Search Results for author: Zhifang Sui

Found 76 papers, 27 papers with code

A Survey for In-context Learning

1 code implementation31 Dec 2022 Qingxiu Dong, Damai Dai, Ce Zheng, Zhiyong Wu, Baobao Chang, Xu sun, Jingjing Xu, Lei LI, Zhifang Sui

With the increasing ability of large language models (LLMs), in-context learning (ICL) has become a new paradigm for natural language processing (NLP), where LLMs make predictions only based on contexts augmented with a few training examples.

Why Can GPT Learn In-Context? Language Models Secretly Perform Gradient Descent as Meta-Optimizers

1 code implementation20 Dec 2022 Damai Dai, Yutao Sun, Li Dong, Yaru Hao, Zhifang Sui, Furu Wei

In order to better understand how ICL works, this paper explains language models as meta-optimizers and understands ICL as a kind of implicit finetuning.

Pretrained Language Models

Statistical Dataset Evaluation: Reliability, Difficulty, and Validity

no code implementations19 Dec 2022 Chengwen Wang, Qingxiu Dong, Xiaochen Wang, Haitao Wang, Zhifang Sui

Taking the Named Entity Recognition (NER) datasets as a case study, we introduce $9$ statistical metrics for a statistical dataset evaluation framework.

named-entity-recognition NER

DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog

no code implementations14 Dec 2022 Xin Zheng, Tianyu Liu, Haoran Meng, Xu Wang, Yufan Jiang, Mengliang Rao, Binghuai Lin, Zhifang Sui, Yunbo Cao

Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios.

Retrieval

Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation

1 code implementation10 Oct 2022 Peiyi Wang, YiFan Song, Tianyu Liu, Binghuai Lin, Yunbo Cao, Sujian Li, Zhifang Sui

In this paper, through empirical studies we argue that this assumption may not hold, and an important reason for catastrophic forgetting is that the learned representations do not have good robustness against the appearance of analogous relations in the subsequent learning process.

Continual Relation Extraction

Neural Knowledge Bank for Pretrained Transformers

no code implementations31 Jul 2022 Damai Dai, Wenbin Jiang, Qingxiu Dong, Yajuan Lyu, Qiaoqiao She, Zhifang Sui

The ability of pretrained Transformers to remember factual knowledge is essential but still limited for existing models.

Language Modelling Machine Translation +2

A Two-Stream AMR-enhanced Model for Document-level Event Argument Extraction

1 code implementation NAACL 2022 Runxin Xu, Peiyi Wang, Tianyu Liu, Shuang Zeng, Baobao Chang, Zhifang Sui

In this paper, we focus on extracting event arguments from an entire document, which mainly faces two critical problems: a) the long-distance dependency between trigger and arguments over sentences; b) the distracting context towards an event in the document.

Document-level Event Extraction Event Argument Extraction +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.

Classification Language Modelling +4

ATP: AMRize Then Parse! Enhancing AMR Parsing with PseudoAMRs

2 code implementations Findings (NAACL) 2022 Liang Chen, Peiyi Wang, Runxin Xu, Tianyu Liu, Zhifang Sui, Baobao Chang

As Abstract Meaning Representation (AMR) implicitly involves compound semantic annotations, we hypothesize auxiliary tasks which are semantically or formally related can better enhance AMR parsing.

Ranked #6 on AMR Parsing on LDC2017T10 (using extra training data)

AMR Parsing Dependency Parsing +1

StableMoE: Stable Routing Strategy for Mixture of Experts

1 code implementation ACL 2022 Damai Dai, Li Dong, Shuming Ma, Bo Zheng, Zhifang Sui, Baobao Chang, Furu Wei

We point out that existing learning-to-route MoE methods suffer from the routing fluctuation issue, i. e., the target expert of the same input may change along with training, but only one expert will be activated for the input during inference.

Language Modelling Machine Translation

Mixture of Experts for Biomedical Question Answering

no code implementations15 Apr 2022 Damai Dai, Wenbin Jiang, Jiyuan Zhang, Weihua Peng, Yajuan Lyu, Zhifang Sui, Baobao Chang, Yong Zhu

In this paper, in order to alleviate the parameter competition problem, we propose a Mixture-of-Expert (MoE) based question answering method called MoEBQA that decouples the computation for different types of questions by sparse routing.

