1 code implementation • CL (ACL) 2021 • Allen Schmaltz
From this sequence-labeling layer we derive dense representations of the input that can then be matched to instances from training, or a support set with known labels.
no code implementations • 28 May 2022 • Allen Schmaltz, Danielle Rasooly
A typical desideratum for quantifying the uncertainty from a classification model as a prediction set is class-conditional singleton set calibration.
1 code implementation • 29 Nov 2020 • Allen Schmaltz, Andrew Beam
We present a novel end-to-end language model for joint retrieval and classification, unifying the strengths of bi- and cross- encoders into a single language model via a coarse-to-fine memory matching search procedure for learning and inference.
no code implementations • 7 Apr 2020 • Allen Schmaltz, Andrew Beam
These challenges are compounded for modalities such as text, where the feature space is very high-dimensional, and often contains considerable amounts of noise.
1 code implementation • 4 Jun 2019 • Allen Schmaltz
From this sequence-labeling layer we derive dense representations of the input that can then be matched to instances from training, or a support set with known labels.
no code implementations • WS 2018 • Allen Schmaltz
In this position paper, we propose that the community consider encouraging researchers to include two riders, a {``}Lay Summary{''} and an {``}AI Safety Disclosure{''}, as part of future NLP papers published in ACL forums that present user-facing systems.
4 code implementations • 4 Apr 2018 • Andrew L. Beam, Benjamin Kompa, Allen Schmaltz, Inbar Fried, Griffin Weber, Nathan P. Palmer, Xu Shi, Tianxi Cai, Isaac S. Kohane
Word embeddings are a popular approach to unsupervised learning of word relationships that are widely used in natural language processing.
1 code implementation • EMNLP 2017 • Allen Schmaltz, Yoon Kim, Alexander M. Rush, Stuart M. Shieber
In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via convolutions, and that modeling the output data as a series of diffs improves effectiveness over standard approaches.
1 code implementation • EMNLP 2016 • Allen Schmaltz, Alexander M. Rush, Stuart M. Shieber
Recent work on word ordering has argued that syntactic structure is important, or even required, for effectively recovering the order of a sentence.
no code implementations • WS 2016 • Allen Schmaltz, Yoon Kim, Alexander M. Rush, Stuart M. Shieber
We demonstrate that an attention-based encoder-decoder model can be used for sentence-level grammatical error identification for the Automated Evaluation of Scientific Writing (AESW) Shared Task 2016.