User profiles for Douwe Kiela
Douwe KielaContextual AI, Stanford University Verified email at stanford.edu Cited by 18902 |
Supervised learning of universal sentence representations from natural language inference data
Many modern NLP systems rely on word embeddings, previously trained in an unsupervised
manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks …
manner on large corpora, as base features. Efforts to obtain embeddings for larger chunks …
Retrieval-augmented generation for knowledge-intensive nlp tasks
Large pre-trained language models have been shown to store factual knowledge in their
parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. …
parameters, and achieve state-of-the-art results when fine-tuned on downstream NLP tasks. …
Winoground: Probing vision and language models for visio-linguistic compositionality
We present a novel task and dataset for evaluating the ability of vision and language models
to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two …
to conduct visio-linguistic compositional reasoning, which we call Winoground. Given two …
Flava: A foundational language and vision alignment model
State-of-the-art vision and vision-and-language models rely on large-scale visio-linguistic
pretraining for obtaining good performance on a variety of downstream tasks. Generally, such …
pretraining for obtaining good performance on a variety of downstream tasks. Generally, such …
Poincaré embeddings for learning hierarchical representations
Abstract Representation learning has become an invaluable approach for learning from
symbolic data such as text and graphs. However, state-of-the-art embedding methods typically …
symbolic data such as text and graphs. However, state-of-the-art embedding methods typically …
True few-shot learning with language models
Pretrained language models (LMs) perform well on many tasks even when learning from a
few examples, but prior work uses many held-out examples to tune various aspects of …
few examples, but prior work uses many held-out examples to tune various aspects of …
The hateful memes challenge: Detecting hate speech in multimodal memes
This work proposes a new challenge set for multimodal classification, focusing on detecting
hate speech in multimodal memes. It is constructed such that unimodal models struggle and …
hate speech in multimodal memes. It is constructed such that unimodal models struggle and …
No training required: Exploring random encoders for sentence classification
We explore various methods for computing sentence representations from pre-trained word
embeddings without any training, ie, using nothing but random parameterizations. Our aim is …
embeddings without any training, ie, using nothing but random parameterizations. Our aim is …
Personalizing dialogue agents: I have a dog, do you have pets too?
Chit-chat models are known to have several problems: they lack specificity, do not display a
consistent personality and are often not very captivating. In this work we present the task of …
consistent personality and are often not very captivating. In this work we present the task of …
Adversarial NLI: A new benchmark for natural language understanding
We introduce a new large-scale NLI benchmark dataset, collected via an iterative, adversarial
human-and-model-in-the-loop procedure. We show that training models on this new …
human-and-model-in-the-loop procedure. We show that training models on this new …