Skip to search formSkip to main contentSkip to account menu

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.

Position-aware Attention and Supervised Data Improve Slot Filling

An effective new model is proposed, which combines an LSTM sequence model with a form of entity position-aware attention that is better suited to relation extraction that builds TACRED, a large supervised relation extraction dataset obtained via crowdsourcing and targeted towards TAC KBP relations.
View on ACL (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)

Ask Me Anything: Dynamic Memory Networks for Natural Language Processing

The dynamic memory network (DMN), a neural network architecture which processes input sequences and questions, forms episodic memories, and generates relevant answers, is introduced.
View PDF on arXiv (opens in a new tab)

Global-Locally Self-Attentive Encoder for Dialogue State Tracking

This paper proposes the Global-Locally Self-Attentive Dialogue State Tracker (GLAD), which learns representations of the user utterance and previous system actions with global-local modules and shows that this significantly improves tracking of rare states.
View on ACL (opens in a new tab)

Multi-hop Reading Comprehension through Question Decomposition and Rescoring

A system that decomposes a compositional question into simpler sub-questions that can be answered by off-the-shelf single-hop RC models is proposed and a new global rescoring approach is introduced that considers each decomposition to select the best final answer, greatly improving overall performance.
View on ACL (opens in a new tab)

Efficient and Robust Question Answering from Minimal Context over Documents

A simple sentence selector is proposed to select the minimal set of sentences to feed into the QA model, and the overall system achieves significant reductions in training and inference times, with accuracy comparable to or better than the state-of-the-art on SQuAD, NewsQA, TriviaQA and SQuad-Open.
View on ACL (opens in a new tab)

Bootstrapped Self Training for Knowledge Base Population

This work proposes bootstrapped selftraining to capture the benefits of both systems: the precision of patterns and the generalizability of trained models and shows that training on the output of patterns drastically improves performance over the patterns.
View Paper (opens in a new tab)

DCN+: Mixed Objective and Deep Residual Coattention for Question Answering

This work proposes a mixed objective that combines cross entropy loss with self-critical policy learning, and improves dynamic coattention networks (DCN) with a deep residual coatt attention encoder that is inspired by recent work in deep self-attention and residual networks.
View PDF on arXiv (opens in a new tab)

Grounded Adaptation for Zero-shot Executable Semantic Parsing

GAZP outperforms data-augmentation in the training environment, performance increases with the amount of GAZP-synthesized data, and cycle-consistency is central to successful adaptation.
View on ACL (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)