Skip to search formSkip to main contentSkip to account menu

Pointer Sentinel Mixture Models

The pointer sentinel-LSTM model achieves state of the art language modeling performance on the Penn Treebank while using far fewer parameters than a standard softmax LSTM and the freely available WikiText corpus is introduced.
View PDF on arXiv (opens in a new tab)

Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning

This work proposes Seq2 SQL, a deep neural network for translating natural language questions to corresponding SQL queries, and releases WikiSQL, a dataset of 80654 hand-annotated examples of questions and SQL queries distributed across 24241 tables fromWikipedia that is an order of magnitude larger than comparable datasets.

A Deep Reinforced Model for Abstractive Summarization

A neural network model with a novel intra-attention that attends over the input and continuously generated output separately, and a new training method that combines standard supervised word prediction and reinforcement learning (RL) that produces higher quality summaries.
View PDF on arXiv (opens in a new tab)

Knowing When to Look: Adaptive Attention via a Visual Sentinel for Image Captioning

This paper proposes a novel adaptive attention model with a visual sentinel that sets the new state-of-the-art by a significant margin on image captioning.
View on IEEE (opens in a new tab)

CTRL: A Conditional Transformer Language Model for Controllable Generation

CTRL is released, a 1.63 billion-parameter conditional transformer language model, trained to condition on control codes that govern style, content, and task-specific behavior, providing more explicit control over text generation.
View PDF on arXiv (opens in a new tab)

Dynamic Coattention Networks For Question Answering

The Dynamic Coattention Network (DCN) for question answering first fuses co-dependent representations of the question and the document in order to focus on relevant parts of both, then a dynamic pointing decoder iterates over potential answer spans to recover from initial local maxima corresponding to incorrect answers.
View PDF on arXiv (opens in a new tab)

Non-Autoregressive Neural Machine Translation

A model is introduced that avoids this autoregressive property and produces its outputs in parallel, allowing an order of magnitude lower latency during inference, and achieves near-state-of-the-art performance on WMT 2016 English-Romanian.
View PDF on arXiv (opens in a new tab)

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

A Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training.
View on ACL (opens in a new tab)

ERASER: A Benchmark to Evaluate Rationalized NLP Models

This work proposes the Evaluating Rationales And Simple English Reasoning (ERASER) a benchmark to advance research on interpretable models in NLP, and proposes several metrics that aim to capture how well the rationales provided by models align with human rationales, and also how faithful these rationales are.
View on ACL (opens in a new tab)

Dynamic Memory Networks for Visual and Textual Question Answering

The new DMN+ model improves the state of the art on both the Visual Question Answering dataset and the \babi-10k text question-answering dataset without supporting fact supervision.
View PDF on arXiv (opens in a new tab)
...
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)