Search Results for author: Pengxiang Cheng

Found 10 papers, 5 papers with code

Unsupervised Contrast-Consistent Ranking with Language Models

no code implementations13 Sep 2023 Niklas Stoehr, Pengxiang Cheng, Jing Wang, Daniel Preotiuc-Pietro, Rajarshi Bhowmik

Recent work focuses on pairwise, pointwise, and listwise prompting techniques to elicit a language model's ranking knowledge.

Language Modelling

Overcoming Catastrophic Forgetting in Massively Multilingual Continual Learning

no code implementations25 May 2023 Genta Indra Winata, Lingjue Xie, Karthik Radhakrishnan, Shijie Wu, Xisen Jin, Pengxiang Cheng, Mayank Kulkarni, Daniel Preotiuc-Pietro

Real-life multilingual systems should be able to efficiently incorporate new languages as data distributions fed to the system evolve and shift over time.

Continual Learning Scheduling

Bounding System-Induced Biases in Recommender Systems with A Randomized Dataset

1 code implementation21 Mar 2023 Dugang Liu, Pengxiang Cheng, Zinan Lin, Xiaolian Zhang, Zhenhua Dong, Rui Zhang, Xiuqiang He, Weike Pan, Zhong Ming

To bridge this gap, we study the debiasing problem from a new perspective and propose to directly minimize the upper bound of an ideal objective function, which facilitates a better potential solution to the system-induced biases.

Recommendation Systems

Dataless Knowledge Fusion by Merging Weights of Language Models

1 code implementation19 Dec 2022 Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, Pengxiang Cheng

In this paper, we study the problem of merging individual models built on different training data sets to obtain a single model that performs well both across all data set domains and can generalize on out-of-domain data.

Multi-Task Learning

DIWIFT: Discovering Instance-wise Influential Features for Tabular Data

no code implementations6 Jul 2022 Dugang Liu, Pengxiang Cheng, Hong Zhu, Xing Tang, Yanyu Chen, Xiaoting Wang, Weike Pan, Zhong Ming, Xiuqiang He

Tabular data is one of the most common data storage formats behind many real-world web applications such as retail, banking, and e-commerce.

feature selection

MetaSelector: Meta-Learning for Recommendation with User-Level Adaptive Model Selection

no code implementations22 Jan 2020 Mi Luo, Fei Chen, Pengxiang Cheng, Zhenhua Dong, Xiuqiang He, Jiashi Feng, Zhenguo Li

Recommender systems often face heterogeneous datasets containing highly personalized historical data of users, where no single model could give the best recommendation for every user.

Meta-Learning Model Selection +1

Attending to Entities for Better Text Understanding

no code implementations11 Nov 2019 Pengxiang Cheng, Katrin Erk

Recent progress in NLP witnessed the development of large-scale pre-trained language models (GPT, BERT, XLNet, etc.)


Implicit Argument Prediction as Reading Comprehension

1 code implementation8 Nov 2018 Pengxiang Cheng, Katrin Erk

Implicit arguments, which cannot be detected solely through syntactic cues, make it harder to extract predicate-argument tuples.

Reading Comprehension

Implicit Argument Prediction with Event Knowledge

1 code implementation NAACL 2018 Pengxiang Cheng, Katrin Erk

Implicit arguments are not syntactically connected to their predicates, and are therefore hard to extract.

Representing Meaning with a Combination of Logical and Distributional Models

1 code implementation CL 2016 I. Beltagy, Stephen Roller, Pengxiang Cheng, Katrin Erk, Raymond J. Mooney

In this paper, we focus on the three components of a practical system integrating logical and distributional models: 1) Parsing and task representation is the logic-based part where input problems are represented in probabilistic logic.

Lexical Entailment Natural Language Inference +1

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