English
Related papers

Related papers: A Unified Data Augmentation Framework for Low-Reso…

200 papers

Single domain generalization (SDG) aims to train a robust model against unknown target domain shifts using data from a single source domain. Data augmentation has been proven an effective approach to SDG. However, the utility of standard…

Computer Vision and Pattern Recognition · Computer Science 2024-02-15 Guangtao Zheng , Mengdi Huai , Aidong Zhang

Spoken dialogue systems allow humans to interact with machines using natural speech. As such, they have many benefits. By using speech as the primary communication medium, a computer interface can facilitate swift, human-like acquisition of…

Computation and Language · Computer Science 2016-09-12 Milica Gasic , Nikola Mrksic , Lina M. Rojas-Barahona , Pei-Hao Su , Stefan Ultes , David Vandyke , Tsung-Hsien Wen , Steve Young

Data augmentation (DA) is crucial to mitigate model training instability and over-fitting problems in low-resource open-domain dialogue generation. However, traditional DA methods often neglect semantic data diversity, restricting the…

Computation and Language · Computer Science 2024-04-02 Zhenhua Liu , Tong Zhu , Jianxiang Xiang , Wenliang Chen

In this work, we address the task of unsupervised domain adaptation (UDA) for semantic segmentation in presence of multiple target domains: The objective is to train a single model that can handle all these domains at test time. Such a…

Computer Vision and Pattern Recognition · Computer Science 2021-09-16 Antoine Saporta , Tuan-Hung Vu , Matthieu Cord , Patrick Pérez

We investigate the task of building open domain, conversational dialogue systems based on large dialogue corpora using generative models. Generative models produce system responses that are autonomously generated word-by-word, opening up…

Computation and Language · Computer Science 2016-04-08 Iulian V. Serban , Alessandro Sordoni , Yoshua Bengio , Aaron Courville , Joelle Pineau

Agnostic domain shift is the main reason of model degradation on the unknown target domains, which brings an urgent need to develop Domain Generalization (DG). Recent advances at DG use dynamic networks to achieve training-free adaptation…

Computer Vision and Pattern Recognition · Computer Science 2023-11-27 Luojun Lin , Zhifeng Shen , Zhishu Sun , Yuanlong Yu , Lei Zhang , Weijie Chen

In recent years, neural networks have proven to be effective in Chinese word segmentation. However, this promising performance relies on large-scale training data. Neural networks with conventional architectures cannot achieve the desired…

Computation and Language · Computer Science 2017-11-07 Jingjing Xu , Xu Sun , Sujian Li , Xiaoyan Cai , Bingzhen Wei

Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping. In this paper, we…

Computer Vision and Pattern Recognition · Computer Science 2023-09-04 Linsen Song , Wayne Wu , Chaoyou Fu , Chen Change Loy , Ran He

While retrieval-augmented generation (RAG) has been shown to enhance factuality of large language model (LLM) outputs, LLMs still suffer from hallucination, generating incorrect or irrelevant information. A common detection strategy…

Computation and Language · Computer Science 2025-03-17 Tobias Leemann , Periklis Petridis , Giuseppe Vietri , Dionysis Manousakas , Aaron Roth , Sergul Aydore

Neural conversation systems generate responses based on the sequence-to-sequence (SEQ2SEQ) paradigm. Typically, the model is equipped with a single set of learned parameters to generate responses for given input contexts. When confronting…

Computation and Language · Computer Science 2020-01-22 Hengyi Cai , Hongshen Chen , Cheng Zhang , Yonghao Song , Xiaofang Zhao , Dawei Yin

Pretrained language models (PLMs) have made remarkable progress in table-to-text generation tasks. However, the lack of domain-specific knowledge makes it challenging to bridge the topological gap between tabular data and text, especially…

Computation and Language · Computer Science 2024-03-28 Zhixin Guo , Minyxuan Yan , Jiexing Qi , Jianping Zhou , Ziwei He , Guanjie Zheng , Xinbing Wang

Deep learning models often struggle to maintain performance when deployed on data distributions different from their training data, particularly in real-world applications where environmental conditions frequently change. While Multi-source…

Machine Learning · Computer Science 2025-05-30 Shohei Enomoto

While multi-party conversations are often less structured than monologues and documents, they are implicitly organized by semantic level correlations across the interactive turns, and dialogue discourse analysis can be applied to predict…

Computation and Language · Computer Science 2021-10-12 Zhengyuan Liu , Nancy F. Chen

Cross-domain aspect-based sentiment analysis (ABSA) aims to perform various fine-grained sentiment analysis tasks on a target domain by transferring knowledge from a source domain. Since labeled data only exists in the source domain, a…

Computation and Language · Computer Science 2023-05-17 Yue Deng , Wenxuan Zhang , Sinno Jialin Pan , Lidong Bing

Despite the impressive capabilities of large language models across various tasks, their continued scaling is severely hampered not only by data scarcity but also by the performance degradation associated with excessive data repetition…

Computation and Language · Computer Science 2025-05-20 Xintong Hao , Ruijie Zhu , Ge Zhang , Ke Shen , Chenggang Li

The performance of task-oriented dialogue models is strongly tied to how well they track dialogue states, which records and updates user information across multi-turn interactions. However, current multi-domain DST encounters two key…

Computation and Language · Computer Science 2026-03-12 Haoxiang Su , Ruiyu Fang , Liting Jiang , Xiaomeng Huang , Shuangyong Song

Most modern approaches for domain adaptive semantic segmentation rely on continued access to source data during adaptation, which may be infeasible due to computational or privacy constraints. We focus on source-free domain adaptation for…

Computer Vision and Pattern Recognition · Computer Science 2022-01-07 Viraj Prabhu , Shivam Khare , Deeksha Kartik , Judy Hoffman

We present M2D2, a fine-grained, massively multi-domain corpus for studying domain adaptation in language models (LMs). M2D2 consists of 8.5B tokens and spans 145 domains extracted from Wikipedia and Semantic Scholar. Using ontologies…

Computation and Language · Computer Science 2022-10-17 Machel Reid , Victor Zhong , Suchin Gururangan , Luke Zettlemoyer

Large-scale e-commercial platforms in the real-world usually contain various recommendation scenarios (domains) to meet demands of diverse customer groups. Multi-Domain Recommendation (MDR), which aims to jointly improve recommendations on…

Information Retrieval · Computer Science 2023-03-08 Linhao Luo , Yumeng Li , Buyu Gao , Shuai Tang , Sinan Wang , Jiancheng Li , Tanchao Zhu , Jiancai Liu , Zhao Li , Shirui Pan

Pre-trained language models have been successfully used in response generation for open-domain dialogue. Four main frameworks have been proposed: (1) Transformer-ED using Transformer encoder and decoder separately for source and target…

Computation and Language · Computer Science 2020-10-27 Yan Zeng , Jian-Yun Nie