29 citations · 107 across the 19 of their papers we have counts for
19 papers
Findings of the WMT 2023 Shared Task on Discourse-Level Literary Translation: A Fresh Orb in the Cosmos of LLMs
Longyue Wang, Zhaopeng Tu, Yan Gu +14
Translating literary works has perennially stood as an elusive dream in machine translation (MT), a journey steeped in intricate challenges. To foster progress in this domain, we h…
SyzTrust: State-aware Fuzzing on Trusted OS Designed for IoT Devices
Qinying Wang, Boyu Chang, Shouling Ji +8
Trusted Execution Environments (TEEs) embedded in IoT devices provide a deployable solution to secure IoT applications at the hardware level. By design, in TEEs, the Trusted Operat…
On the Cultural Gap in Text-to-Image Generation
Bingshuai Liu, Longyue Wang, Chenyang Lyu +4
One challenge in text-to-image (T2I) generation is the inadvertent reflection of culture gaps present in the training data, which signifies the disparity in generated image quality…
UVSCAN: Detecting Third-Party Component Usage Violations in IoT Firmware
Binbin Zhao, Shouling Ji, Xuhong Zhang +5
Nowadays, IoT devices integrate a wealth of third-party components (TPCs) in firmware to shorten the development cycle. TPCs usually have strict usage specifications, e.g., checkin…
Macaw-LLM: Multi-Modal Language Modeling with Image, Audio, Video, and Text Integration
Chenyang Lyu, Minghao Wu, Longyue Wang +5
Although instruction-tuned large language models (LLMs) have exhibited remarkable capabilities across various NLP tasks, their effectiveness on other data modalities beyond text ha…
Out-of-Distribution Generalization in Text Classification: Past, Present, and Future
Linyi Yang, Yaoxiao Song, Xuan Ren +6
Machine learning (ML) systems in natural language processing (NLP) face significant challenges in generalizing to out-of-distribution (OOD) data, where the test distribution differ…
Is a Video worth Images? A Highly Efficient Approach to Transformer-based Video Question Answering
Chenyang Lyu, Tianbo Ji, Yvette Graham +1
Conventional Transformer-based Video Question Answering (VideoQA) approaches generally encode frames independently through one or more image encoders followed by interaction betwee…
Semantic-aware Dynamic Retrospective-Prospective Reasoning for Event-level Video Question Answering
Chenyang Lyu, Tianbo Ji, Yvette Graham +1
Event-Level Video Question Answering (EVQA) requires complex reasoning across video events to obtain the visual information needed to provide optimal answers. However, despite sign…
A Paradigm Shift: The Future of Machine Translation Lies with Large Language Models
Chenyang Lyu, Zefeng Du, Jitao Xu +7
Machine Translation (MT) has greatly advanced over the years due to the developments in deep neural networks. However, the emergence of Large Language Models (LLMs) like GPT-4 and…
Document-Level Machine Translation with Large Language Models
Longyue Wang, Chenyang Lyu, Tianbo Ji +4
Large language models (LLMs) such as ChatGPT can produce coherent, cohesive, relevant, and fluent answers for various natural language processing (NLP) tasks. Taking document-level…
Dialogue-to-Video Retrieval
Chenyang Lyu, Manh-Duy Nguyen, Van-Tu Ninh +3
Recent years have witnessed an increasing amount of dialogue/conversation on the web especially on social media. That inspires the development of dialogue-based retrieval, in which…
MINER: A Hybrid Data-Driven Approach for REST API Fuzzing
Chenyang Lyu, Jiacheng Xu, Shouling Ji +6
In recent years, REST API fuzzing has emerged to explore errors on a cloud service. Its performance highly depends on the sequence construction and request generation. However, exi…
One Bad Apple Spoils the Barrel: Understanding the Security Risks Introduced by Third-Party Components in IoT Firmware
Binbin Zhao, Shouling Ji, Jiacheng Xu +8
Currently, the development of IoT firmware heavily depends on third-party components (TPCs) to improve development efficiency. Nevertheless, TPCs are not secure, and the vulnerabil…
Exploiting Rich Textual User-Product Context for Improving Sentiment Analysis
Chenyang Lyu, Linyi Yang, Yue Zhang +2
User and product information associated with a review is useful for sentiment polarity prediction. Typical approaches incorporating such information focus on modeling users and pro…
QAScore -- An Unsupervised Unreferenced Metric for the Question Generation Evaluation
Tianbo Ji, Chenyang Lyu, Gareth Jones +2
Question Generation (QG) aims to automate the task of composing questions for a passage with a set of chosen answers found within the passage. In recent years, the introduction of…
Extending the Scope of Out-of-Domain: Examining QA models in multiple subdomains
Chenyang Lyu, Jennifer Foster, Yvette Graham
Past works that investigate out-of-domain performance of QA systems have mainly focused on general domains (e.g. news domain, wikipedia domain), underestimating the importance of s…
Achieving Reliable Human Assessment of Open-Domain Dialogue Systems
Tianbo Ji, Yvette Graham, Gareth J. F. Jones +2
Evaluation of open-domain dialogue systems is highly challenging and development of better techniques is highlighted time and again as desperately needed. Despite substantial effor…
Improving Unsupervised Question Answering via Summarization-Informed Question Generation
Chenyang Lyu, Lifeng Shang, Yvette Graham +3
Question Generation (QG) is the task of generating a plausible question for a given <passage, answer> pair. Template-based QG uses linguistically-informed heuristics to transform d…
Improving Document-Level Sentiment Analysis with User and Product Context
Chenyang Lyu, Jennifer Foster, Yvette Graham
Past work that improves document-level sentiment analysis by encoding user and product information has been limited to considering only the text of the current review. We investiga…