Large language models (LLMs) demonstrate remarkable ability to comprehen...
k-Nearest neighbor machine translation (kNN-MT) has attracted increasing...
Keyphrase prediction aims to generate phrases (keyphrases) that highly
s...
Video Panoptic Segmentation (VPS) aims to achieve comprehensive pixel-le...
Fine-grained information on translation errors is helpful for the transl...
Neural machine translation (NMT) is often criticized for failures that h...
Keyphrase generation aims to automatically generate short phrases summar...
In this paper, we present our submission to the sentence-level MQM bench...
In this report, we present our submission to the WMT 2022 Metrics Shared...
Estimating heterogeneous treatment effects is a well-studied topic in th...
We present TubeFormer-DeepLab, the first attempt to tackle multiple core...
End-to-End Speech Translation (E2E-ST) has received increasing attention...
Attribute-based Controlled Text Generation (CTG) refers to generating
se...
This paper develops automatic song translation (AST) for tonal languages...
Recently, lane detection has made great progress in autonomous driving. ...
The operation of urban transportation produces massive traffic data, whi...
End-to-end speech-to-text translation (E2E-ST) is becoming increasingly
...
For the last few decades, several major subfields of artificial intellig...
We study the problem of online learning with human feedback in the
human...
Recently, kNN-MT has shown the promising capability of directly
incorpor...
Zero-shot translation, directly translating between language pairs unsee...
Translating e-commercial product descriptions, a.k.a product-oriented ma...
In this paper, we consider the use of large-scale genomics data for trea...
DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a
...
In this paper, we tackle video panoptic segmentation, a task that requir...
Simile recognition is to detect simile sentences and to extract simile
c...
Neural machine translation systems tend to fail on less de-cent inputs
d...
In this study, we first investigate a novel capsule network with dynamic...
Combining individual p-values to aggregate multiple small effects has a
...
Semantic Role Labeling (SRL) is believed to be a crucial step towards na...
Semantic annotations are vital for training models for object recognitio...
Image deblurring techniques play important roles in many image processin...
Video enhancement plays an important role in various video applications....