Search Results for author: Hengyi Cai

Found 12 papers, 4 papers with code

XL$^2$Bench: A Benchmark for Extremely Long Context Understanding with Long-range Dependencies

no code implementations8 Apr 2024 Xuanfan Ni, Hengyi Cai, Xiaochi Wei, Shuaiqiang Wang, Dawei Yin, Piji Li

However, prior benchmarks create datasets that ostensibly cater to long-text comprehension by expanding the input of traditional tasks, which falls short to exhibit the unique characteristics of long-text understanding, including long dependency tasks and longer text length compatible with modern LLMs' context window size.

Long-Context Understanding Reading Comprehension

Text-Video Retrieval via Variational Multi-Modal Hypergraph Networks

no code implementations6 Jan 2024 Qian Li, Lixin Su, Jiashu Zhao, Long Xia, Hengyi Cai, Suqi Cheng, Hengzhu Tang, Junfeng Wang, Dawei Yin

Compared to conventional textual retrieval, the main obstacle for text-video retrieval is the semantic gap between the textual nature of queries and the visual richness of video content.

Retrieval Variational Inference +1

Towards Verifiable Text Generation with Evolving Memory and Self-Reflection

no code implementations14 Dec 2023 Hao Sun, Hengyi Cai, Bo wang, Yingyan Hou, Xiaochi Wei, Shuaiqiang Wang, Yan Zhang, Dawei Yin

Despite the remarkable ability of large language models (LLMs) in language comprehension and generation, they often suffer from producing factually incorrect information, also known as hallucination.

Hallucination Retrieval +1

Explainability for Large Language Models: A Survey

no code implementations2 Sep 2023 Haiyan Zhao, Hanjie Chen, Fan Yang, Ninghao Liu, Huiqi Deng, Hengyi Cai, Shuaiqiang Wang, Dawei Yin, Mengnan Du

For each paradigm, we summarize the goals and dominant approaches for generating local explanations of individual predictions and global explanations of overall model knowledge.

Answering Ambiguous Questions via Iterative Prompting

1 code implementation8 Jul 2023 Weiwei Sun, Hengyi Cai, Hongshen Chen, Pengjie Ren, Zhumin Chen, Maarten de Rijke, Zhaochun Ren

To provide feasible answers to an ambiguous question, one approach is to directly predict all valid answers, but this can struggle with balancing relevance and diversity.

Open-Domain Question Answering valid

Approximated Doubly Robust Search Relevance Estimation

no code implementations16 Aug 2022 Lixin Zou, Changying Hao, Hengyi Cai, Suqi Cheng, Shuaiqiang Wang, Wenwen Ye, Zhicong Cheng, Simiu Gu, Dawei Yin

We further instantiate the proposed unbiased relevance estimation framework in Baidu search, with comprehensive practical solutions designed regarding the data pipeline for click behavior tracking and online relevance estimation with an approximated deep neural network.


Pre-trained Language Model based Ranking in Baidu Search

no code implementations24 May 2021 Lixin Zou, Shengqiang Zhang, Hengyi Cai, Dehong Ma, Suqi Cheng, Daiting Shi, Zhifan Zhu, Weiyue Su, Shuaiqiang Wang, Zhicong Cheng, Dawei Yin

However, it is nontrivial to directly apply these PLM-based rankers to the large-scale web search system due to the following challenging issues:(1) the prohibitively expensive computations of massive neural PLMs, especially for long texts in the web-document, prohibit their deployments in an online ranking system that demands extremely low latency;(2) the discrepancy between existing ranking-agnostic pre-training objectives and the ad-hoc retrieval scenarios that demand comprehensive relevance modeling is another main barrier for improving the online ranking system;(3) a real-world search engine typically involves a committee of ranking components, and thus the compatibility of the individually fine-tuned ranking model is critical for a cooperative ranking system.

Language Modelling Retrieval

Data Manipulation: Towards Effective Instance Learning for Neural Dialogue Generation via Learning to Augment and Reweight

no code implementations ACL 2020 Hengyi Cai, Hongshen Chen, Yonghao Song, Cheng Zhang, Xiaofang Zhao, Dawei Yin

In this paper, we propose a data manipulation framework to proactively reshape the data distribution towards reliable samples by augmenting and highlighting effective learning samples as well as reducing the effect of inefficient samples simultaneously.

Dialogue Generation

KNPTC: Knowledge and Neural Machine Translation Powered Chinese Pinyin Typo Correction

no code implementations2 May 2018 Hengyi Cai, Xingguang Ji, Yonghao Song, Yan Jin, Yang Zhang, Mairgup Mansur, Xiaofang Zhao

In contrast to previous work, KNPTC is able to integrate explicit knowledge into NMT for pinyin typo correction, and is able to learn to correct a variety of typos without the guidance of manually selected constraints or languagespecific features.

Machine Translation NMT +2

Cannot find the paper you are looking for? You can Submit a new open access paper.