Search Results for author: Xiaodan Zhu

Found 93 papers, 39 papers with code

Emotion Inference in Multi-Turn Conversations with Addressee-Aware Module and Ensemble Strategy

no code implementations EMNLP 2021 Dayu Li, Xiaodan Zhu, Yang Li, Suge Wang, Deyu Li, Jian Liao, Jianxing Zheng

Emotion inference in multi-turn conversations aims to predict the participant’s emotion in the next upcoming turn without knowing the participant’s response yet, and is a necessary step for applications such as dialogue planning.

WinoLogic: A Zero-Shot Logic-based Diagnostic Dataset for Winograd Schema Challenge

no code implementations EMNLP 2021 Weinan He, Canming Huang, Yongmei Liu, Xiaodan Zhu

To better evaluate NLMs, we propose a logic-based framework that focuses on high-quality commonsense knowledge.

Retrieval, Analogy, and Composition: A framework for Compositional Generalization in Image Captioning

no code implementations Findings (EMNLP) 2021 Zhan Shi, Hui Liu, Martin Renqiang Min, Christopher Malon, Li Erran Li, Xiaodan Zhu

Image captioning systems are expected to have the ability to combine individual concepts when describing scenes with concept combinations that are not observed during training.

Image Captioning Retrieval

Self-Consistent Decoding for More Factual Open Responses

1 code implementation1 Mar 2024 Christopher Malon, Xiaodan Zhu

We compare this "Sample & Select" method to greedy decoding, beam search, nucleus sampling, and the recently introduced hallucination avoiding decoders of DoLA, P-CRR, and S-CRR.

Hallucination Response Generation +1

HGOT: Hierarchical Graph of Thoughts for Retrieval-Augmented In-Context Learning in Factuality Evaluation

1 code implementation14 Feb 2024 Yihao Fang, Stephen W. Thomas, Xiaodan Zhu

With the widespread adoption of large language models (LLMs) in numerous applications, the challenge of factuality and the propensity for hallucinations raises significant concerns.

Answer Selection In-Context Learning +1

Calibration Attack: A Framework For Adversarial Attacks Targeting Calibration

no code implementations5 Jan 2024 Stephen Obadinma, Xiaodan Zhu, Hongyu Guo

We introduce a new framework of adversarial attacks, named calibration attacks, in which the attacks are generated and organized to trap victim models to be miscalibrated without altering their original accuracy, hence seriously endangering the trustworthiness of the models and any decision-making based on their confidence scores.

Decision Making

Can GPT models be Financial Analysts? An Evaluation of ChatGPT and GPT-4 on mock CFA Exams

no code implementations12 Oct 2023 Ethan Callanan, Amarachi Mbakwe, Antony Papadimitriou, Yulong Pei, Mathieu Sibue, Xiaodan Zhu, Zhiqiang Ma, Xiaomo Liu, Sameena Shah

Large Language Models (LLMs) have demonstrated remarkable performance on a wide range of Natural Language Processing (NLP) tasks, often matching or even beating state-of-the-art task-specific models.

Ensemble Distillation for Unsupervised Constituency Parsing

1 code implementation3 Oct 2023 Behzad Shayegh, Yanshuai Cao, Xiaodan Zhu, Jackie C. K. Cheung, Lili Mou

We investigate the unsupervised constituency parsing task, which organizes words and phrases of a sentence into a hierarchical structure without using linguistically annotated data.

Constituency Grammar Induction Sentence

ChatGPT as Data Augmentation for Compositional Generalization: A Case Study in Open Intent Detection

1 code implementation25 Aug 2023 Yihao Fang, Xianzhi Li, Stephen W. Thomas, Xiaodan Zhu

Open intent detection, a crucial aspect of natural language understanding, involves the identification of previously unseen intents in user-generated text.

