• Publications
  • Influence
DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs
TLDR
A new reading comprehension benchmark, DROP, which requires Discrete Reasoning Over the content of Paragraphs, and presents a new model that combines reading comprehension methods with simple numerical reasoning to achieve 51% F1.
DuReader: a Chinese Machine Reading Comprehension Dataset from Real-world Applications
TLDR
This paper introduces DuReader, a new large-scale, open-domain Chinese machine reading comprehension (MRC) dataset, designed to address real-world MRC, and organizes a shared competition to encourage the exploration of more models.
A Two-Stage Parsing Method for Text-Level Discourse Analysis
TLDR
This paper designs a pipelined two-stage parsing method for generating an RST tree from text and argues that relation labeling can benefit from naked tree structure and should be treated elaborately with consideration of three kinds of relations including within- Sentence, across-sentence and across-paragraph relations.
Do NLP Models Know Numbers? Probing Numeracy in Embeddings
TLDR
This work investigates the numerical reasoning capabilities of a state-of-the-art question answering model on the DROP dataset and finds this model excels on questions that require numerical reasoning, i.e., it already captures numeracy.
Multi-Passage Machine Reading Comprehension with Cross-Passage Answer Verification
TLDR
An end-to-end neural model is proposed that enables answer candidates from different passages to verify each other based on their content representations and achieves the state-of-the-art performance on the English MS-MARCO dataset and the Chinese DuReader dataset.
Toward Fast and Accurate Neural Discourse Segmentation
TLDR
This paper proposes an end-to-end neural segmenter based on BiLSTM-CRF framework that addresses the problem of data insufficiency by transferring a word representation model that is trained on a large corpus and proposes a restricted self-attention mechanism in order to capture useful information within a neighborhood.
Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamics
TLDR
The results indicate that a shift in focus from quantity to quality of data could lead to robust models and improved out-of-distribution generalization, and a model-based tool to characterize and diagnose datasets.
Bag-of-Words as Target for Neural Machine Translation
TLDR
This paper proposes an approach that uses both the sentences and the bag-of-words as targets in the training stage, in order to encourage the model to generate the potentially correct sentences that are not appeared in theTraining set.
Tag-Enhanced Tree-Structured Neural Networks for Implicit Discourse Relation Classification
TLDR
This work employs the Tree-LSTM model and Tree-GRU model, which is based on the tree structure, to encode the arguments in a relation and further leverage the constituent tags to control the semantic composition process in these tree-structured neural networks.
MultiModalQA: Complex Question Answering over Text, Tables and Images
TLDR
This paper creates MMQA, a challenging question answering dataset that requires joint reasoning over text, tables and images, and defines a formal language that allows it to take questions that can be answered from a single modality, and combine them to generate cross-modal questions.
...
...