Our best-performing models reach F1 scores of 70. 0 and 72. 9 on notes and conversations respectively, using no labeled data from target domains.

Domain Adaptation Event Extraction +1

Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation

1 code implementation ACL 2020 Aakanksha Naik, Carolyn Rosé

We tackle the task of building supervised event trigger identification models which can generalize better across domains.

Domain Adaptation

TDDiscourse: A Dataset for Discourse-Level Temporal Ordering of Events

no code implementations WS 2019 Aakanksha Naik, Luke Breitfeller, Carolyn Rose

Prior work on temporal relation classification has focused extensively on event pairs in the same or adjacent sentences (local), paying scant attention to discourse-level (global) pairs.

Relation Classification

Using Functional Schemas to Understand Social Media Narratives

1 code implementation WS 2019 Xinru Yan, Aakanksha Naik, Yohan Jo, Carolyn Rose

We propose a novel take on understanding narratives in social media, focusing on learning {''}functional story schemas{''}, which consist of sets of stereotypical functional structures.

Classification General Classification +1

Exploring Numeracy in Word Embeddings

no code implementations ACL 2019 Aakanksha Naik, Ravich, Abhilasha er, Carolyn Rose, Eduard Hovy

In this work, we show that existing embedding models are inadequate at constructing representations that capture salient aspects of mathematical meaning for numbers, which is important for language understanding.

Word Embeddings

Stress Test Evaluation for Natural Language Inference

1 code implementation COLING 2018 Aakanksha Naik, Abhilasha Ravichander, Norman Sadeh, Carolyn Rose, Graham Neubig

Natural language inference (NLI) is the task of determining if a natural language hypothesis can be inferred from a given premise in a justifiable manner.

Natural Language Inference Natural Language Understanding

Extracting Personal Medical Events for User Timeline Construction using Minimal Supervision

no code implementations WS 2017 Aakanksha Naik, Chris Bogart, Carolyn Rose

In this paper, we describe a system for automatic construction of user disease progression timelines from their posts in online support groups using minimal supervision.

Event Detection

Tackling Biomedical Text Summarization: OAQA at BioASQ 5B

no code implementations WS 2017 Khyathi u, Aakanksha Naik, Ch, Aditya rasekar, Zi Yang, Niloy Gupta, Eric Nyberg

In this paper, we describe our participation in phase B of task 5b of the fifth edition of the annual BioASQ challenge, which includes answering factoid, list, yes-no and summary questions from biomedical data.

Answer Generation Extractive Summarization +2

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