Data Augmentation Natural Language Understanding +1

NatLogAttack: A Framework for Attacking Natural Language Inference Models with Natural Logic

no code implementations6 Jul 2023 Zi'ou Zheng, Xiaodan Zhu

We propose NatLogAttack to perform systematic attacks centring around natural logic, a classical logic formalism that is traceable back to Aristotle's syllogism and has been closely developed for natural language inference.

Natural Language Inference

Prototype-Based Interpretability for Legal Citation Prediction

no code implementations25 May 2023 Chu Fei Luo, Rohan Bhambhoria, Samuel Dahan, Xiaodan Zhu

Deep learning has made significant progress in the past decade, and demonstrates potential to solve problems with extensive social impact.

Citation Prediction Decision Making

A Simple and Effective Framework for Strict Zero-Shot Hierarchical Classification

no code implementations24 May 2023 Rohan Bhambhoria, Lei Chen, Xiaodan Zhu

To address these limitations, we propose the use of entailment-contradiction prediction in conjunction with LLMs, which allows for strong performance in a strict zero-shot setting.

Towards Legally Enforceable Hate Speech Detection for Public Forums

1 code implementation23 May 2023 Chu Fei Luo, Rohan Bhambhoria, Xiaodan Zhu, Samuel Dahan

With this task definition, automatic hate speech detection can be more closely aligned to enforceable laws, and hence assist in more rigorous enforcement of legal protections against harmful speech in public forums.

Hate Speech Detection

Prefix Propagation: Parameter-Efficient Tuning for Long Sequences

1 code implementation20 May 2023 Jonathan Li, Will Aitken, Rohan Bhambhoria, Xiaodan Zhu

Parameter-efficient tuning aims to mitigate the large memory requirements of adapting pretrained language models for downstream tasks.

Are ChatGPT and GPT-4 General-Purpose Solvers for Financial Text Analytics? A Study on Several Typical Tasks

no code implementations10 May 2023 Xianzhi Li, Samuel Chan, Xiaodan Zhu, Yulong Pei, Zhiqiang Ma, Xiaomo Liu, Sameena Shah

The most recent large language models(LLMs) such as ChatGPT and GPT-4 have shown exceptional capabilities of generalist models, achieving state-of-the-art performance on a wide range of NLP tasks with little or no adaptation.

Binary Classification named-entity-recognition +5

Effectiveness of Data Augmentation for Parameter Efficient Tuning with Limited Data

no code implementations5 Mar 2023 Stephen Obadinma, Hongyu Guo, Xiaodan Zhu

In this paper, we examine the effectiveness of several popular task-agnostic data augmentation techniques, i. e., EDA, Back Translation, and Mixup, when using two general parameter efficient tuning methods, P-tuning v2 and LoRA, under data scarcity.

Data Augmentation Sentence +1

Optimal scheduling of park-level integrated energy system considering ladder-type carbon trading mechanism and flexible load

no code implementations3 Mar 2023 Hongbin Sun, Xinmei Sun, Lei Kou, Benfa Zhang, Xiaodan Zhu

In an attempt to improve the utilization efficiency of multi-energy coupling in park-level integrated energy system (PIES), promote wind power consumption and reduce carbon emissions, a low-carbon economic operation optimization model of PIES integrating flexible load and carbon trading mechanism is constructed.

Scheduling

Learning Better Intent Representations for Financial Open Intent Classification

no code implementations25 Oct 2022 Xianzhi Li, Will Aitken, Xiaodan Zhu, Stephen W. Thomas

With the recent surge of NLP technologies in the financial domain, banks and other financial entities have adopted virtual agents (VA) to assist customers.

Classification intent-classification +3

Parameter-Efficient Legal Domain Adaptation

no code implementations25 Oct 2022 Jonathan Li, Rohan Bhambhoria, Xiaodan Zhu

Unfortunately, parameter-efficient methods perform poorly with small amounts of data, which are common in the legal domain (where data labelling costs are high).

