3.2k citations · 7k across the 61 of their papers we have counts for
16 papers · 1 filter
How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions
Zewei Chu, Mingda Chen, Jing Chen +4
We present a large-scale dataset for the task of rewriting an ill-formed natural language question to a well-formed one. Our multi-domain question rewriting MQR dataset is construc…
Improving Joint Training of Inference Networks and Structured Prediction Energy Networks
Lifu Tu, Richard Yuanzhe Pang, Kevin Gimpel
Deep energy-based models are powerful, but pose challenges for learning and inference (Belanger and McCallum, 2016). Tu and Gimpel (2018) developed an efficient framework for energ…
Latent-Variable Generative Models for Data-Efficient Text Classification
Xiaoan Ding, Kevin Gimpel
Generative classifiers offer potential advantages over their discriminative counterparts, namely in the areas of data efficiency, robustness to data shift and adversarial examples,…
Simple and Effective Paraphrastic Similarity from Parallel Translations
John Wieting, Kevin Gimpel, Graham Neubig +1
We present a model and methodology for learning paraphrastic sentence embeddings directly from bitext, removing the time-consuming intermediate step of creating paraphrase corpora.…
Beyond BLEU: Training Neural Machine Translation with Semantic Similarity
John Wieting, Taylor Berg-Kirkpatrick, Kevin Gimpel +1
While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve…
Generating Diverse Story Continuations with Controllable Semantics
Lifu Tu, Xiaoan Ding, Dong Yu +1
We propose a simple and effective modeling framework for controlled generation of multiple, diverse outputs. We focus on the setting of generating the next sentence of a story give…
ALBERT: A Lite BERT for Self-supervised Learning of Language Representations
Zhenzhong Lan, Mingda Chen, Sebastian Goodman +3
Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases be…
Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations
Mingda Chen, Zewei Chu, Kevin Gimpel
Prior work on pretrained sentence embeddings and benchmarks focus on the capabilities of stand-alone sentences. We propose DiscoEval, a test suite of tasks to evaluate whether sent…
EntEval: A Holistic Evaluation Benchmark for Entity Representations
Mingda Chen, Zewei Chu, Yang Chen +2
Rich entity representations are useful for a wide class of problems involving entities. Despite their importance, there is no standardized benchmark that evaluates the overall qual…
Variational Sequential Labelers for Semi-Supervised Learning
Mingda Chen, Qingming Tang, Karen Livescu +1
We introduce a family of multitask variational methods for semi-supervised sequence labeling. Our model family consists of a latent-variable generative model and a discriminative l…
Smaller Text Classifiers with Discriminative Cluster Embeddings
Mingda Chen, Kevin Gimpel
Word embedding parameters often dominate overall model sizes in neural methods for natural language processing. We reduce deployed model sizes of text classifiers by learning a har…
Controllable Paraphrase Generation with a Syntactic Exemplar
Mingda Chen, Qingming Tang, Sam Wiseman +1
Prior work on controllable text generation usually assumes that the controlled attribute can take on one of a small set of values known a priori. In this work, we propose a novel t…
Visually Grounded Neural Syntax Acquisition
Haoyue Shi, Jiayuan Mao, Kevin Gimpel +1
We present the Visually Grounded Neural Syntax Learner (VG-NSL), an approach for learning syntactic representations and structures without any explicit supervision. The model learn…
PoMo: Generating Entity-Specific Post-Modifiers in Context
Jun Seok Kang, Robert L. Logan, Zewei Chu +5
We introduce entity post-modifier generation as an instance of a collaborative writing task. Given a sentence about a target entity, the task is to automatically generate a post-mo…
A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations
Mingda Chen, Qingming Tang, Sam Wiseman +1
We propose a generative model for a sentence that uses two latent variables, with one intended to represent the syntax of the sentence and the other to represent its semantics. We…
Benchmarking Approximate Inference Methods for Neural Structured Prediction
Lifu Tu, Kevin Gimpel
Exact structured inference with neural network scoring functions is computationally challenging but several methods have been proposed for approximating inference. One approach is…