Question Answering

Lossless Speedup of Autoregressive Translation with Generalized Aggressive Decoding

1 code implementation30 Mar 2022 Heming Xia, Tao Ge, Furu Wei, Zhifang Sui

Different from previous work accelerating translation at the cost of quality loss, we propose Generalized Aggressive Decoding (GAD) -- a novel decoding paradigm for lossless speedup of autoregressive translation, through the collaboration of autoregressive and non-autoregressive translation (NAT) of the Transformer.

Abstractive Text Summarization Translation

Hierarchical Curriculum Learning for AMR Parsing

1 code implementation ACL 2022 Peiyi Wang, Liang Chen, Tianyu Liu, Damai Dai, Yunbo Cao, Baobao Chang, Zhifang Sui

Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.

AMR Parsing Representation Learning

An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling

1 code implementation NAACL 2022 Peiyi Wang, Runxin Xu, Tianyu Liu, Qingyu Zhou, Yunbo Cao, Baobao Chang, Zhifang Sui

Few-Shot Sequence Labeling (FSSL) is a canonical paradigm for the tagging models, e. g., named entity recognition and slot filling, to generalize on an emerging, resource-scarce domain.

Few-shot NER Meta-Learning +3

Behind the Scenes: An Exploration of Trigger Biases Problem in Few-Shot Event Classification

1 code implementation29 Aug 2021 Peiyi Wang, Runxin Xu, Tianyu Liu, Damai Dai, Baobao Chang, Zhifang Sui

However, we find they suffer from trigger biases that signify the statistical homogeneity between some trigger words and target event types, which we summarize as trigger overlapping and trigger separability.

Explicit Interaction Network for Aspect Sentiment Triplet Extraction

no code implementations21 Jun 2021 Peiyi Wang, Tianyu Liu, Damai Dai, Runxin Xu, Baobao Chang, Zhifang Sui

Table encoder extracts sentiment at token-pair level, so that the compositional feature between targets and opinions can be easily captured.

Aspect Sentiment Triplet Extraction

Decompose, Fuse and Generate: A Formation-Informed Method for Chinese Definition Generation

no code implementations NAACL 2021 Hua Zheng, Damai Dai, Lei LI, Tianyu Liu, Zhifang Sui, Baobao Chang, Yang Liu

In this paper, we tackle the task of Definition Generation (DG) in Chinese, which aims at automatically generating a definition for a word.

Problems and Countermeasures in Natural Language Processing Evaluation

no code implementations20 Apr 2021 Qingxiu Dong, Zhifang Sui, Weidong Zhan, Baobao Chang

Starting from the concept, com-position, development and meaning of natural language evaluation, this article classifies and summarizes the tasks and char-acteristics of mainstream natural language evaluation, and then summarizes the problems and causes of natural language pro-cessing evaluation.

Knowledge Neurons in Pretrained Transformers

3 code implementations ACL 2022 Damai Dai, Li Dong, Yaru Hao, Zhifang Sui, Baobao Chang, Furu Wei

In this paper, we present preliminary studies on how factual knowledge is stored in pretrained Transformers by introducing the concept of knowledge neurons.

Pretrained Language Models

A Token-level Reference-free Hallucination Detection Benchmark for Free-form Text Generation

2 code implementations ACL 2022 Tianyu Liu, Yizhe Zhang, Chris Brockett, Yi Mao, Zhifang Sui, Weizhu Chen, Bill Dolan

Large pretrained generative models like GPT-3 often suffer from hallucinating non-existent or incorrect content, which undermines their potential merits in real applications.

Text Generation

Incorporating Connections Beyond Knowledge Embeddings: A Plug-and-Play Module to Enhance Commonsense Reasoning in Machine Reading Comprehension

no code implementations26 Mar 2021 Damai Dai, Hua Zheng, Zhifang Sui, Baobao Chang

Conventional Machine Reading Comprehension (MRC) has been well-addressed by pattern matching, but the ability of commonsense reasoning remains a gap between humans and machines.