Domain Adaptation

JECC: Commonsense Reasoning Tasks Derived from Interactive Fictions

1 code implementation18 Oct 2022 Mo Yu, Yi Gu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell, Chuang Gan

Hence, in order to achieve higher performance on our tasks, models need to effectively utilize such functional knowledge to infer the outcomes of actions, rather than relying solely on memorizing facts.

Reading Comprehension

Interpretable Low-Resource Legal Decision Making

no code implementations1 Jan 2022 Rohan Bhambhoria, Hui Liu, Samuel Dahan, Xiaodan Zhu

In this work, we utilize deep learning models in the area of trademark law to shed light on the issue of likelihood of confusion between trademarks.

Decision Making Weakly-supervised Learning

How Curriculum Learning Impacts Model Calibration

no code implementations29 Sep 2021 Stephen Obadinma, Xiaodan Zhu, Hongyu Guo

Our studies suggest the following: most of the time curriculum learning has a negligible effect on calibration, but in certain cases under the context of limited training time and noisy data, curriculum learning can substantially reduce calibration error in a manner that cannot be explained by dynamically sampling the dataset.

Exploring Decomposition for Table-based Fact Verification

1 code implementation Findings (EMNLP) 2021 Xiaoyu Yang, Xiaodan Zhu

Fact verification based on structured data is challenging as it requires models to understand both natural language and symbolic operations performed over tables.

Fact Verification Table-based Fact Verification

Unsupervised Pre-training with Structured Knowledge for Improving Natural Language Inference

no code implementations8 Sep 2021 Xiaoyu Yang, Xiaodan Zhu, Zhan Shi, Tianda Li

There have been two lines of approaches that can be used to further address the limitation: (1) unsupervised pretraining can leverage knowledge in much larger unstructured text data; (2) structured (often human-curated) knowledge has started to be considered in neural-network-based models for NLI.

Natural Language Inference Sentence +2

Unsupervised Conversation Disentanglement through Co-Training

1 code implementation EMNLP 2021 Hui Liu, Zhan Shi, Xiaodan Zhu

For the message-pair classifier, we enrich its training data by retrieving message pairs with high confidence from the disentangled sessions predicted by the session classifier.

Conversation Disentanglement Disentanglement

Detecting Speaker Personas from Conversational Texts

1 code implementation EMNLP 2021 Jia-Chen Gu, Zhen-Hua Ling, Yu Wu, Quan Liu, Zhigang Chen, Xiaodan Zhu

This is a many-to-many semantic matching task because both contexts and personas in SPD are composed of multiple sentences.

Enhancing Descriptive Image Captioning with Natural Language Inference

1 code implementation ACL 2021 Zhan Shi, Hui Liu, Xiaodan Zhu

In this paper we propose a novel approach to encourage captioning models to produce more detailed captions using natural language inference, based on the motivation that, among different captions of an image, descriptive captions are more likely to entail less descriptive captions.

Descriptive Image Captioning +1

Preview, Attend and Review: Schema-Aware Curriculum Learning for Multi-Domain Dialog State Tracking

no code implementations1 Jun 2021 Yinpei Dai, Hangyu Li, Yongbin Li, Jian Sun, Fei Huang, Luo Si, Xiaodan Zhu

Existing dialog state tracking (DST) models are trained with dialog data in a random order, neglecting rich structural information in a dataset.

 Ranked #1 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)

dialog state tracking Multi-domain Dialogue State Tracking

SemEval-2021 Task 4: Reading Comprehension of Abstract Meaning

1 code implementation SEMEVAL 2021 Boyuan Zheng, Xiaoyu Yang, Yu-Ping Ruan, ZhenHua Ling, Quan Liu, Si Wei, Xiaodan Zhu

Given a passage and the corresponding question, a participating system is expected to choose the correct answer from five candidates of abstract concepts in a cloze-style machine reading comprehension setup.

