• Publications
  • Influence
Universal Dependency Annotation for Multilingual Parsing
TLDR
We present a new collection of treebanks with homogeneous syntactic dependency annotation for six languages: German, English, Swedish, Spanish, French and Korean. Expand
  • 400
  • 61
  • PDF
Assessing the Ability of LSTMs to Learn Syntax-Sensitive Dependencies
TLDR
The success of long short-term memory (LSTM) neural networks in language processing is typically attributed to their ability to capture long-distance statistical regularities. Expand
  • 402
  • 59
  • PDF
Multilingual Part-of-Speech Tagging with Bidirectional Long Short-Term Memory Models and Auxiliary Loss
TLDR
Bidirectional long short-term memory (bi-LSTM) networks have recently proven successful for various NLP sequence modeling tasks, but little is known about their reliance to input representations, target languages, data size, and label noise. Expand
  • 296
  • 48
  • PDF
Deep multi-task learning with low level tasks supervised at lower layers
TLDR
We present a multi-task learning architecture with deep bi-directional RNNs, where different tasks supervision can happen at different layers. Expand
  • 300
  • 17
  • PDF
Improving sentence compression by learning to predict gaze
TLDR
We show how eye-tracking corpora can be used to improve sentence compression models, presenting a novel multi-task learning algorithm based on multi-layer LSTMs. Expand
  • 84
  • 7
  • PDF
A Strong Baseline for Learning Cross-Lingual Word Embeddings from Sentence Alignments
TLDR
This paper draws both empirical and theoretical parallels between the embedding and alignment literature, and suggests that adding additional sources of information, which go beyond the traditional signal of bilingual sentence-aligned corpora, may substantially improve cross-lingual word embeddings, and that future baselines should at least take such features into account. Expand
  • 47
  • 6
  • PDF
oLMpics - On what Language Model Pre-training Captures
TLDR
We propose eight reasoning tasks, which conceptually require operations such as comparison, conjunction, and composition, and propose an evaluation protocol that includes both zero-shot evaluation (no fine-tuning) as well as comparing the learning curve of a fine tuned LM to the learning curves of multiple controls, which paints a rich picture of the LM capabilities. Expand
  • 51
  • 6
  • PDF
Break It Down: A Question Understanding Benchmark
TLDR
We introduce a Question Decomposition Meaning Representation (QDMR) for questions. Expand
  • 16
  • 5
  • PDF
Towards Faithfully Interpretable NLP Systems: How should we define and evaluate faithfulness?
TLDR
We survey the literature with respect to faithfulness evaluation, and arrange the current approaches around three assumptions, providing an explicit form to how faithfulness is "defined" by the community. Expand
  • 20
  • 3
  • PDF
Null It Out: Guarding Protected Attributes by Iterative Nullspace Projection
TLDR
We present Iterative Null-space Projection (INLP), a novel method for removing information from neural representations. Expand
  • 15
  • 3
  • PDF