Search

Machine translation (MT) is now widely and freely available, and has the potential to greatly improve cross-lingual communication. In order to use MT reliably and safely, end users must be able to assess the quality of system outputs and determine how much they can rely on them to guide their...

Deployed AI systems often do not work. They can be constructed haphazardly, deployed indiscriminately, and promoted deceptively. However, despite this reality, scholars, the press, and policymakers pay too little attention to functionality. This leads to technical and policy solutions focused on...

In this paper we first propose a new statistical parsing model, which is a generative model of lexicalised context-free grammar. We then extend the model to include a probabilistic treatment of both subcategorisation and wh-movement. Results on Wall Street Journal text show that the parser performs...

Machine learning currently exerts an outsized influence on the world, increasingly affecting institutional practices and impacted communities. It is therefore critical that we question vague conceptions of the field as value-neutral or universally beneficial, and investigate what specific values the...

A new system lets robots manipulate soft, deformable material into various shapes from visual inputs, which could one day enable better home assistants.

With in the broader scope of machine learning, data augmentation is a common strategy to improve generalization and robustness of machine learning models. While data augmentation has been widely used within computer vision, its use in the NLP has been been comparably rather limited. The reason for...

Open Information Extraction (IE) systems extract relational tuples from text, without requiring a pre-specified vocabulary, by identifying relation phrases and associated arguments in arbitrary sentences. However, state-of-the-art Open IE systems such as REVERB and WOE share two important weaknesses...

With the increasing application of machine learning in high-stake decision-making problems, potential algorithmic bias towards people from certain social groups poses negative impacts on individuals and our society at large. In the real-world scenario, many such problems involve positive and...

Researchers develop tools to help data scientists make the features used in machine-learning models more understandable for end users.

Real-world classification problems must contend with domain shift, the (potential) mismatch between the domain where a model is deployed and the domain(s) where the training data was gathered. Methods to handle such problems must specify what structure is common between the domains and what varies...

Using transfer learning to adapt a pre-trained "source model" to a downstream "target task" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to...

Human communication is increasingly intermixed with language generated by AI. Across chat, email, and social media, AI systems produce smart replies, autocompletes, and translations. AI-generated language is often not identified as such but poses as human language, raising concerns about novel forms...

Depending on how you look at it, drugs that can act on multiple targets could be a boon instead of a challenge

This robotic system uses radio frequency signals, computer vision, and complex reasoning to efficiently find items hidden under a pile.

Scientific research and development relies on the sharing of ideas and artifacts. With the growing reliance on artificial intelligence (AI) for many different applications, the sharing of code, data, and models is important to ensure the ability to replicate methods and the democratization of...

Self-play is a common paradigm for constructing solutions in Markov games that can yield optimal policies in collaborative settings. However, these policies often adopt highly-specialized conventions that make playing with a novel partner difficult. To address this, recent approaches rely on...

Researchers develop a comfortable, form-fitting fabric that recognizes its wearer’s activities, like walking, running, and jumping.

Companies develop AI to gain an advantage over their competition, but this results in flawed products entering the market.

Offline RL algorithms must account for the fact that the dataset they are provided may leave many facets of the environment unknown. The most common way to approach this challenge is to employ pessimistic or conservative methods, which avoid behaviors that are too dissimilar from those in the...

Most deep reinforcement learning (RL) algorithms distill experience into parametric behavior policies or value functions via gradient updates. While effective, this approach has several disadvantages: (1) it is computationally expensive, (2) it can take many updates to integrate experiences into the...