Xuanjing Huang

Gated Recursive Neural Network for Chinese Word Segmentation

2015

Xinchi Chen, Xipeng Qiu, Chenxi Zhu, Xuanjing Huang. Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2015.

Hashtag Recommendation for Multimodal Microblog Using Co-Attention Network

2017

In microblogging services, authors can use hashtags to mark keywords or topics. Many live social media applications (e.g., microblog retrieval, classification) can gain great benefits from these manually labeled tags. However, only a small portion …

A Learning Error Analysis for Structured Prediction with Approximate Inference

2017 · Neural Information Processing Systems

In this work, we try to understand the differences between exact and approximate inference algorithms in structured prediction. We compare the estimation and approximation error of both underestimate and overestimate models. The result shows that, …

Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis

2019 · arXiv (Cornell University)

Cross-domain sentiment analysis is currently a hot topic in the research and engineering areas. One of the most popular frameworks in this field is the domain-invariant representation learning (DIRL) paradigm, which aims to learn a …

Learning Sparse Sharing Architectures for Multiple Tasks

2020 · Proceedings of the AAAI Conference on Artificial Intelligence

Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing. How choosing a suitable sharing mechanism depends on the relations among the tasks, which is …

RethinkCWS: Is Chinese Word Segmentation a Solved Task?

2020

The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models. In this paper, we take …

Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?

2022

Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge. The transfer is more successful between some languages, but it is not well understood what leads …

CausalABSC: Causal Inference for Aspect Debiasing in Aspect-Based Sentiment Classification

2023 · IEEE/ACM Transactions on Audio Speech and Language Processing

As the primary subtask of sentiment analysis, aspect-based sentiment classification (ABSC) aims to predict the sentiment polarity for a given aspect. While recent deep neural models for ABSC have shown good performance, their robustness is …

Hi-ArG: Exploring the Integration of Hierarchical Argumentation Graphs in Language Pretraining

2023

Jingcong Liang, Rong Ye, Meng Han, Qi Zhang, Ruofei Lai, Xinyu Zhang, Zhao Cao, Xuanjing Huang, Zhongyu Wei. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

LLaMA Beyond English: An Empirical Study on Language Capability Transfer

2024 · arXiv (Cornell University)

In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant …

Debatrix: Multi-dimensional Debate Judge with Iterative Chronological Analysis Based on LLM

2024

How can we construct an automated debate judge to evaluate an extensive, vibrant, multiturn debate?This task is challenging, as judging a debate involves grappling with lengthy texts, intricate argument relationships, and multi-dimensional assessments.At the same …

Pre-Trained Policy Discriminators are General Reward Models

2025

We offer a novel perspective on reward modeling by formulating it as a policy discriminator, which quantifies the difference between two policies to generate a reward signal, guiding the training policy towards a target policy …

Long Short-Term Memory Neural Networks for Chinese Word Segmentation

2015

Currently most of state-of-the-art methods for Chinese word segmentation are based on supervised learning, whose features are mostly extracted from a local context.These methods cannot utilize the long distance information which is also crucial for …

Multi-Timescale Long Short-Term Memory Neural Network for Modelling Sentences and Documents

2015

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, it is still a challenge task to model long texts, such as sentences and documents. In this paper, …

Convolutional neural tensor network architecture for community-based question answering

2015 · International Conference on Artificial Intelligence

Retrieving similar questions is very important in community-based question answering. A major challenge is the lexical gap in sentence matching. In this paper, we propose a convolutional neural tensor network architecture to encode the sentences …

Recurrent Neural Network for Text Classification with Multi-Task Learning

2016 · arXiv (Cornell University)

Neural network based methods have obtained great progress on a variety of natural language processing tasks. However, in most previous works, the models are learned based on single-task supervised objectives, which often suffer from insufficient …

Adaptive Co-attention Network for Named Entity Recognition in Tweets

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

In this study, we investigate the problem of named entity recognition for tweets. Named entity recognition is an important task in natural language processing and has been carefully studied in recent decades. Previous named entity …

Task-oriented Dialogue System for Automatic Diagnosis

2018

Zhongyu Wei, Qianlong Liu, Baolin Peng, Huaixiao Tou, Ting Chen, Xuanjing Huang, Kam-fai Wong, Xiangying Dai. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers). 2018.

Generating Responses with a Specific Emotion in Dialog

2019

It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction. After a careful investigation of …

Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation

2019

Disentangling the content and style in the latent space is prevalent in unpaired text style transfer. However, two major issues exist in most of the current neural models. 1) It is difficult to completely strip …

Adversarial Multi-task Learning for Text Classification

2017

Neural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing approaches, the extracted shared features are …

Adversarial Multi-Criteria Learning for Chinese Word Segmentation

2017

Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS). Most existing methods focus on improve the performance for each single criterion. However, it is interesting to exploit these different criteria and …

Searching for Effective Neural Extractive Summarization: What Works and What’s Next

2019

The recent years have seen remarkable success in the use of deep neural networks on text summarization. However, there is no clear understanding of why they perform so well, or how they might be improved. …

CNN-Based Chinese NER with Lexicon Rethinking

2019

Character-level Chinese named entity recognition (NER) that applies long short-term memory (LSTM) to incorporate lexicons has achieved great success. However, this method fails to fully exploit GPU parallelism and candidate lexicons can conflict. In this …

A Lexicon-Based Graph Neural Network for Chinese NER

2019

Tao Gui, Yicheng Zou, Qi Zhang, Minlong Peng, Jinlan Fu, Zhongyu Wei, Xuanjing Huang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language …

GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge

2019

Luyao Huang, Chi Sun, Xipeng Qiu, Xuanjing Huang. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Heterogeneous Graph Neural Networks for Extractive Document Summarization

2020

As a crucial step in extractive document summarization, learning cross-sentence relations has been explored by a plethora of approaches. An intuitive way is to put them in the graphbased neural network, which has a more …

FLAT: Chinese NER Using Flat-Lattice Transformer

2020

Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information. However, since the lattice structure is complex and dynamic, most existing lattice-based models …

Extractive Summarization as Text Matching

2020

This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems. Instead of following the commonly used framework of extracting sentences individually and modeling the relationship between sentences, we …

K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters

2021

We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa. Existing methods typically update the original parameters of pre-trained models when injecting knowledge. However, when multiple kinds of knowledge are …