Machine Reading Comprehension

Partner Matters! An Empirical Study on Fusing Personas for Personalized Response Selection in Retrieval-Based Chatbots

1 code implementation19 May 2021 Jia-Chen Gu, Hui Liu, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu

Empirical studies on the Persona-Chat dataset show that the partner personas neglected in previous studies can improve the accuracy of response selection in the IMN- and BERT-based models.

Retrieval

Improving Text-to-SQL with Schema Dependency Learning

no code implementations7 Mar 2021 Binyuan Hui, Xiang Shi, Ruiying Geng, Binhua Li, Yongbin Li, Jian Sun, Xiaodan Zhu

In this paper, we present the Schema Dependency guided multi-task Text-to-SQL model (SDSQL) to guide the network to effectively capture the interactions between questions and schemas.

Text-To-SQL

Learning to Retrieve Entity-Aware Knowledge and Generate Responses with Copy Mechanism for Task-Oriented Dialogue Systems

1 code implementation22 Dec 2020 Chao-Hong Tan, Xiaoyu Yang, Zi'ou Zheng, Tianda Li, Yufei Feng, Jia-Chen Gu, Quan Liu, Dan Liu, Zhen-Hua Ling, Xiaodan Zhu

Task-oriented conversational modeling with unstructured knowledge access, as track 1 of the 9th Dialogue System Technology Challenges (DSTC 9), requests to build a system to generate response given dialogue history and knowledge access.

Response Generation Task-Oriented Dialogue Systems

Exploring End-to-End Differentiable Natural Logic Modeling

1 code implementation COLING 2020 Yufei Feng, Zi'ou Zheng, Quan Liu, Michael Greenspan, Xiaodan Zhu

We explore end-to-end trained differentiable models that integrate natural logic with neural networks, aiming to keep the backbone of natural language reasoning based on the natural logic formalism while introducing subsymbolic vector representations and neural components.

Inductive Bias

Deriving Commonsense Inference Tasks from Interactive Fictions

no code implementations19 Oct 2020 Mo Yu, Xiaoxiao Guo, Yufei Feng, Xiaodan Zhu, Michael Greenspan, Murray Campbell

Commonsense reasoning simulates the human ability to make presumptions about our physical world, and it is an indispensable cornerstone in building general AI systems.

Reading Comprehension

Program Enhanced Fact Verification with Verbalization and Graph Attention Network

1 code implementation EMNLP 2020 Xiaoyu Yang, Feng Nie, Yufei Feng, Quan Liu, Zhigang Chen, Xiaodan Zhu

Built on that, we construct the graph attention verification networks, which are designed to fuse different sources of evidences from verbalized program execution, program structures, and the original statements and tables, to make the final verification decision.

Fact Verification Graph Attention

Improving Image Captioning with Better Use of Caption

no code implementations ACL 2020 Zhan Shi, Xu Zhou, Xipeng Qiu, Xiaodan Zhu

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community.

Image Captioning Inductive Bias +2

SemEval-2020 Task 4: Commonsense Validation and Explanation

2 code implementations SEMEVAL 2020 Cunxiang Wang, Shuailong Liang, Yili Jin, Yilong Wang, Xiaodan Zhu, Yue Zhang

In this paper, we present SemEval-2020 Task 4, Commonsense Validation and Explanation (ComVE), which includes three subtasks, aiming to evaluate whether a system can distinguish a natural language statement that makes sense to humans from one that does not, and provide the reasons.

Improving Image Captioning with Better Use of Captions

1 code implementation21 Jun 2020 Zhan Shi, Xu Zhou, Xipeng Qiu, Xiaodan Zhu

Image captioning is a multimodal problem that has drawn extensive attention in both the natural language processing and computer vision community.

Image Captioning Inductive Bias +2

Filtering before Iteratively Referring for Knowledge-Grounded Response Selection in Retrieval-Based Chatbots

1 code implementation Findings of the Association for Computational Linguistics 2020 Jia-Chen Gu, Zhen-Hua Ling, Quan Liu, Zhigang Chen, Xiaodan Zhu

The challenges of building knowledge-grounded retrieval-based chatbots lie in how to ground a conversation on its background knowledge and how to match response candidates with both context and knowledge simultaneously.

