Skip to search formSkip to main contentSkip to account menu

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.
View on ACL (opens in a new tab)

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.
View on ACL (opens in a new tab)

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.
View PDF on arXiv (opens in a new tab)

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.
View on ACL (opens in a new tab)

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.
View PDF on arXiv (opens in a new tab)

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…
View on ACL (opens in a new tab)

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 only multimodal…
View PDF on arXiv (opens in a new tab)

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.
View on ACL (opens in a new tab)

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.
View PDF on arXiv (opens in a new tab)

The Second Conversational Intelligence Challenge (ConvAI2)

To improve performance on multi-turn conversations with humans, future systems must go beyond single word metrics like perplexity to measure the performance across sequences of utterances (conversations)—in terms of repetition, consistency and balance of dialogue acts.
View PDF on arXiv (opens in a new tab)
...
By clicking accept or continuing to use the site, you agree to the terms outlined in our Privacy Policy (opens in a new tab), Terms of Service (opens in a new tab), and Dataset License (opens in a new tab)