Related papers: Mask-combine Decoding and Classification Approach …

The relation classification task assigns the proper semantic relation to a pair of subject and object entities; the task plays a crucial role in various text mining applications, such as knowledge graph construction and entities interaction…

Image Captioning, or the automatic generation of descriptions for images, is one of the core problems in Computer Vision and has seen considerable progress using Deep Learning Techniques. We propose to use Inception-ResNet Convolutional…

Context-aware translation can be achieved by processing a concatenation of consecutive sentences with the standard Transformer architecture. This paper investigates the intuitive idea of providing the model with explicit information about…

Segments that span contiguous parts of inputs, such as phonemes in speech, named entities in sentences, actions in videos, occur frequently in sequence prediction problems. Segmental models, a class of models that explicitly hypothesizes…

Pretrained multilingual encoder models can directly perform zero-shot multilingual tasks or linguistic probing by reformulating the input examples into cloze-style prompts. This is accomplished by predicting the probabilities of the label…

Forecast combination involves using multiple forecasts to create a single, more accurate prediction. Recently, feature-based forecasting has been employed to either select the most appropriate forecasting models or to optimize the weights…

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream…

We study a linear contextual optimization problem where a decision maker has access to historical data and contextual features to learn a cost prediction model aimed at minimizing decision error. We adopt the predict-then-optimize framework…

Large language models have been widely applied to sequential recommendation tasks, yet during inference, they continue to rely on decoding strategies developed for natural language processing. This creates a mismatch between text-generation…

Scheduled sampling is widely used to mitigate the exposure bias problem for neural machine translation. Its core motivation is to simulate the inference scene during training by replacing ground-truth tokens with predicted tokens, thus…

In this work, we address the challenging video scene parsing problem by developing effective representation learning methods given limited parsing annotations. In particular, we contribute two novel methods that constitute a unified parsing…

We introduce a new multi-modal task for computer systems, posed as a combined vision-language comprehension challenge: identifying the most suitable text describing a scene, given several similar options. Accomplishing the task entails…

Modern scene text recognition systems often depend on large end-to-end architectures that require extensive training and are prohibitively expensive for real-time scenarios. In such cases, the deployment of heavy models becomes impractical…

Citation texts are sometimes not very informative or in some cases inaccurate by themselves; they need the appropriate context from the referenced paper to reflect its exact contributions. To address this problem, we propose an unsupervised…

Iterative refinement -- start with a random guess, then iteratively improve the guess -- is a useful paradigm for representation learning because it offers a way to break symmetries among equally plausible explanations for the data. This…

Memory-based video object segmentation methods model multiple objects over long temporal-spatial spans by establishing memory bank, which achieve the remarkable performance. However, they struggle to overcome the false matching and are…

Transformers have gained increasing popularity in a wide range of applications, including Natural Language Processing (NLP), Computer Vision and Speech Recognition, because of their powerful representational capacity. However, harnessing…

Current pre-trained cross-lingual sentence encoders approaches use sentence-level objectives only. This can lead to loss of information, especially for tokens, which then degrades the sentence representation. We propose MEXMA, a novel…

We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we develop two general approaches for an important…

Regression, the task of predicting a continuous scalar target y based on some features x is one of the most fundamental tasks in machine learning and statistics. It has been observed and theoretically analyzed that the classical approach,…