Skip to search formSkip to main contentSkip to account menu

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

This work presents two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT, and uses a self-supervised loss that focuses on modeling inter-sentence coherence.
View PDF on arXiv (opens in a new tab)

SummScreen: A Dataset for Abstractive Screenplay Summarization

Human evaluation and qualitative analysis reveal that the non-oracle models are competitive with their oracle counterparts in terms of generating faithful plot events and can benefit from better content selectors.
View on ACL (opens in a new tab)

A Multi-Task Approach for Disentangling Syntax and Semantics in Sentence Representations

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 show we can achieve…
View on ACL (opens in a new tab)

Controllable Paraphrase Generation with a Syntactic Exemplar

This work proposes a novel task, where the syntax of a generated sentence is controlled rather by a sentential exemplar, and develops a variational model with a neural module specifically designed for capturing syntactic knowledge and several multitask training objectives to promote disentangled representation learning.
View on ACL (opens in a new tab)

Evaluation Benchmarks and Learning Criteria for Discourse-Aware Sentence Representations

This work proposes DiscoEval, a test suite of tasks to evaluate whether sentence representations include broader context information, and proposes a variety of training objectives that makes use of natural annotations from Wikipedia to build sentence encoders capable of modeling discourse.
View on ACL (opens in a new tab)

Variational Sequential Labelers for Semi-Supervised Learning

A family of multitask variational methods for semi-supervised sequence labeling that combines a latent-variable generative model and a discriminative labeler, and explores several latent variable configurations, including ones with hierarchical structure.
View on ACL (opens in a new tab)

WikiTableT: A Large-Scale Data-to-Text Dataset for Generating Wikipedia Article Sections

Qualitative analysis shows that the best approaches can generate fluent and high quality texts but they struggle with coherence and factuality, showing the potential for the WIKITABLET dataset to inspire future work on long-form generation.
View on ACL (opens in a new tab)

EntEval: A Holistic Evaluation Benchmark for Entity Representations

This work proposes EntEval: a test suite of diverse tasks that require nontrivial understanding of entities including entity typing, entity similarity, entity relation prediction, and entity disambiguation, and develops training techniques for learning better entity representations by using natural hyperlink annotations in Wikipedia.
View on ACL (opens in a new tab)

How to Ask Better Questions? A Large-Scale Multi-Domain Dataset for Rewriting Ill-Formed Questions

A large-scale dataset for the task of rewriting an ill-formed natural language question to a well-formed one andTrain sequence-to-sequence neural models on the constructed dataset and obtain an improvement of 13.2% in BLEU-4 over baseline methods built from other data resources.
View PDF on arXiv (opens in a new tab)

Controllable Paraphrasing and Translation with a Syntactic Exemplar

The authors' single proposed model can perform four tasks: controlled paraphrase generation in both languages and controlled machine translation in both language directions, and analysis shows that their models learn to disentangle semantics and syntax in their latent representations.
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)