Related papers: Multi-level Contrastive Learning for Script-based …
Subword-level models have been the dominant paradigm in NLP. However, character-level models have the benefit of seeing each character individually, providing the model with more detailed information that ultimately could lead to better…
Most pretrained language models rely on subword tokenization, which processes text as a sequence of subword tokens. However, different granularities of text, such as characters, subwords, and words, can contain different kinds of…
Graph contrastive learning is a general learning paradigm excelling at capturing invariant information from diverse perturbations in graphs. Recent works focus on exploring the structural rationale from graphs, thereby increasing the…
Existing text recognition methods usually need large-scale training data. Most of them rely on synthetic training data due to the lack of annotated real images. However, there is a domain gap between the synthetic data and real data, which…
Generating long, cohesive video stories with consistent characters is a significant challenge for current text-to-video AI. We introduce a method that approaches video generation in a filmmaker-like manner. Instead of creating a video in…
We study cross-lingual stance detection, which aims to leverage labeled data in one language to identify the relative perspective (or stance) of a given document with respect to a claim in a different target language. In particular, we…
Context information in search sessions has proven to be useful for capturing user search intent. Existing studies explored user behavior sequences in sessions in different ways to enhance query suggestion or document ranking. However, a…
Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary…
As the functionality of dialogue systems evolves, hybrid dialogue systems that accomplish user-specific goals and participate in open-topic chitchat with users are attracting growing attention. Existing research learns both tasks…
Social media messages' brevity and unconventional spelling pose a challenge to language identification. We introduce a hierarchical model that learns character and contextualized word-level representations for language identification. Our…
Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into…
Most of the existing works for dialogue generation are data-driven models trained directly on corpora crawled from websites. They mainly focus on improving the model architecture to produce better responses but pay little attention to…
As a safety critical task, autonomous driving requires accurate predictions of road users' future trajectories for safe motion planning, particularly under challenging conditions. Yet, many recent deep learning methods suffer from a…
Sequential recommendation methods play a crucial role in modern recommender systems because of their ability to capture a user's dynamic interest from her/his historical interactions. Despite their success, we argue that these approaches…
Contrastive Language-Image Pretraining (CLIP) has emerged as a novel paradigm to learn visual models from language supervision. While researchers continue to push the frontier of CLIP, reproducing these works remains challenging. This is…
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level…
Semantic segmentation models struggle to generalize in the presence of domain shift. In this paper, we introduce contrastive learning for feature alignment in cross-domain adaptation. We assemble both in-domain contrastive pairs and…
In this paper we present the results of our experiments in training and deploying a self-supervised retrieval-based chatbot trained with contrastive learning for assisting customer support agents. In contrast to most existing research…
Recent progress has been made on developing a unified framework for joint text detection and recognition in natural images, but existing joint models were mostly built on two-stage framework by involving ROI pooling, which can degrade the…
While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem. We propose a novel domain adaptation technique that embodies a multitask framework…