Retrieval

DialBERT: A Hierarchical Pre-Trained Model for Conversation Disentanglement

1 code implementation8 Apr 2020 Tianda Li, Jia-Chen Gu, Xiaodan Zhu, Quan Liu, Zhen-Hua Ling, Zhiming Su, Si Wei

Disentanglement is a problem in which multiple conversations occur in the same channel simultaneously, and the listener should decide which utterance is part of the conversation he will respond to.

Conversation Disentanglement Disentanglement

Learning Cross-modal Context Graph for Visual Grounding

2 code implementations20 Nov 2019 Yongfei Liu, Bo Wan, Xiaodan Zhu, Xuming He

To address their limitations, this paper proposes a language-guided graph representation to capture the global context of grounding entities and their relations, and develop a cross-modal graph matching strategy for the multiple-phrase visual grounding task.

Graph Matching Visual Grounding

Anomaly Detection Based on Unsupervised Disentangled Representation Learning in Combination with Manifold Learning

no code implementations25 Sep 2019 Xiaoyan Li, Iluju Kiringa, Tet Yeap, Xiaodan Zhu, Yifeng Li

Identifying anomalous samples from highly complex and unstructured data is a crucial but challenging task in a variety of intelligent systems.

Anomaly Detection Density Estimation +3

Dually Interactive Matching Network for Personalized Response Selection in Retrieval-Based Chatbots

1 code implementation IJCNLP 2019 Jia-Chen Gu, Zhen-Hua Ling, Xiaodan Zhu, Quan Liu

Compared with previous persona fusion approaches which enhance the representation of a context by calculating its similarity with a given persona, the DIM model adopts a dual matching architecture, which performs interactive matching between responses and contexts and between responses and personas respectively for ranking response candidates.

Retrieval

Exploring Deep Anomaly Detection Methods Based on Capsule Net

1 code implementation15 Jul 2019 Xiaoyan Li, Iluju Kiringa, Tet Yeap, Xiaodan Zhu, Yifeng Li

In this paper, we develop and explore deep anomaly detection techniques based on the capsule network (CapsNet) for image data.

Anomaly Detection

Deep Learning for Natural Language Inference

no code implementations NAACL 2019 Samuel Bowman, Xiaodan Zhu

This tutorial discusses cutting-edge research on NLI, including recent advance on dataset development, cutting-edge deep learning models, and highlights from recent research on using NLI to understand capabilities and limits of deep learning models for language understanding and reasoning.

Natural Language Inference

Exploring Unsupervised Pretraining and Sentence Structure Modelling for Winograd Schema Challenge

no code implementations22 Apr 2019 Yu-Ping Ruan, Xiaodan Zhu, Zhen-Hua Ling, Zhan Shi, Quan Liu, Si Wei

Winograd Schema Challenge (WSC) was proposed as an AI-hard problem in testing computers' intelligence on common sense representation and reasoning.

Common Sense Reasoning Sentence

Promoting Diversity for End-to-End Conversation Response Generation

no code implementations27 Jan 2019 Yu-Ping Ruan, Zhen-Hua Ling, Quan Liu, Jia-Chen Gu, Xiaodan Zhu

At this stage, two different models are proposed, i. e., a variational generative (VariGen) model and a retrieval based (Retrieval) model.

Response Generation Retrieval

Logographic Subword Model for Neural Machine Translation

no code implementations7 Sep 2018 Yihao Fang, Rong Zheng, Xiaodan Zhu

A novel logographic subword model is proposed to reinterpret logograms as abstract subwords for neural machine translation.

Machine Translation Translation

Neural Natural Language Inference Models Enhanced with External Knowledge

1 code implementation ACL 2018 Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Diana Inkpen, Si Wei

With the availability of large annotated data, it has recently become feasible to train complex models such as neural-network-based inference models, which have shown to achieve the state-of-the-art performance.

