Search Results for author: Houfeng Wang

Found 71 papers, 17 papers with code

Multi-Layer Pseudo-Siamese Biaffine Model for Dependency Parsing

1 code implementation COLING 2022 Ziyao Xu, Houfeng Wang, Bingdong Wang

However, previous work only used the biaffine method at the end of the dependency parser as a scorer, and its application in multi-layer form is ignored.

Dependency Parsing

Original Content Is All You Need! an Empirical Study on Leveraging Answer Summary for WikiHowQA Answer Selection Task

no code implementations COLING 2022 Liang Wen, Juan Li, Houfeng Wang, Yingwei Luo, Xiaolin Wang, Xiaodong Zhang, Zhicong Cheng, Dawei Yin

And their experiments show that leveraging the answer summaries helps to attend the essential information in original lengthy answers and improve the answer selection performance under certain circumstances.

Answer Selection

Adjusting the Precision-Recall Trade-Off with Align-and-Predict Decoding for Grammatical Error Correction

1 code implementation ACL 2022 Xin Sun, Houfeng Wang

Modern writing assistance applications are always equipped with a Grammatical Error Correction (GEC) model to correct errors in user-entered sentences.

Grammatical Error Correction

Preference Ranking Optimization for Human Alignment

no code implementations30 Jun 2023 Feifan Song, Bowen Yu, Minghao Li, Haiyang Yu, Fei Huang, Yongbin Li, Houfeng Wang

In this paper, we propose Preference Ranking Optimization (PRO) as an alternative to PPO for directly aligning LLMs with the Bradley-Terry comparison.

Semiparametric Language Models Are Scalable Continual Learners

no code implementations2 Mar 2023 Guangyue Peng, Tao Ge, Si-Qing Chen, Furu Wei, Houfeng Wang

We demonstrate that SeMem improves the scalability of semiparametric LMs for continual learning over streaming data in two ways: (1) data-wise scalability: as the model becomes stronger through continual learning, it will encounter fewer difficult cases that need to be memorized, causing the growth of the non-parametric memory to slow down over time rather than growing at a linear rate with the size of training data; (2) model-wise scalability: SeMem allows a larger model to memorize fewer samples than its smaller counterpart because it is rarer for a larger model to encounter incomprehensible cases, resulting in a non-parametric memory that does not scale linearly with model size.

Continual Learning Language Modelling +1

HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification

1 code implementation28 Apr 2022 Zihan Wang, Peiyi Wang, Tianyu Liu, Binghuai Lin, Yunbo Cao, Zhifang Sui, Houfeng Wang

However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potentials of PLMs can not be fully tapped.

Language Modelling Multi-Label Classification +2

Confidence Calibration for Intent Detection via Hyperspherical Space and Rebalanced Accuracy-Uncertainty Loss

no code implementations17 Mar 2022 Yantao Gong, Cao Liu, Fan Yang, Xunliang Cai, Guanglu Wan, Jiansong Chen, Weipeng Zhang, Houfeng Wang

Experiments on the open datasets verify that our model outperforms the existing calibration methods and achieves a significant improvement on the calibration metric.

Intent Detection

Using calibrator to improve robustness in Machine Reading Comprehension

no code implementations24 Feb 2022 Jing Jin, Houfeng Wang

Machine Reading Comprehension(MRC) has achieved a remarkable result since some powerful models, such as BERT, are proposed.

Machine Reading Comprehension Representation Learning

Zero-shot Cross-lingual Transfer of Prompt-based Tuning with a Unified Multilingual Prompt

1 code implementation23 Feb 2022 Lianzhe Huang, Shuming Ma, Dongdong Zhang, Furu Wei, Houfeng Wang

To collocate with the unified prompt, we propose a new initialization method for the target label word to further improve the model's transferability across languages.

Zero-Shot Cross-Lingual Transfer

A Unified Strategy for Multilingual Grammatical Error Correction with Pre-trained Cross-Lingual Language Model

no code implementations26 Jan 2022 Xin Sun, Tao Ge, Shuming Ma, Jingjing Li, Furu Wei, Houfeng Wang

Synthetic data construction of Grammatical Error Correction (GEC) for non-English languages relies heavily on human-designed and language-specific rules, which produce limited error-corrected patterns.

