research
∙
05/29/2023
Autoencoding Conditional Neural Processes for Representation Learning
Conditional neural processes (CNPs) are a flexible and efficient family ...
share
research
∙
05/26/2023
Theoretical and Practical Perspectives on what Influence Functions Do
Influence functions (IF) have been seen as a technique for explaining mo...
research
∙
05/26/2023
Compositional Generalization without Trees using Multiset Tagging and Latent Permutations
Seq2seq models have been shown to struggle with compositional generaliza...
research
∙
01/31/2023
Recursive Neural Networks with Bottlenecks Diagnose (Non-)Compositionality
A recent line of work in NLP focuses on the (dis)ability of models to ge...
research
∙
11/15/2022
Hierarchical Phrase-based Sequence-to-Sequence Learning
We describe a neural transducer that maintains the flexibility of standa...
research
∙
10/06/2022
Compositional Generalisation with Structured Reordering and Fertility Layers
Seq2seq models have been shown to struggle with compositional generalisa...
research
∙
05/30/2022
Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
Unlike literal expressions, idioms' meanings do not directly follow from...
research
∙
12/13/2021
Sparse Interventions in Language Models with Differentiable Masking
There has been a lot of interest in understanding what information is ca...
research
∙
09/09/2021
Learning Opinion Summarizers by Selecting Informative Reviews
Opinion summarization has been traditionally approached with unsupervise...
research
∙
09/08/2021
Highly Parallel Autoregressive Entity Linking with Discriminative Correction
Generative approaches have been recently shown to be effective for both ...
research
∙
09/03/2021
Language Modeling, Lexical Translation, Reordering: The Training Process of NMT through the Lens of Classical SMT
Differently from the traditional statistical MT that decomposes the tran...
research
∙
06/10/2021
Exploring Unsupervised Pretraining Objectives for Machine Translation
Unsupervised cross-lingual pretraining has achieved strong results in ne...
research
∙
06/08/2021
Meta-Learning to Compositionally Generalize
Natural language is compositional; the meaning of a sentence is a functi...
research
∙
06/06/2021
Structured Reordering for Modeling Latent Alignments in Sequence Transduction
Despite success in many domains, neural models struggle in settings wher...
research
∙
04/16/2021
Editing Factual Knowledge in Language Models
The factual knowledge acquired during pretraining and stored in the para...
research
∙
04/14/2021
Sparse Attention with Linear Units
Recently, it has been argued that encoder-decoder models can be made mor...
research
∙
04/12/2021
Learning from Executions for Semantic Parsing
Semantic parsing aims at translating natural language (NL) utterances on...
research
∙
03/03/2021
An Empirical Study of Compound PCFGs
Compound probabilistic context-free grammars (C-PCFGs) have recently est...
research
∙
11/03/2020
Detecting Word Sense Disambiguation Biases in Machine Translation for Model-Agnostic Adversarial Attacks
Word sense disambiguation is a well-known source of translation errors i...
research
∙
10/27/2020
Fast Interleaved Bidirectional Sequence Generation
Independence assumptions during sequence generation can speed up inferen...
research
∙
10/23/2020
A Differentiable Relaxation of Graph Segmentation and Alignment for AMR Parsing
Abstract Meaning Representations (AMR) are a broad-coverage semantic for...
research
∙
10/22/2020
Meta-Learning for Domain Generalization in Semantic Parsing
The importance of building semantic parsers which can be applied to new ...
research
∙
10/21/2020
Analyzing the Source and Target Contributions to Predictions in Neural Machine Translation
In Neural Machine Translation (and, more generally, conditional language...
research
∙
10/16/2020
Adaptive Feature Selection for End-to-End Speech Translation
Information in speech signals is not evenly distributed, making it an ad...
research
∙
10/01/2020
Interpreting Graph Neural Networks for NLP With Differentiable Edge Masking
Graph neural networks (GNNs) have become a popular approach to integrati...
