Search Results for author: Matthew R. Gormley

Found 29 papers, 15 papers with code

Effective Convolutional Attention Network for Multi-label Clinical Document Classification

no code implementations EMNLP 2021 Yang Liu, Hua Cheng, Russell Klopfer, Matthew R. Gormley, Thomas Schaaf

Multi-label document classification (MLDC) problems can be challenging, especially for long documents with a large label set and a long-tail distribution over labels.

Classification Document Classification +1

It's MBR All the Way Down: Modern Generation Techniques Through the Lens of Minimum Bayes Risk

1 code implementation2 Oct 2023 Amanda Bertsch, Alex Xie, Graham Neubig, Matthew R. Gormley

Minimum Bayes Risk (MBR) decoding is a method for choosing the outputs of a machine learning system based not on the output with the highest probability, but the output with the lowest risk (expected error) among multiple candidates.

MDACE: MIMIC Documents Annotated with Code Evidence

1 code implementation ACL 2023 Hua Cheng, Rana Jafari, April Russell, Russell Klopfer, Edmond Lu, Benjamin Striner, Matthew R. Gormley

In this paper, we introduce MDACE, the first publicly available code evidence dataset, which is built on a subset of the MIMIC-III clinical records.

Document Classification Extreme Multi-Label Classification

Unlimiformer: Long-Range Transformers with Unlimited Length Input

1 code implementation NeurIPS 2023 Amanda Bertsch, Uri Alon, Graham Neubig, Matthew R. Gormley

This kNN index can be kept on either the GPU or CPU memory and queried in sub-linear time; this way, we can index practically unlimited input sequences, while every attention head in every decoder layer retrieves its top-k keys, instead of attending to every key.

Revisiting text decomposition methods for NLI-based factuality scoring of summaries

no code implementations30 Nov 2022 John Glover, Federico Fancellu, Vasudevan Jagannathan, Matthew R. Gormley, Thomas Schaaf

In this paper we systematically compare different granularities of decomposition -- from document to sub-sentence level, and we show that the answer is no.

Natural Language Inference Sentence

AdaFocal: Calibration-aware Adaptive Focal Loss

1 code implementation21 Nov 2022 Arindam Ghosh, Thomas Schaaf, Matthew R. Gormley

In this paper, we propose a calibration-aware adaptive focal loss called AdaFocal that utilizes the calibration properties of focal (and inverse-focal) loss and adaptively modifies $\gamma_t$ for different groups of samples based on $\gamma_{t-1}$ from the previous step and the knowledge of model's under/over-confidence on the validation set.

Out-of-Distribution Detection

He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues

1 code implementation27 Oct 2022 Amanda Bertsch, Graham Neubig, Matthew R. Gormley

As a sample application, we demonstrate that applying perspective shifting to a dialogue summarization dataset (SAMSum) substantially improves the zero-shot performance of extractive news summarization models on this data.

coreference-resolution News Summarization +1

On Efficiently Acquiring Annotations for Multilingual Models

1 code implementation ACL 2022 Joel Ruben Antony Moniz, Barun Patra, Matthew R. Gormley

When tasked with supporting multiple languages for a given problem, two approaches have arisen: training a model for each language with the annotation budget divided equally among them, and training on a high-resource language followed by zero-shot transfer to the remaining languages.

Active Learning Dependency Parsing

Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction

no code implementations ACL (SIGMORPHON) 2021 Maria Ryskina, Eduard Hovy, Taylor Berg-Kirkpatrick, Matthew R. Gormley

Traditionally, character-level transduction problems have been solved with finite-state models designed to encode structural and linguistic knowledge of the underlying process, whereas recent approaches rely on the power and flexibility of sequence-to-sequence models with attention.

Limitations of Autoregressive Models and Their Alternatives

no code implementations NAACL 2021 Chu-Cheng Lin, Aaron Jaech, Xin Li, Matthew R. Gormley, Jason Eisner

Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.

Language Modelling

Phonetic and Visual Priors for Decipherment of Informal Romanization

1 code implementation ACL 2020 Maria Ryskina, Matthew R. Gormley, Taylor Berg-Kirkpatrick

Informal romanization is an idiosyncratic process used by humans in informal digital communication to encode non-Latin script languages into Latin character sets found on common keyboards.

Decipherment Inductive Bias

Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces

1 code implementation ACL 2019 Barun Patra, Joel Ruben Antony Moniz, Sarthak Garg, Matthew R. Gormley, Graham Neubig

We then propose Bilingual Lexicon Induction with Semi-Supervision (BLISS) --- a semi-supervised approach that relaxes the isometric assumption while leveraging both limited aligned bilingual lexicons and a larger set of unaligned word embeddings, as well as a novel hubness filtering technique.

Bilingual Lexicon Induction Word Embeddings

Neural Finite-State Transducers: Beyond Rational Relations

no code implementations NAACL 2019 Chu-Cheng Lin, Hao Zhu, Matthew R. Gormley, Jason Eisner

We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.

Approximation-Aware Dependency Parsing by Belief Propagation

no code implementations TACL 2015 Matthew R. Gormley, Mark Dredze, Jason Eisner

We show how to adjust the model parameters to compensate for the errors introduced by this approximation, by following the gradient of the actual loss on training data.

Dependency Parsing

Improved Relation Extraction with Feature-Rich Compositional Embedding Models

1 code implementation EMNLP 2015 Matthew R. Gormley, Mo Yu, Mark Dredze

We propose a Feature-rich Compositional Embedding Model (FCM) for relation extraction that is expressive, generalizes to new domains, and is easy-to-implement.

 Ranked #1 on Relation Extraction on ACE 2005 (Cross Sentence metric)

Relation Relation Classification +2

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