Search Results for author: Kartik Goyal

Found 13 papers, 1 papers with code

Exposing the Implicit Energy Networks behind Masked Language Models via Metropolis--Hastings

no code implementations4 Jun 2021 Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick

While recent work has shown that scores from models trained by the ubiquitous masked language modeling (MLM) objective effectively discriminate probable and improbable sequences, it is still an open question if these MLMs specify a principled probability distribution over the space of possible sequences.

Language Modelling Machine Translation +1

A Probabilistic Generative Model for Typographical Analysis of Early Modern Printing

no code implementations ACL 2020 Kartik Goyal, Chris Dyer, Christopher Warren, Max G'Sell, Taylor Berg-Kirkpatrick

We show that our approach outperforms rigid interpretable clustering baselines (Ocular) and overly-flexible deep generative models (VAE) alike on the task of completely unsupervised discovery of typefaces in mixed-font documents.

A Continuous Relaxation of Beam Search for End-to-end Training of Neural Sequence Models

no code implementations1 Aug 2017 Kartik Goyal, Graham Neubig, Chris Dyer, Taylor Berg-Kirkpatrick

In experiments, we show that optimizing this new training objective yields substantially better results on two sequence tasks (Named Entity Recognition and CCG Supertagging) when compared with both cross entropy trained greedy decoding and cross entropy trained beam decoding baselines.

CCG Supertagging Motion Segmentation +1

Differentiable Scheduled Sampling for Credit Assignment

no code implementations ACL 2017 Kartik Goyal, Chris Dyer, Taylor Berg-Kirkpatrick

We demonstrate that a continuous relaxation of the argmax operation can be used to create a differentiable approximation to greedy decoding for sequence-to-sequence (seq2seq) models.

Machine Translation Named Entity Recognition +1

PanPhon: A Resource for Mapping IPA Segments to Articulatory Feature Vectors

1 code implementation COLING 2016 David R. Mortensen, Patrick Littell, Akash Bharadwaj, Kartik Goyal, Chris Dyer, Lori Levin

This paper contributes to a growing body of evidence that{---}when coupled with appropriate machine-learning techniques{--}linguistically motivated, information-rich representations can outperform one-hot encodings of linguistic data.

NER

Named Entity Recognition for Linguistic Rapid Response in Low-Resource Languages: Sorani Kurdish and Tajik

no code implementations COLING 2016 Patrick Littell, Kartik Goyal, David R. Mortensen, Alexa Little, Chris Dyer, Lori Levin

This paper describes our construction of named-entity recognition (NER) systems in two Western Iranian languages, Sorani Kurdish and Tajik, as a part of a pilot study of {``}Linguistic Rapid Response{''} to potential emergency humanitarian relief situations.

Named Entity Recognition NER

Bridge-Language Capitalization Inference in Western Iranian: Sorani, Kurmanji, Zazaki, and Tajik

no code implementations LREC 2016 Patrick Littell, David R. Mortensen, Kartik Goyal, Chris Dyer, Lori Levin

In Sorani Kurdish, one of the most useful orthographic features in named-entity recognition {--} capitalization {--} is absent, as the language{'}s Perso-Arabic script does not make a distinction between uppercase and lowercase letters.

Named Entity Recognition

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