Search Results for author: Alexander Hanbo Li

Found 11 papers, 3 papers with code

Contextual Rephrase Detection for Reducing Friction in Dialogue Systems

no code implementations EMNLP 2021 Zhuoyi Wang, Saurabh Gupta, Jie Hao, Xing Fan, Dingcheng Li, Alexander Hanbo Li, Chenlei Guo

Rephrase detection is used to identify the rephrases and has long been treated as a task with pairwise input, which does not fully utilize the contextual information (e. g. users’ implicit feedback).

Learning to Selectively Learn for Weakly-supervised Paraphrase Generation

no code implementations EMNLP 2021 Kaize Ding, Dingcheng Li, Alexander Hanbo Li, Xing Fan, Chenlei Guo, Yang Liu, Huan Liu

In this work, we go beyond the existing paradigms and propose a novel approach to generate high-quality paraphrases with weak supervision data.

Language Modelling Meta-Learning +1

Dual Reader-Parser on Hybrid Textual and Tabular Evidence for Open Domain Question Answering

1 code implementation ACL 2021 Alexander Hanbo Li, Patrick Ng, Peng Xu, Henghui Zhu, Zhiguo Wang, Bing Xiang

However, a large amount of world's knowledge is stored in structured databases, and need to be accessed using query languages such as SQL.

Open-Domain Question Answering

Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training

3 code implementations18 Dec 2020 Peng Shi, Patrick Ng, Zhiguo Wang, Henghui Zhu, Alexander Hanbo Li, Jun Wang, Cicero Nogueira dos santos, Bing Xiang

Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM).

Language Modelling Self-Supervised Learning +2

Decomposed Adversarial Learned Inference

no code implementations21 Apr 2020 Alexander Hanbo Li, Yaqing Wang, Changyou Chen, Jing Gao

Effective inference for a generative adversarial model remains an important and challenging problem.

Censored Quantile Regression Forest

no code implementations8 Jan 2020 Alexander Hanbo Li, Jelena Bradic

Random forests are powerful non-parametric regression method but are severely limited in their usage in the presence of randomly censored observations, and naively applied can exhibit poor predictive performance due to the incurred biases.

Semi-Supervised Learning for Text Classification by Layer Partitioning

no code implementations26 Nov 2019 Alexander Hanbo Li, Abhinav Sethy

In this way, $F$ serves as a feature extractor that maps the input to high-level representation and adds systematical noise using dropout.

Classification General Classification +1

Knowledge Enhanced Attention for Robust Natural Language Inference

no code implementations31 Aug 2019 Alexander Hanbo Li, Abhinav Sethy

Neural network models have been very successful at achieving high accuracy on natural language inference (NLI) tasks.

Natural Language Inference

Censored Quantile Regression Forests

1 code implementation8 Feb 2019 Alexander Hanbo Li, Jelena Bradic

Random forests are powerful non-parametric regression method but are severely limited in their usage in the presence of randomly censored observations, and naively applied can exhibit poor predictive performance due to the incurred biases.

Forest-type Regression with General Losses and Robust Forest

no code implementations ICML 2017 Alexander Hanbo Li, Andrew Martin

This paper introduces a new general framework for forest-type regression which allows the development of robust forest regressors by selecting from a large family of robust loss functions.

Boosting in the presence of outliers: adaptive classification with non-convex loss functions

no code implementations5 Oct 2015 Alexander Hanbo Li, Jelena Bradic

Along with the Arch Boosting framework, the non-convex losses lead to the new class of boosting algorithms, named adaptive, robust, boosting (ARB).

General Classification

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