b'Ivan Titov'

research

∙ 05/29/2023

Autoencoding Conditional Neural Processes for Representation Learning

Conditional neural processes (CNPs) are a flexible and efficient family ...

0 Victor Prokhorov, et al. ∙

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...

0 Andrea Schioppa, et al. ∙

research

∙ 05/26/2023

Compositional Generalization without Trees using Multiset Tagging and Latent Permutations

Seq2seq models have been shown to struggle with compositional generaliza...

0 Matthias Lindemann, et al. ∙

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...

0 Verna Dankers, et al. ∙

research

∙ 11/15/2022

Hierarchical Phrase-based Sequence-to-Sequence Learning

We describe a neural transducer that maintains the flexibility of standa...

0 Bailin Wang, et al. ∙

research

∙ 10/06/2022

Compositional Generalisation with Structured Reordering and Fertility Layers

Seq2seq models have been shown to struggle with compositional generalisa...

7 Matthias Lindemann, et al. ∙

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...

3 Verna Dankers, et al. ∙

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...

4 Nicola De Cao, et al. ∙

research

∙ 09/09/2021

Learning Opinion Summarizers by Selecting Informative Reviews

Opinion summarization has been traditionally approached with unsupervise...

15 Arthur Bražinskas, et al. ∙

research

∙ 09/08/2021

Highly Parallel Autoregressive Entity Linking with Discriminative Correction

Generative approaches have been recently shown to be effective for both ...

20 Nicola De Cao, et al. ∙

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...

12 Elena Voita, et al. ∙

research

∙ 06/10/2021

Exploring Unsupervised Pretraining Objectives for Machine Translation

Unsupervised cross-lingual pretraining has achieved strong results in ne...

8 Christos Baziotis, et al. ∙

research

∙ 06/08/2021

Meta-Learning to Compositionally Generalize

Natural language is compositional; the meaning of a sentence is a functi...

12 Henry Conklin, et al. ∙

research

∙ 06/06/2021

Structured Reordering for Modeling Latent Alignments in Sequence Transduction

Despite success in many domains, neural models struggle in settings wher...

2 Bailin Wang, et al. ∙

research

∙ 04/16/2021

Editing Factual Knowledge in Language Models

The factual knowledge acquired during pretraining and stored in the para...

4 Nicola De Cao, et al. ∙

research

∙ 04/14/2021

Sparse Attention with Linear Units

Recently, it has been argued that encoder-decoder models can be made mor...

23 Biao Zhang, et al. ∙

research

∙ 04/12/2021

Learning from Executions for Semantic Parsing

Semantic parsing aims at translating natural language (NL) utterances on...

15 Bailin Wang, et al. ∙

research

∙ 03/03/2021

An Empirical Study of Compound PCFGs

Compound probabilistic context-free grammars (C-PCFGs) have recently est...

4 Yanpeng Zhao, et al. ∙

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...

9 Denis Emelin, et al. ∙

research

∙ 10/27/2020

Fast Interleaved Bidirectional Sequence Generation

Independence assumptions during sequence generation can speed up inferen...

1 Biao Zhang, et al. ∙

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...

7 Chunchuan Lyu, et al. ∙

research

∙ 10/22/2020

Meta-Learning for Domain Generalization in Semantic Parsing

The importance of building semantic parsers which can be applied to new ...

2 Bailin Wang, et al. ∙

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...

7 Elena Voita, et al. ∙

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...

15 Biao Zhang, et al. ∙

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...

17 Michael Sejr Schlichtkrull, et al. ∙

research

∙ 09/25/2020

Visually Grounded Compound PCFGs

Exploiting visual groundings for language understanding has recently bee...

0 Yanpeng Zhao, et al. ∙

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 ...

0 Yanpeng Zhao, et al. ∙

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...

27 Nicola De Cao, et al. ∙

research

∙ 04/30/2020

Few-Shot Learning for Abstractive Multi-Document Opinion Summarization

Opinion summarization is an automatic creation of text reflecting subjec...

7 Arthur Bražinskas, et al. ∙

research

∙ 04/30/2020

Preventing Posterior Collapse with Levenshtein Variational Autoencoder

Variational autoencoders (VAEs) are a standard framework for inducing la...

2 Serhii Havrylov, et al. ∙

research

∙ 04/24/2020

Improving Massively Multilingual Neural Machine Translation and Zero-Shot Translation

Massively multilingual models for neural machine translation (NMT) are t...

0 Biao Zhang, et al. ∙

research

∙ 04/24/2020

On Sparsifying Encoder Outputs in Sequence-to-Sequence Models

Sequence-to-sequence models usually transfer all encoder outputs to the ...

0 Biao Zhang, et al. ∙

research

∙ 03/27/2020

Information-Theoretic Probing with Minimum Description Length

To measure how well pretrained representations encode some linguistic pr...

0 Elena Voita, et al. ∙

research

∙ 11/06/2019

Unsupervised Multi-Document Opinion Summarization as Copycat-Review Generation

Summarization of opinions is the process of automatically creating text ...

14 Arthur Bražinskas, et al. ∙

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...

18 Shangmin Guo, et al. ∙

research

∙ 10/07/2019

Capturing Argument Interaction in Semantic Role Labeling with Capsule Networks

Semantic role labeling (SRL) involves extracting propositions (i.e. pred...

0 Xinchi Chen, et al. ∙

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...

0 Diego Marcheggiani, et al. ∙

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...

0 Bailin Wang, et al. ∙

research

∙ 09/07/2019

Semantic Role Labeling with Iterative Structure Refinement

Modern state-of-the-art Semantic Role Labeling (SRL) methods rely on exp...

0 Chunchuan Lyu, et al. ∙

research

∙ 09/03/2019

Context-Aware Monolingual Repair for Neural Machine Translation

Modern sentence-level NMT systems often produce plausible translations o...

0 Elena Voita, et al. ∙

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...

0 Elena Voita, et al. ∙

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...

0 Biao Zhang, et al. ∙

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...

0 Denis Emelin, et al. ∙

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...

0 Caio Corro, et al. ∙

research

∙ 06/04/2019

Boosting Entity Linking Performance by Leveraging Unlabeled Documents

Modern entity linking systems rely on large collections of documents spe...

3 Phong Le, et al. ∙

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...

0 Elena Voita, et al. ∙

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...

0 Joost Bastings, et al. ∙

research

∙ 05/17/2019

Distant Learning for Entity Linking with Automatic Noise Detection

Accurate entity linkers have been produced for domains and languages whe...

1 Phong Le, et al. ∙

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...

0 Elena Voita, et al. ∙

research

∙ 04/21/2019

Obfuscation for Privacy-preserving Syntactic Parsing

The goal of homomorphic encryption is to encrypt data such that another ...

6 Zhifeng Hu, et al. ∙

Ivan Titov

Featured Co-authors