Knowledge Graph Embeddings Knowledge Graphs +1

Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View

1 code implementation17 Feb 2021 Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui

In open domain table-to-text generation, we notice that the unfaithful generation usually contains hallucinated content which can not be aligned to any input table record.

Few-Shot Learning Table-to-Text Generation

Coarse-to-Fine Entity Representations for Document-level Relation Extraction

1 code implementation4 Dec 2020 Damai Dai, Jing Ren, Shuang Zeng, Baobao Chang, Zhifang Sui

In classification, we combine the entity representations from both two levels into more comprehensive representations for relation extraction.

Document-level Relation Extraction

An Anchor-Based Automatic Evaluation Metric for Document Summarization

no code implementations COLING 2020 Kexiang Wang, Tianyu Liu, Baobao Chang, Zhifang Sui

The widespread adoption of reference-based automatic evaluation metrics such as ROUGE has promoted the development of document summarization.

Document Summarization

Discriminatively-Tuned Generative Classifiers for Robust Natural Language Inference

1 code implementation EMNLP 2020 Xiaoan Ding, Tianyu Liu, Baobao Chang, Zhifang Sui, Kevin Gimpel

We explore training objectives for discriminative fine-tuning of our generative classifiers, showing improvements over log loss fine-tuning from prior work .

Natural Language Inference

An Empirical Study on Model-agnostic Debiasing Strategies for Robust Natural Language Inference

1 code implementation CONLL 2020 Tianyu Liu, Xin Zheng, Xiaoan Ding, Baobao Chang, Zhifang Sui

The prior work on natural language inference (NLI) debiasing mainly targets at one or few known biases while not necessarily making the models more robust.

Data Augmentation Natural Language Inference

HypoNLI: Exploring the Artificial Patterns of Hypothesis-only Bias in Natural Language Inference

no code implementations LREC 2020 Tianyu Liu, Xin Zheng, Baobao Chang, Zhifang Sui

Many recent studies have shown that for models trained on datasets for natural language inference (NLI), it is possible to make correct predictions by merely looking at the hypothesis while completely ignoring the premise.

Natural Language Inference

XGPT: Cross-modal Generative Pre-Training for Image Captioning

no code implementations3 Mar 2020 Qiaolin Xia, Haoyang Huang, Nan Duan, Dong-dong Zhang, Lei Ji, Zhifang Sui, Edward Cui, Taroon Bharti, Xin Liu, Ming Zhou

While many BERT-based cross-modal pre-trained models produce excellent results on downstream understanding tasks like image-text retrieval and VQA, they cannot be applied to generation tasks directly.

Data Augmentation Denoising +7

Multi-View Learning for Vision-and-Language Navigation

no code implementations2 Mar 2020 Qiaolin Xia, Xiujun Li, Chunyuan Li, Yonatan Bisk, Zhifang Sui, Jianfeng Gao, Yejin Choi, Noah A. Smith

Learning to navigate in a visual environment following natural language instructions is a challenging task because natural language instructions are highly variable, ambiguous, and under-specified.

MULTI-VIEW LEARNING Navigate +1

Pun-GAN: Generative Adversarial Network for Pun Generation

1 code implementation IJCNLP 2019 Fuli Luo, Shunyao Li, Pengcheng Yang, Lei LI, Baobao Chang, Zhifang Sui, Xu sun

It consists of a generator to produce pun sentences, and a discriminator to distinguish between the generated pun sentences and the real sentences with specific word senses.

Towards Comprehensive Description Generation from Factual Attribute-value Tables

no code implementations ACL 2019 Tianyu Liu, Fuli Luo, Pengcheng Yang, Wei Wu, Baobao Chang, Zhifang Sui

To relieve these problems, we first propose force attention (FA) method to encourage the generator to pay more attention to the uncovered attributes to avoid potential key attributes missing.

Learning to Control the Fine-grained Sentiment for Story Ending Generation

no code implementations ACL 2019 Fuli Luo, Damai Dai, Pengcheng Yang, Tianyu Liu, Baobao Chang, Zhifang Sui, Xu sun

Therefore, we propose a generic and novel framework which consists of a sentiment analyzer and a sentimental generator, respectively addressing the two challenges.

