Search Results for author: Arzoo Katiyar

Found 9 papers, 4 papers with code

Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning

1 code implementation EMNLP 2020 Yi Yang, Arzoo Katiyar

We present a simple few-shot named entity recognition (NER) system based on nearest neighbor learning and structured inference.

few-shot-ner Few-shot NER +2

Revisiting Few-sample BERT Fine-tuning

1 code implementation ICLR 2021 Tianyi Zhang, Felix Wu, Arzoo Katiyar, Kilian Q. Weinberger, Yoav Artzi

We empirically test the impact of these factors, and identify alternative practices that resolve the commonly observed instability of the process.

SPARSE: Structured Prediction using Argument-Relative Structured Encoding

no code implementations WS 2019 Rishi Bommasani, Arzoo Katiyar, Claire Cardie

We apply our approach to the second-order structured prediction task studied in the 2016/2017 Belief and Sentiment analysis evaluations (BeSt): given a document and its entities, relations, and events (including metadata and mentions), determine the sentiment of each entity towards every relation and event in the document.

Sentiment Analysis Structured Prediction

Nested Named Entity Recognition Revisited

no code implementations NAACL 2018 Arzoo Katiyar, Claire Cardie

We propose a novel recurrent neural network-based approach to simultaneously handle nested named entity recognition and nested entity mention detection.

Coreference Resolution Nested Named Entity Recognition +2

Going out on a limb: Joint Extraction of Entity Mentions and Relations without Dependency Trees

no code implementations ACL 2017 Arzoo Katiyar, Claire Cardie

We also compare our model with an end-to-end tree-based LSTM model (SPTree) by Miwa and Bansal (2016) and show that our model performs within 1{\%} on entity mentions and 2{\%} on relations.

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