200 citations · 811 across the 66 of their papers we have counts for
12 papers · 1 filter
Visually Grounded Reasoning across Languages and Cultures
Fangyu Liu, Emanuele Bugliarello, Edoardo Maria Ponti +3
The design of widespread vision-and-language datasets and pre-trained encoders directly adopts, or draws inspiration from, the concepts and images of ImageNet. While one can hardly…
An Empirical Survey of the Effectiveness of Debiasing Techniques for Pre-trained Language Models
Nicholas Meade, Elinor Poole-Dayan, Siva Reddy
Recent work has shown pre-trained language models capture social biases from the large amounts of text they are trained on. This has attracted attention to developing techniques th…
The Power of Prompt Tuning for Low-Resource Semantic Parsing
Nathan Schucher, Siva Reddy, Harm de Vries
Prompt tuning has recently emerged as an effective method for adapting pre-trained language models to a number of language understanding and generation tasks. In this paper, we inv…
Evaluating the Faithfulness of Importance Measures in NLP by Recursively Masking Allegedly Important Tokens and Retraining
Andreas Madsen, Nicholas Meade, Vaibhav Adlakha +1
To explain NLP models a popular approach is to use importance measures, such as attention, which inform input tokens are important for making a prediction. However, an open questio…
Compositional Generalization in Dependency Parsing
Emily Goodwin, Siva Reddy, Timothy J. O'Donnell +1
Compositionality -- the ability to combine familiar units like words into novel phrases and sentences -- has been the focus of intense interest in artificial intelligence in recent…
TopiOCQA: Open-domain Conversational Question Answering with Topic Switching
Vaibhav Adlakha, Shehzaad Dhuliawala, Kaheer Suleman +2
In a conversational question answering scenario, a questioner seeks to extract information about a topic through a series of interdependent questions and answers. As the conversati…
Post-hoc Interpretability for Neural NLP: A Survey
Andreas Madsen, Siva Reddy, Sarath Chandar
Neural networks for NLP are becoming increasingly complex and widespread, and there is a growing concern if these models are responsible to use. Explaining models helps to address…
Modelling Latent Translations for Cross-Lingual Transfer
Edoardo Maria Ponti, Julia Kreutzer, Ivan Vulić +1
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-train…
Minimax and Neyman-Pearson Meta-Learning for Outlier Languages
Edoardo Maria Ponti, Rahul Aralikatte, Disha Shrivastava +2
Model-agnostic meta-learning (MAML) has been recently put forth as a strategy to learn resource-poor languages in a sample-efficient fashion. Nevertheless, the properties of these…
End-to-End Training of Multi-Document Reader and Retriever for Open-Domain Question Answering
Devendra Singh Sachan, Siva Reddy, William Hamilton +2
We present an end-to-end differentiable training method for retrieval-augmented open-domain question answering systems that combine information from multiple retrieved documents wh…
Understanding by Understanding Not: Modeling Negation in Language Models
Arian Hosseini, Siva Reddy, Dzmitry Bahdanau +3
Negation is a core construction in natural language. Despite being very successful on many tasks, state-of-the-art pre-trained language models often handle negation incorrectly. To…
Back-Training excels Self-Training at Unsupervised Domain Adaptation of Question Generation and Passage Retrieval
Devang Kulshreshtha, Robert Belfer, Iulian Vlad Serban +1
In this work, we introduce back-training, an alternative to self-training for unsupervised domain adaptation (UDA) from source to target domain. While self-training generates synth…