Text Generation

A Dual Reinforcement Learning Framework for Unsupervised Text Style Transfer

2 code implementations24 May 2019 Fuli Luo, Peng Li, Jie zhou, Pengcheng Yang, Baobao Chang, Zhifang Sui, Xu sun

Therefore, in this paper, we propose a dual reinforcement learning framework to directly transfer the style of the text via a one-step mapping model, without any separation of content and style.

reinforcement-learning reinforcement Learning +2

Incorporating Glosses into Neural Word Sense Disambiguation

1 code implementation ACL 2018 Fuli Luo, Tianyu Liu, Qiaolin Xia, Baobao Chang, Zhifang Sui

GAS models the semantic relationship between the context and the gloss in an improved memory network framework, which breaks the barriers of the previous supervised methods and knowledge-based methods.

Word Sense Disambiguation

Table-to-text Generation by Structure-aware Seq2seq Learning

3 code implementations27 Nov 2017 Tianyu Liu, Kexiang Wang, Lei Sha, Baobao Chang, Zhifang Sui

In the decoding phase, dual attention mechanism which contains word level attention and field level attention is proposed to model the semantic relevance between the generated description and the table.

Table-to-Text Generation

Order-Planning Neural Text Generation From Structured Data

1 code implementation1 Sep 2017 Lei Sha, Lili Mou, Tianyu Liu, Pascal Poupart, Sujian Li, Baobao Chang, Zhifang Sui

Generating texts from structured data (e. g., a table) is important for various natural language processing tasks such as question answering and dialog systems.

Question Answering Table-to-Text Generation

A Soft-label Method for Noise-tolerant Distantly Supervised Relation Extraction

no code implementations EMNLP 2017 Tianyu Liu, Kexiang Wang, Baobao Chang, Zhifang Sui

Distant-supervised relation extraction inevitably suffers from wrong labeling problems because it heuristically labels relational facts with knowledge bases.

Relation Extraction

Improving Chinese SRL with Heterogeneous Annotations

no code implementations22 Feb 2017 Qiaolin Xia, Baobao Chang, Zhifang Sui

Previous studies on Chinese semantic role labeling (SRL) have concentrated on single semantically annotated corpus.

Chinese Semantic Role Labeling Semantic Role Labeling

Event Detection with Burst Information Networks

no code implementations COLING 2016 Tao Ge, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou

Retrospective event detection is an important task for discovering previously unidentified events in a text stream.

Event Detection

Towards Time-Aware Knowledge Graph Completion

no code implementations COLING 2016 Tingsong Jiang, Tianyu Liu, Tao Ge, Lei Sha, Baobao Chang, Sujian Li, Zhifang Sui

In this paper, we present a novel time-aware knowledge graph completion model that is able to predict links in a KG using both the existing facts and the temporal information of the facts.

Question Answering Relation Extraction

Reading and Thinking: Re-read LSTM Unit for Textual Entailment Recognition

no code implementations COLING 2016 Lei Sha, Baobao Chang, Zhifang Sui, Sujian Li

After read the premise again, the model can get a better understanding of the premise, which can also affect the understanding of the hypothesis.

Information Retrieval Machine Translation +4

Aligning Coordinated Text Streams through Burst Information Network Construction and Decipherment

no code implementations27 Sep 2016 Tao Ge, Qing Dou, Xiaoman Pan, Heng Ji, Lei Cui, Baobao Chang, Zhifang Sui, Ming Zhou

We introduce a novel Burst Information Network (BINet) representation that can display the most important information and illustrate the connections among bursty entities, events and keywords in the corpus.

Decipherment Translation

Implicit Discourse Relation Classification via Multi-Task Neural Networks

no code implementations9 Mar 2016 Yang Liu, Sujian Li, Xiaodong Zhang, Zhifang Sui

Without discourse connectives, classifying implicit discourse relations is a challenging task and a bottleneck for building a practical discourse parser.

Classification General Classification +2

Joint Learning Templates and Slots for Event Schema Induction

no code implementations NAACL 2016 Lei Sha, Sujian Li, Baobao Chang, Zhifang Sui

Automatic event schema induction (AESI) means to extract meta-event from raw text, in other words, to find out what types (templates) of event may exist in the raw text and what roles (slots) may exist in each event type.

Image Segmentation Semantic Segmentation

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