Grammatical Error Correction Language Modelling +2

Towards Controlled and Diverse Generation of Article Comments

no code implementations25 Jul 2021 Linhao Zhang, Houfeng Wang

In this paper, we make the first step towards controllable generation of comments, by building a system that can explicitly control the emotion of the generated comments.

Comment Generation

A Joint and Domain-Adaptive Approach to Spoken Language Understanding

no code implementations25 Jul 2021 Linhao Zhang, Yu Shi, Linjun Shou, Ming Gong, Houfeng Wang, Michael Zeng

In this paper, we attempt to bridge these two lines of research and propose a joint and domain adaptive approach to SLU.

Domain Adaptation Intent Detection +3

Learn to Focus: Hierarchical Dynamic Copy Network for Dialogue State Tracking

no code implementations25 Jul 2021 Linhao Zhang, Houfeng Wang

Recently, researchers have explored using the encoder-decoder framework to tackle dialogue state tracking (DST), which is a key component of task-oriented dialogue systems.

Dialogue State Tracking Task-Oriented Dialogue Systems

Instantaneous Grammatical Error Correction with Shallow Aggressive Decoding

1 code implementation ACL 2021 Xin Sun, Tao Ge, Furu Wei, Houfeng Wang

In this paper, we propose Shallow Aggressive Decoding (SAD) to improve the online inference efficiency of the Transformer for instantaneous Grammatical Error Correction (GEC).

Grammatical Error Correction

First Target and Opinion then Polarity: Enhancing Target-opinion Correlation for Aspect Sentiment Triplet Extraction

no code implementations17 Feb 2021 Lianzhe Huang, Peiyi Wang, Sujian Li, Tianyu Liu, Xiaodong Zhang, Zhicong Cheng, Dawei Yin, Houfeng Wang

Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from a sentence, including target entities, associated sentiment polarities, and opinion spans which rationalize the polarities.

Aspect Sentiment Triplet Extraction

Improving Machine Translation by Searching Skip Connections Efficiently

no code implementations1 Jan 2021 Chen Yang, Houfeng Wang

To improve the efficiency of trying different skip connection architectures, we apply the idea of network morphism to add skip connections as a procedure of fine-tuning.

Machine Translation Translation

Syntax-Aware Graph Attention Network for Aspect-Level Sentiment Classification

no code implementations COLING 2020 Lianzhe Huang, Xin Sun, Sujian Li, Linhao Zhang, Houfeng Wang

In this paper, we exploit syntactic awareness to the model by the graph attention network on the dependency tree structure and external pre-training knowledge by BERT language model, which helps to model the interaction between the context and aspect words better.

Classification Graph Attention +3

Text Level Graph Neural Network for Text Classification

2 code implementations IJCNLP 2019 Lianzhe Huang, Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang

Recently, researches have explored the graph neural network (GNN) techniques on text classification, since GNN does well in handling complex structures and preserving global information.

General Classification text-classification +1

Exploring Sequence-to-Sequence Learning in Aspect Term Extraction

no code implementations ACL 2019 Dehong Ma, Sujian Li, Fangzhao Wu, Xing Xie, Houfeng Wang

Aspect term extraction (ATE) aims at identifying all aspect terms in a sentence and is usually modeled as a sequence labeling problem.

Term Extraction

Phrase-level Self-Attention Networks for Universal Sentence Encoding

no code implementations EMNLP 2018 Wei Wu, Houfeng Wang, Tianyu Liu, Shuming Ma

As a result, the memory consumption can be reduced because the self-attention is performed at the phrase level instead of the sentence level.

Multi-class Classification Natural Language Inference +3

Joint Learning for Targeted Sentiment Analysis

no code implementations EMNLP 2018 Dehong Ma, Sujian Li, Houfeng Wang

Targeted sentiment analysis (TSA) aims at extracting targets and classifying their sentiment classes.