Natural Language Inference

Recurrent Neural Network-Based Sentence Encoder with Gated Attention for Natural Language Inference

2 code implementations WS 2017 Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang, Diana Inkpen

The RepEval 2017 Shared Task aims to evaluate natural language understanding models for sentence representation, in which a sentence is represented as a fixed-length vector with neural networks and the quality of the representation is tested with a natural language inference task.

Natural Language Inference Natural Language Understanding +1

Deep Learning for Semantic Composition

no code implementations ACL 2017 Xiaodan Zhu, Edward Grefenstette

Learning representation to model the meaning of text has been a core problem in NLP.

Semantic Composition

A Dataset for Multi-Target Stance Detection

no code implementations EACL 2017 Parinaz Sobhani, Diana Inkpen, Xiaodan Zhu

Current models for stance classification often treat each target independently, but in many applications, there exist natural dependencies among targets, e. g., stance towards two or more politicians in an election or towards several brands of the same product.

Classification General Classification +3

Exploring Question Understanding and Adaptation in Neural-Network-Based Question Answering

no code implementations14 Mar 2017 Junbei Zhang, Xiaodan Zhu, Qian Chen, Li-Rong Dai, Si Wei, Hui Jiang

The last several years have seen intensive interest in exploring neural-network-based models for machine comprehension (MC) and question answering (QA).

Question Answering Reading Comprehension

Extracting Discriminative Keyphrases with Learned Semantic Hierarchies

no code implementations COLING 2016 Yunli Wang, Yong Jin, Xiaodan Zhu, Cyril Goutte

We show that such knowledge can be used to construct better discriminative keyphrase extraction systems that do not assume a static, fixed set of keyphrases for a document.

Keyphrase Extraction Specificity

Distraction-Based Neural Networks for Document Summarization

1 code implementation26 Oct 2016 Qian Chen, Xiaodan Zhu, Zhen-Hua Ling, Si Wei, Hui Jiang

Distributed representation learned with neural networks has recently shown to be effective in modeling natural languages at fine granularities such as words, phrases, and even sentences.

Document Summarization

A Dataset for Detecting Stance in Tweets

no code implementations LREC 2016 Saif Mohammad, Svetlana Kiritchenko, Parinaz Sobhani, Xiaodan Zhu, Colin Cherry

Apart from stance, the tweets are also annotated for whether the target of interest is the target of opinion in the tweet.

A Deep Learning Model for Structured Outputs with High-order Interaction

no code implementations29 Apr 2015 Hongyu Guo, Xiaodan Zhu, Martin Renqiang Min

Many real-world applications are associated with structured data, where not only input but also output has interplay.

Classification General Classification +2

Long Short-Term Memory Over Tree Structures

no code implementations16 Mar 2015 Xiaodan Zhu, Parinaz Sobhani, Hongyu Guo

The chain-structured long short-term memory (LSTM) has showed to be effective in a wide range of problems such as speech recognition and machine translation.

Machine Translation Natural Language Understanding +4

Measuring academic influence: Not all citations are equal

no code implementations26 Jan 2015 Xiaodan Zhu, Peter Turney, Daniel Lemire, André Vellino

Unlike the conventional h-index, it weights citations by how many times a reference is mentioned.

feature selection

NRC-Canada: Building the State-of-the-Art in Sentiment Analysis of Tweets

1 code implementation SEMEVAL 2013 Saif M. Mohammad, Svetlana Kiritchenko, Xiaodan Zhu

In this paper, we describe how we created two state-of-the-art SVM classifiers, one to detect the sentiment of messages such as tweets and SMS (message-level task) and one to detect the sentiment of a term within a submissions stood first in both tasks on tweets, obtaining an F-score of 69. 02 in the message-level task and 88. 93 in the term-level task.

Sentiment Analysis

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