• Publications
  • Influence
Supervised Learning of Universal Sentence Representations from Natural Language Inference Data
It is shown how universal sentence representations trained using the supervised data of the Stanford Natural Language Inference datasets can consistently outperform unsupervised methods like SkipThought vectors on a wide range of transfer tasks.
Personalizing Dialogue Agents: I have a dog, do you have pets too?
This work collects data and train models tocondition on their given profile information; and information about the person they are talking to, resulting in improved dialogues, as measured by next utterance prediction.
Poincaré Embeddings for Learning Hierarchical Representations
This work introduces a new approach for learning hierarchical representations of symbolic data by embedding them into hyperbolic space -- or more precisely into an n-dimensional Poincare ball -- and introduces an efficient algorithm to learn the embeddings based on Riemannian optimization.
SentEval: An Evaluation Toolkit for Universal Sentence Representations
We introduce SentEval, a toolkit for evaluating the quality of universal sentence representations. SentEval encompasses a variety of tasks, including binary and multi-class classification, natural
Adversarial NLI: A New Benchmark for Natural Language Understanding
This work introduces a new large-scale NLI benchmark dataset, collected via an iterative, adversarial human-and-model-in-the-loop procedure, and shows that non-expert annotators are successful at finding their weaknesses.
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
A general-purpose fine-tuning recipe for retrieval-augmented generation (RAG) -- models which combine pre-trained parametric and non-parametric memory for language generation, and finds that RAG models generate more specific, diverse and factual language than a state-of-the-art parametric-only seq2seq baseline.
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
It is shown that an embedding in hyperbolic space can reveal important aspects of a company's organizational structure as well as reveal historical relationships between language families.
What makes a good conversation? How controllable attributes affect human judgments
This work examines two controllable neural text generation methods, conditional training and weighted decoding, in order to control four important attributes for chit-chat dialogue: repetition, specificity, response-relatedness and question-asking, and shows that by controlling combinations of these variables their models obtain clear improvements in human quality judgments.
Learning Image Embeddings using Convolutional Neural Networks for Improved Multi-Modal Semantics
We construct multi-modal concept representations by concatenating a skip-gram linguistic representation vector with a visual concept representation vector computed using the feature extraction layers
HyperLex: A Large-Scale Evaluation of Graded Lexical Entailment
We introduce HyperLex—a data set and evaluation resource that quantifies the extent of the semantic category membership, that is, type-of relation, also known as hyponymy–hypernymy or lexical