Sentiment Analysis Word Embeddings

Sememe Prediction: Learning Semantic Knowledge from Unstructured Textual Wiki Descriptions

no code implementations16 Aug 2018 Wei Li, Xuancheng Ren, Damai Dai, Yunfang Wu, Houfeng Wang, Xu sun

In the experiments, we take a real-world sememe knowledge base HowNet and the corresponding descriptions of the words in Baidu Wiki for training and evaluation.


A Neural Question Answering Model Based on Semi-Structured Tables

no code implementations COLING 2018 Hao Wang, Xiaodong Zhang, Shuming Ma, Xu sun, Houfeng Wang, Mengxiang Wang

Then the system measures the relevance between each question and candidate table cells, and choose the most related cell as the source of answer.

Knowledge Graphs Multiple-choice +1

SGM: Sequence Generation Model for Multi-label Classification

1 code implementation COLING 2018 Pengcheng Yang, Xu sun, Wei Li, Shuming Ma, Wei Wu, Houfeng Wang

Further analysis of experimental results demonstrates that the proposed methods not only capture the correlations between labels, but also select the most informative words automatically when predicting different labels.

Classification General Classification +1

Training Simplification and Model Simplification for Deep Learning: A Minimal Effort Back Propagation Method

3 code implementations17 Nov 2017 Xu Sun, Xuancheng Ren, Shuming Ma, Bingzhen Wei, Wei Li, Jingjing Xu, Houfeng Wang, Yi Zhang

Based on the sparsified gradients, we further simplify the model by eliminating the rows or columns that are seldom updated, which will reduce the computational cost both in the training and decoding, and potentially accelerate decoding in real-world applications.

Addressing Domain Adaptation for Chinese Word Segmentation with Global Recurrent Structure

no code implementations IJCNLP 2017 Shen Huang, Xu sun, Houfeng Wang

Boundary features are widely used in traditional Chinese Word Segmentation (CWS) methods as they can utilize unlabeled data to help improve the Out-of-Vocabulary (OOV) word recognition performance.

Chinese Word Segmentation Domain Adaptation +2

Interactive Attention Networks for Aspect-Level Sentiment Classification

5 code implementations4 Sep 2017 Dehong Ma, Sujian Li, Xiaodong Zhang, Houfeng Wang

In this paper, we argue that both targets and contexts deserve special treatment and need to be learned their own representations via interactive learning.

Aspect-Based Sentiment Analysis (ABSA) Classification +2

Noise-Clustered Distant Supervision for Relation Extraction: A Nonparametric Bayesian Perspective

no code implementations EMNLP 2017 Qing Zhang, Houfeng Wang

For the task of relation extraction, distant supervision is an efficient approach to generate labeled data by aligning knowledge base with free texts.

General Classification Matrix Completion +2

A Two-Stage Parsing Method for Text-Level Discourse Analysis

1 code implementation ACL 2017 Yizhong Wang, Sujian Li, Houfeng Wang

Previous work introduced transition-based algorithms to form a unified architecture of parsing rhetorical structures (including span, nuclearity and relation), but did not achieve satisfactory performance.

Dependency Parsing Document Summarization +2

meProp: Sparsified Back Propagation for Accelerated Deep Learning with Reduced Overfitting

2 code implementations ICML 2017 Xu Sun, Xuancheng Ren, Shuming Ma, Houfeng Wang

In back propagation, only a small subset of the full gradient is computed to update the model parameters.

Bi-LSTM Neural Networks for Chinese Grammatical Error Diagnosis

no code implementations WS 2016 Shen Huang, Houfeng Wang

Grammatical Error Diagnosis for Chinese has always been a challenge for both foreign learners and NLP researchers, for the variousity of grammar and the flexibility of expression.

Grammatical Error Detection Word Embeddings

Towards Label Imbalance in Multi-label Classification with Many Labels

no code implementations5 Apr 2016 Li Li, Houfeng Wang

To the best of our knowledge, we are the first to tackle the imbalance problem in multi-label classification with many labels.

Classification General Classification +2

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