Search Results for author:
Found 23 papers, 10 papers with code
Training for Gibbs Sampling on Conditional Random Fields with Neural Scoring Factors
Most recent improvements in NLP come from changes to the neural network architectures modeling the text input.
Effective Convolutional Attention Network for Multi-label Clinical Document Classification
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.
Ranked #2 on
Medical Code Prediction
on MIMIC-III
Revisiting text decomposition methods for NLI-based factuality scoring of summaries
In this paper we systematically compare different granularities of decomposition -- from document to sub-sentence level, and we show that the answer is no.
He Said, She Said: Style Transfer for Shifting the Perspective of Dialogues
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.
On Efficiently Acquiring Annotations for Multilingual Models
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.
Leveraging Pretrained Models for Automatic Summarization of Doctor-Patient Conversations
We show that fluent and adequate summaries can be generated with limited training data by fine-tuning BART on a specially constructed dataset.
Comparative Error Analysis in Neural and Finite-state Models for Unsupervised Character-level Transduction
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
Standard autoregressive language models perform only polynomial-time computation to compute the probability of the next symbol.
An Empirical Investigation of Beam-Aware Training in Supertagging
This approach leads to mismatches as, during training, the model is not exposed to its mistakes and does not use beam search.
Phonetic and Visual Priors for Decipherment of Informal Romanization
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.
Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces
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.
Neural Finite-State Transducers: Beyond Rational Relations
We introduce neural finite state transducers (NFSTs), a family of string transduction models defining joint and conditional probability distributions over pairs of strings.
Learning Beam Search Policies via Imitation Learning
Beam search is widely used for approximate decoding in structured prediction problems.
Neural Factor Graph Models for Cross-lingual Morphological Tagging
Morphological analysis involves predicting the syntactic traits of a word (e. g. {POS: Noun, Case: Acc, Gender: Fem}).
Approximation-Aware Dependency Parsing by Belief Propagation
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.
Improved Relation Extraction with Feature-Rich Compositional Embedding Models
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)