research
∙
09/25/2020
Visually Grounded Compound PCFGs
Exploiting visual groundings for language understanding has recently bee...
research
∙
05/01/2020
Unsupervised Transfer of Semantic Role Models from Verbal to Nominal Domain
Semantic role labeling (SRL) is an NLP task involving the assignment of ...
research
∙
04/30/2020
How do Decisions Emerge across Layers in Neural Models? Interpretation with Differentiable Masking
Attribution methods assess the contribution of inputs (e.g., words) to t...
research
∙
04/30/2020
Few-Shot Learning for Abstractive Multi-Document Opinion Summarization
Opinion summarization is an automatic creation of text reflecting subjec...
research
∙
04/30/2020
Preventing Posterior Collapse with Levenshtein Variational Autoencoder
Variational autoencoders (VAEs) are a standard framework for inducing la...
research
∙
04/24/2020
Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation
Massively multilingual models for neural machine translation (NMT) are t...
research
∙
04/24/2020
On Sparsifying Encoder Outputs in Sequence-to-Sequence Models
Sequence-to-sequence models usually transfer all encoder outputs to the ...
research
∙
03/27/2020
Information-Theoretic Probing with Minimum Description Length
To measure how well pretrained representations encode some linguistic pr...
research
∙
11/06/2019
Unsupervised Multi-Document Opinion Summarization as Copycat-Review Generation
Summarization of opinions is the process of automatically creating text ...
research
∙
10/11/2019
The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents
Since first introduced, computer simulation has been an increasingly imp...
research
∙
10/07/2019
Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks
Semantic role labeling (SRL) involves extracting propositions (i.e. pred...
research
∙
09/21/2019
Graph Convolutions over Constituent Trees for Syntax-Aware Semantic Role Labeling
Semantic role labeling (SRL) is the task of identifying predicates and l...
research
∙
09/09/2019
Learning Semantic Parsers from Denotations with Latent Structured Alignments and Abstract Programs
Semantic parsing aims to map natural language utterances onto machine in...
research
∙
09/07/2019
Semantic Role Labeling with Iterative Structure Refinement
Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on exp...
research
∙
09/03/2019
Context-Aware Monolingual Repair for Neural Machine Translation
Modern sentence-level NMT systems often produce plausible translations o...
research
∙
09/03/2019
The Bottom-up Evolution of Representations in the Transformer: A Study with Machine Translation and Language Modeling Objectives
We seek to understand how the representations of individual tokens and t...
research
∙
08/29/2019
Improving Deep Transformer with Depth-Scaled Initialization and Merged Attention
The general trend in NLP is towards increasing model capacity and perfor...
research
∙
06/28/2019
Widening the Representation Bottleneck in Neural Machine Translation with Lexical Shortcuts
The transformer is a state-of-the-art neural translation model that uses...
research
∙
06/24/2019
Learning Latent Trees with Stochastic Perturbations and Differentiable Dynamic Programming
We treat projective dependency trees as latent variables in our probabil...
research
∙
06/04/2019
Boosting Entity Linking Performance by Leveraging Unlabeled Documents
Modern entity linking systems rely on large collections of documents spe...
research
∙
05/23/2019
Analyzing Multi-Head Self-Attention: Specialized Heads Do the Heavy Lifting, the Rest Can Be Pruned
Multi-head self-attention is a key component of the Transformer, a state...
research
∙
05/20/2019
Interpretable Neural Predictions with Differentiable Binary Variables
The success of neural networks comes hand in hand with a desire for more...
research
∙
05/17/2019
Distant Learning for Entity Linking with Automatic Noise Detection
Accurate entity linkers have been produced for domains and languages whe...
research
∙
05/15/2019
When a Good Translation is Wrong in Context: Context-Aware Machine Translation Improves on Deixis, Ellipsis, and Lexical Cohesion
Though machine translation errors caused by the lack of context beyond o...
research
∙
04/21/2019
