Search for: All records

Translating culture-related content is vital for effective cross-cultural communication. However, many culture-specific items (CSIs) often lack viable translations across languages, making it challenging to collect high-quality, diverse parallel corpora with CSI annotations. This difficulty hinders the analysis of cultural awareness of machine translation (MT) systems, including traditional neural MT and the emerging MT paradigm using large language models (LLM). To address this gap, we introduce a novel parallel corpus, enriched with CSI annotations in 6 language pairs for investigating Culturally-Aware Machine Translation---CAMT. Furthermore, we design two evaluation metrics to assess CSI translations, focusing on their pragmatic translation quality. Our findings show the superior ability of LLMs over neural MTs in leveraging external cultural knowledge for translating CSIs, especially those lacking translations in the target culture. 

Recent advances in Large Language Models (LLMs) show the potential to significantly augment or even replace complex human writing activities. However, for complex tasks where people need to make decisions as well as write a justification, the trade offs between making work efficient and hindering decisions remain unclear. In this paper, we explore this question in the context of designing intelligent scaffolding for writing meta-reviews for an academic peer review process. We prototyped a system called MetaWriter'' trained on five years of open peer review data to support meta-reviewing. The system highlights common topics in the original peer reviews, extracts key points by each reviewer, and on request, provides a preliminary draft of a meta-review that can be further edited. To understand how novice and experienced meta-reviewers use MetaWriter, we conducted a within-subject study with 32 participants. Each participant wrote meta-reviews for two papers: one with and one without MetaWriter. We found that MetaWriter significantly expedited the authoring process and improved the coverage of meta-reviews, as rated by experts, compared to the baseline. While participants recognized the efficiency benefits, they raised concerns around trust, over-reliance, and agency. We also interviewed six paper authors to understand their opinions of using machine intelligence to support the peer review process and reported critical reflections. We discuss implications for future interactive AI writing tools to support complex synthesis work. 

We present a two-photon fluorescence microscope designed for high-speed imaging of neural activity at cellular resolution. Our microscope uses an adaptive sampling scheme with line illumination. Instead of building images pixel by pixel via scanning a diffraction-limited spot across the sample, our scheme only illuminates the regions of interest (i.e., neuronal cell bodies) and samples a large area of them in a single measurement. Such a scheme significantly increases the imaging speed and reduces the overall laser power on the brain tissue. Using this approach, we performed high-speed imaging of the neuronal activity in mouse cortexin vivo. Our method provides a sampling strategy in laser-scanning two-photon microscopy and will be powerful for high-throughput imaging of neural activity. 

We demonstrate a high-speed two-photon fluorescence microscope using line illumination with an adaptive sampling scheme. The illumination pattern is modulated by a digital micro-mirror device so only the regions of interest are illuminated and sampled. 

We present a new deep compressed imaging modality by scanning a learned illumination pattern on the sample and detecting the signal with a single-pixel detector. This new imaging modality allows a compressed sampling of the object, and thus a high imaging speed. The object is reconstructed through a deep neural network inspired by compressed sensing algorithm. We optimize the illumination pattern and the image reconstruction network by training an end-to-end auto-encoder framework. Comparing with the conventional single-pixel camera and point-scanning imaging system, we accomplish a high-speed imaging with a reduced light dosage, while preserving a high imaging quality. 

The need for high-speed imaging in applications such as biomedicine, surveillance, and consumer electronics has called for new developments of imaging systems. While the industrial effort continuously pushes the advance of silicon focal plane array image sensors, imaging through a single-pixel detector has gained significant interest thanks to the development of computational algorithms. Here, we present a new imaging modality, deep compressed imaging via optimized-pattern scanning, which can significantly increase the acquisition speed for a single-detector-based imaging system. We project and scan an illumination pattern across the object and collect the sampling signal with a single-pixel detector. We develop an innovative end-to-end optimized auto-encoder, using a deep neural network and compressed sensing algorithm, to optimize the illumination pattern, which allows us to reconstruct faithfully the image from a small number of measurements, with a high frame rate. Compared with the conventional switching-mask-based single-pixel camera and point-scanning imaging systems, our method achieves a much higher imaging speed, while retaining a similar imaging quality. We experimentally validated this imaging modality in the settings of both continuous-wave illumination and pulsed light illumination and showed high-quality image reconstructions with a high compressed sampling rate. This new compressed sensing modality could be widely applied in different imaging systems, enabling new applications that require high imaging speeds. 

We propose a new imaging scheme of compressed sensing by scanning an illumination pattern on the object. Comparing with conventional single-pixel cameras, we expect a >50x increase in imaging speed with similar imaging quality. 

Intelligent personal assistant systems, with either text-based or voice-based conversational interfaces, are becoming increasingly popular. Most previous research has used either retrieval-based or generation-based methods. Retrieval-based methods have the advantage of returning fluent and informative responses with great diversity. The retrieved responses are easier to control and explain. However, the response retrieval performance is limited by the size of the response repository. On the other hand, although generation-based methods can return highly coherent responses given conversation context, they are likely to return universal or general responses with insufficient ground knowledge information. In this paper, we build a hybrid neural conversation model with the capability of both response retrieval and generation, in order to combine the merits of these two types of methods. Experimental results on Twitter and Foursquare data show that the proposed model can outperform both retrieval-based methods and generation-based methods (including a recently proposed knowledge-grounded neural conversation model) under both automatic evaluation metrics and human evaluation. Our models and research findings provide new insights on how to integrate text retrieval and text generation models for building conversation systems.