Papers by Matthew R. Gormley

11 papers
Neural Factor Graph Models for Cross-lingual Morphological Tagging (P18-1)

Copied to clipboard

Challenge: Existing approaches to morphological tagging are limited by the assumption that tag sets overlap . a limited amount of data is available for most languages to learn these morphology taggers.
Approach: They propose a method for cross-lingual morphological tagging that relaxes this assumption . they use factorial conditional random fields with neural network potentials to smooth over superficial differences in the surface forms .
Outcome: The proposed model can smooth over superficial differences in the surface forms and generate unseen or rare tag sets.
Effective Convolutional Attention Network for Multi-label Clinical Document Classification (2021.emnlp-main)

Copied to clipboard

Challenge: a large number of medical encounters need to be coded everyday due to long document sets and large label set.
Approach: They propose a convolutional attention network for multi-label document classification problem . they use convolution-based encoders and convolution networks to aggregate information across documents .
Outcome: The proposed model outperforms prior best model and multilingual Transformer model on a widely used dataset in the medical domain.
Limitations of Autoregressive Models and Their Alternatives (2021.naacl-main)

Copied to clipboard

Challenge: Standard autoregressive language models only perform polynomial-time computation to compute probability of next symbol.
Approach: authors propose alternative to standard autoregressive language models that use polynomial-time computation to compute probability of next symbol.
Outcome: a large model size can grow superpolynomially in length, allowing it to store precomputed results and verify solutions.
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations (2021.findings-emnlp)

Copied to clipboard

Challenge: Using pretrained transformer models for automatically summarizing doctor-patient conversations presents challenges . limited training data, domain shift, long and noisy transcripts, and high target summary variability are challenges compared to human annotators.
Approach: They propose a method for fine-tuning pretrained transformer models for automatically summarizing doctor-patient conversations directly from transcripts.
Outcome: The proposed method surpasses the performance of an average human annotator and the quality of previous published work for the task.
He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues (2022.findings-emnlp)

Copied to clipboard

Challenge: Existing work on style transfer has focused on controlling formality, authorial style, and sentiment of text.
Approach: They propose a style transfer task that reframes a dialogue from informal first person to formal third person rephrasing . they use a dataset to annotate dialogues from a text summarization corpus .
Outcome: The proposed task improves the performance of extractive models on a dialogue summarization dataset.
In-Context Learning with Long-Context Models: An In-Depth Exploration (2025.naacl-long)

Copied to clipboard

Challenge: In-context learning is limited by context length, but it can be used for many tasks.
Approach: They study the behavior of in-context learning at an extreme context length . example retrieval shows excellent performance at low context lengths but has diminished gains .
Outcome: The proposed model can perform many tasks with reasonable accuracy when a few examples are provided in-context.
Neural Finite-State Transducers: Beyond Rational Relations (N19-1)

Copied to clipboard

Challenge: a finite state transducer defines joint and conditional probability distributions over strings . a weighted finite-state transducers can only model certain functions, known as the rational relations .
Approach: They propose a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
Outcome: The proposed models are more powerful than previous finite-state models with neural features.
An Empirical Investigation of Beam-Aware Training in Supertagging (2020.findings-emnlp)

Copied to clipboard

Challenge: Structured prediction is often approached by training a local normalized model with maximum likelihood and decoding approximately with beam search.
Approach: They propose a meta-algorithm that captures beam-aware training algorithms and suggests new ones.
Outcome: The proposed algorithm improves performance for both models and the simpler model . it also improves the model which must manage uncertainty during decoding .
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces (P19-1)

Copied to clipboard

Challenge: Recent work on bilingual lexicon induction (BLI) relies on an assumption about the isometry of two embedding spaces.
Approach: They propose a semi-supervised approach that relaxes the isometric assumption while leveraging limited aligned bilingual lexicons and a larger set of unaligned word embeddings.
Outcome: The proposed method obtains state-of-the-art results on 15 of 18 language pairs on the MUSE dataset and does particularly well when the embedding spaces don’t appear isometric.
Training for Gibbs Sampling on Conditional Random Fields with Neural Scoring Factors (2020.emnlp-main)

Copied to clipboard

Challenge: Recent advances in NLP focus on simple approaches to model the output label space . graphical models are often limited to (heuristic) greedy search and its variants .
Approach: They propose an approach for efficiently training and decoding hybrids of graphical and graphical models based on Gibbs sampling.
Outcome: The proposed approach improves on Dutch and Dutch with graphical models . the proposed model improves over a strong baseline on three languages .
Phonetic and Visual Priors for Decipherment of Informal Romanization (2020.acl-main)

Copied to clipboard

Challenge: 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.
Approach: They propose a noisy-channel WFST cascade model for deciphering the original non-Latin script from observed romanized text in an unsupervised fashion.
Outcome: The proposed model improves on romanized Egyptian Arabic and Russian data and is closer to the supervised skyline.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations