Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Computer Sciences

Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 1381 - 1410 of 4473

Full-Text Articles in Entire DC Network

Target-Based Offensive Language Identification, Marcos Zampieri, Skye Morgan, Kai North, Tharindu Ranasinghe, Austin Simmons, Paridhi Khandelwal, Sara Rosenthal, Preslav Nakov Jul 2023

Target-Based Offensive Language Identification, Marcos Zampieri, Skye Morgan, Kai North, Tharindu Ranasinghe, Austin Simmons, Paridhi Khandelwal, Sara Rosenthal, Preslav Nakov

Natural Language Processing Faculty Publications

We present TBO, a new dataset for Target-based Offensive language identification. TBO contains post-level annotations regarding the harmfulness of an offensive post and token-level annotations comprising of the target and the offensive argument expression. Popular offensive language identification datasets for social media focus on annotation taxonomies only at the post level and more recently, some datasets have been released that feature only token-level annotations. TBO is an important resource that bridges the gap between post-level and token-level annotation datasets by introducing a single comprehensive unified annotation taxonomy. We use the TBO taxonomy to annotate post-level and token-level offensive language on …

Go to article

Improved Logical Reasoning Of Language Models Via Differentiable Symbolic Programming, Hanlin Zhang, Jiani Huang, Ziyang Li, Mayur Naik, Eric Xing Jul 2023

Improved Logical Reasoning Of Language Models Via Differentiable Symbolic Programming, Hanlin Zhang, Jiani Huang, Ziyang Li, Mayur Naik, Eric Xing

Machine Learning Faculty Publications

Pre-trained large language models (LMs) struggle to perform logical reasoning reliably despite advances in scale and compositionality. In this work, we tackle this challenge through the lens of symbolic programming. We propose DSR-LM, a Differentiable Symbolic Reasoning framework where pre-trained LMs govern the perception of factual knowledge, and a symbolic module performs deductive reasoning. In contrast to works that rely on hand-crafted logic rules, our differentiable symbolic reasoning framework efficiently learns weighted rules and applies semantic loss to further improve LMs. DSR-LM is scalable, interpretable, and allows easy integration of prior knowledge, thereby supporting extensive symbolic programming to robustly derive …

Go to article

Bertnet: Harvesting Knowledge Graphs With Arbitrary Relations From Pretrained Language Models, Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric P. Xing, Zhiting Hu Jul 2023

Bertnet: Harvesting Knowledge Graphs With Arbitrary Relations From Pretrained Language Models, Shibo Hao, Bowen Tan, Kaiwen Tang, Bin Ni, Xiyan Shao, Hengzhe Zhang, Eric P. Xing, Zhiting Hu

Machine Learning Faculty Publications

It is crucial to automatically construct knowledge graphs (KGs) of diverse new relations to support knowledge discovery and broad applications. Previous KG construction methods, based on either crowdsourcing or text mining, are often limited to a small predefined set of relations due to manual cost or restrictions in text corpus. Recent research proposed to use pretrained language models (LMs) as implicit knowledge bases that accept knowledge queries with prompts. Yet, the implicit knowledge lacks many desirable properties of a full-scale symbolic KG, such as easy access, navigation, editing, and quality assurance. In this paper, we propose a new approach of …

Go to article

Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov Jul 2023

Bertastic At Semeval-2023 Task 3: Fine-Tuning Pretrained Multilingual Transformers – Does Order Matter?, Tarek Mahmoud, Preslav Nakov

Natural Language Processing Faculty Publications

The naïve approach for fine-tuning pretrained deep learning models on downstream tasks involves feeding them mini-batches of randomly sampled data. In this paper, we propose a more elaborate method for fine-tuning Pretrained Multilingual Transformers (PMTs) on multilingual data. Inspired by the success of curriculum learning approaches, we investigate the significance of fine-tuning PMTs on multilingual data in a sequential fashion language by language. Unlike the curriculum learning paradigm where the model is presented with increasingly complex examples, we do not adopt a notion of “easy” and “hard” samples. Instead, our experiments draw insight from psychological findings on how the human …

Go to article

Adaptive Compositional Continual Meta-Learning, Bin Wu, Jinyuan Fang, Xiangxiang Zeng, Shangsong Liang, Qiang Zhang Jul 2023

Adaptive Compositional Continual Meta-Learning, Bin Wu, Jinyuan Fang, Xiangxiang Zeng, Shangsong Liang, Qiang Zhang

Machine Learning Faculty Publications

This paper focuses on continual meta-learning, where few-shot tasks are heterogeneous and sequentially available. Recent works use a mixture model for meta-knowledge to deal with the heterogeneity. However, these methods suffer from parameter inefficiency caused by two reasons: (1) the underlying assumption of mutual exclusiveness among mixture components hinders sharing meta-knowledge across heterogeneous tasks. (2) they only allow increasing mixture components and cannot adaptively filter out redundant components. In this paper, we propose an Adaptive Compositional Continual Meta-Learning (ACML) algorithm, which employs a compositional premise to associate a task with a subset of mixture components, allowing meta-knowledge sharing among heterogeneous …

Go to article

Linear Classifier: An Often-Forgotten Baseline For Text Classification, Yu Chen Lin, Si An Chen, Jie Jyun Liu, Chih Jen Lin Jul 2023

Linear Classifier: An Often-Forgotten Baseline For Text Classification, Yu Chen Lin, Si An Chen, Jie Jyun Liu, Chih Jen Lin

Machine Learning Faculty Publications

Large-scale pre-trained language models such as BERT are popular solutions for text classification. Due to the superior performance of these advanced methods, nowadays, people often directly train them for a few epochs and deploy the obtained model. In this opinion paper, we point out that this way may only sometimes get satisfactory results. We argue the importance of running a simple baseline like linear classifiers on bag-of-words features along with advanced methods. First, for many text data, linear methods show competitive performance, high efficiency, and robustness. Second, advanced models such as BERT may only achieve the best results if properly …

Go to article

Team Thesyllogist At Semeval-2023 Task 3: Language-Agnostic Framing Detection In Multi-Lingual Online News: A Zero-Shot Transfer Approach, Osama Mohammed Afzal, Preslav Nakov Jul 2023

Team Thesyllogist At Semeval-2023 Task 3: Language-Agnostic Framing Detection In Multi-Lingual Online News: A Zero-Shot Transfer Approach, Osama Mohammed Afzal, Preslav Nakov

Natural Language Processing Faculty Publications

We describe our system for SemEval-2022 Task 3 subtask 2 which on detecting the frames used in a news article in a multi-lingual setup. We propose a multi-lingual approach based on machine translation of the input, followed by an English prediction model. Our system demonstrated good zero-shot transfer capability, achieving micro-F1 scores of 53% for Greek (4th on the leaderboard) and 56.1% for Georgian (3rd on the leaderboard), without any prior training on translated data for these languages. Moreover, our system achieved comparable performance on seven other languages, including German, English, French, Russian, Italian, Polish, and Spanish. Our results demonstrate …

Go to article

Semeval-2023 Task 3: Detecting The Category, The Framing, And The Persuasion Techniques In Online News In A Multi-Lingual Setup, Jakub Piskorski, Nicolas Stefanovitch, Giovanni Da San Martino, Preslav Nakov Jul 2023

Semeval-2023 Task 3: Detecting The Category, The Framing, And The Persuasion Techniques In Online News In A Multi-Lingual Setup, Jakub Piskorski, Nicolas Stefanovitch, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

We describe SemEval-2023 task 3 on Detecting the Category, the Framing, and the Persuasion Techniques in Online News in a Multilingual Setup: the dataset, the task organization process, the evaluation setup, the results, and the participating systems. The task focused on news articles in nine languages (six known to the participants upfront: English, French, German, Italian, Polish, and Russian), and three additional ones revealed to the participants at the testing phase: Spanish, Greek, and Georgian). The task featured three subtasks: (1) determining the genre of the article (opinion, reporting, or satire), (2) identifying one or more frames used in an …

Go to article

Multilingual Multifaceted Understanding Of Online News In Terms Of Genre, Framing And Persuasion Techniques, Jakub Piskorski, Nicolas Stefanovitch, Nikolaos Nikolaidis, Giovanni Da San Martino, Preslav Nakov Jul 2023

Multilingual Multifaceted Understanding Of Online News In Terms Of Genre, Framing And Persuasion Techniques, Jakub Piskorski, Nicolas Stefanovitch, Nikolaos Nikolaidis, Giovanni Da San Martino, Preslav Nakov

Natural Language Processing Faculty Publications

We present a new multilingual multifacet dataset of news articles, each annotated for genre (objective news reporting vs. opinion vs. satire), framing (what key aspects are highlighted), and persuasion techniques (logical fallacies, emotional appeals, ad hominem attacks, etc.). The persuasion techniques are annotated at the span level, using a taxonomy of 23 fine-grained techniques grouped into 6 coarse categories. The dataset contains 1,612 news articles covering recent news on current topics of public interest in six European languages (English, French, German, Italian, Polish, and Russian), with more than 37k annotated spans of persuasion techniques. We describe the dataset and the …

Go to article

Identification Of Dialect For Eastern And Southwestern Ojibwe Words Using A Small Corpus, Kalvin Hartwig, Evan Lucas, Timothy C. Havens Jul 2023

Identification Of Dialect For Eastern And Southwestern Ojibwe Words Using A Small Corpus, Kalvin Hartwig, Evan Lucas, Timothy C. Havens

Michigan Tech Publications

The Ojibwe language has several dialects that vary to some degree in both spoken and written form. We present a method of using support vector machines to classify two different dialects (Eastern and Southwestern Ojibwe) using a very small corpus of text. Classification accuracy at the sentence level is 90% across a five-fold cross validation and 72% when the sentence-trained model is applied to a data set of individual words. Our code and the word level data set are released openly at https://github.com/evanperson/OjibweDialect.

Go to article

What Was More Frequently Used -- "And" Or "Or": Based On Analysis Of European Languages, Olga Kosheleva, Vladik Kreinovich Jul 2023

What Was More Frequently Used -- "And" Or "Or": Based On Analysis Of European Languages, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

Traditional logic has two main connectives: "and" and "or". A natural question is: which of the two is more frequently used? This question is easy to answer for the current usage of these connectives -- we can simply analyze all the texts, but what can we say about the past usage? To answer this question, we use the known linguistics fact that, in general, notions that are more frequently used are described by shorter words. It turns out that in most European languages, the word for "and" is shorter -- or of the same length -- as the word for …

Go to article

Managing The Creative Frontier Of Generative Ai: The Novelty-Usefulness Tradeoff, Anirban. Mukherjee, Hannah H. Chang Jul 2023

Managing The Creative Frontier Of Generative Ai: The Novelty-Usefulness Tradeoff, Anirban. Mukherjee, Hannah H. Chang

Research Collection Lee Kong Chian School Of Business

In this paper, drawing inspiration from the human creativity literature, we explore the optimal balance between novelty and usefulness in generative Artificial Intelligence (AI) systems. We posit that overemphasizing either aspect can lead to limitations such as hallucinations and memorization. Hallucinations, characterized by AI responses containing random inaccuracies or falsehoods, emerge when models prioritize novelty over usefulness. Memorization, where AI models reproduce content from their training data, results from an excessive focus on usefulness, potentially limiting creativity. To address these challenges, we propose a framework that includes domain-specific analysis, data and transfer learning, user preferences and customization, custom evaluation metrics, …

Go to article

Research On Legal Text Matching Based On Pre-Training Model, Chuanming Yu, Yifan Jiang Jul 2023

Research On Legal Text Matching Based On Pre-Training Model, Chuanming Yu, Yifan Jiang

Journal of Scientific Information Research

[Purpose/significance]This study aims to solve the problem of traditional short text matching models being difficult to apply to long text matching tasks such as legal case retrieval. [Method/process]For the task of legal case matching, this paper proposes a Legal Text Matching model based on RoFormer （LTMR）. In the coding layer, the legal case is encoded through the RoFormer model and the legal feature extractor. In the reasoning layer, the context and interactive information of long text are further extracted by using interactive attention and self-attention mechanisms. We conducted the empirical research by applying the proposed model to the CAIL2019-SCM dataset. …

Go to article

Stock-Oriented Measurement Of Financial News Correlation: Based On Theory Of Quantifying News Value, Jing Shi, Bin Zhang, Ye Chen Jul 2023

Stock-Oriented Measurement Of Financial News Correlation: Based On Theory Of Quantifying News Value, Jing Shi, Bin Zhang, Ye Chen

Journal of Scientific Information Research

[Purpose/significance]To identify crucial financial news information and tap its potential value related to specific stocks more quickly and accurately, we conduct financial news correlation measurement research in terms of stocks.[Method/process]Natural Language Processing and Machine Learning are used to measure the correlation by text analysis in the word's dimension. Then, the theory of quantifying news is applied to construct a stock-oriented evaluation index system for financial news correlation.[Result/conclusion]This paper realizes a personalized and automatic measurement of news correlation with the index system. Further, the influence of each index is also be analyzed.

Go to article

A Semantic Understanding Oriented Evaluation Of The Intelligent Q&A Service On Chinese Provincial Government Websites, Fang Wang, Zhonghan Wei, Zhixuan Lian, Jia Kang Jul 2023

A Semantic Understanding Oriented Evaluation Of The Intelligent Q&A Service On Chinese Provincial Government Websites, Fang Wang, Zhonghan Wei, Zhixuan Lian, Jia Kang

Journal of Scientific Information Research

[Purpose/significance]Intelligent question answering （Q&A） system has become an important facility for websites to provide consulting services. The complexity of government consultation issues poses higher requirements for the semantic understanding ability of intelligent Q&A systems on government websites.[Method/process]This study evaluates the Q&A systems of 30 Chinese provincial government websites from three aspects of problem solving quality,service interaction quality and basic construction quality by using the "Semantic Understanding based Evaluation Indicator System for Intelligent Q&A Service on Government Websites" developed by the Center for Network Society Governance of Nankai University and the supporting test sets.[Result/conclusion]The results show that Shanghai, Zhejiang and Beijing …

Go to article

Learning To Ask Clarification Questions With Spatial Reasoning, Yang Deng, Shuaiyi Li, Wai Lam Jul 2023

Learning To Ask Clarification Questions With Spatial Reasoning, Yang Deng, Shuaiyi Li, Wai Lam

Research Collection School Of Computing and Information Systems

Asking clarifying questions has become a key element of various conversational systems, allowing for an effective resolution of ambiguity and uncertainty through natural language questions. Despite the extensive applications of spatial information grounded dialogues, it remains an understudied area on learning to ask clarification questions with the capability of spatial reasoning. In this work, we propose a novel method, named SpatialCQ, for this problem. Specifically, we first align the representation space between textual and spatial information by encoding spatial states with textual descriptions. Then a multi-relational graph is constructed to capture the spatial relations and enable spatial reasoning with relational …

Go to article

Humans Against Large Language Models On Hard Paraphrase Detection Tasks, Jamie C. Macbeth, Ella Chang, Jingyu Gin Chen, Yining Hua, Sandra Grandic, Winnie X. Zheng Jul 2023

Humans Against Large Language Models On Hard Paraphrase Detection Tasks, Jamie C. Macbeth, Ella Chang, Jingyu Gin Chen, Yining Hua, Sandra Grandic, Winnie X. Zheng

Computer Science: Faculty Publications

The ability to recognize that pairs or sets of language expressions “mean the same thing” is a cognitive task for which meaning representation is clearly a central issue. This paper uses the task of paraphrasing to study meaning representation in a cognitive system. The main claim is that a consequential part of the meaning representation for a natural language expression is a set of language-free structures that are not part of the expression in question. To support this claim, we construct a corpus of paraphrase pairs using a system that has a non-linguistic meaning represen- tation decoupled from the linguistic …

Go to article

Security Of Text To Image Conversions, Zobaida Alssadi Jul 2023

Security Of Text To Image Conversions, Zobaida Alssadi

Theses and Dissertations

The use of images and icons to represent news or narratives has grown in popularity. Still, one critical problem is that they are not equivalent to language, making them vulnerable to adversary attacks. This study examines the impact of image-poisoning attacks based on polysemantic words and of image attacks based on cultural differences when converting text to images. Such attacks can lead to the loss of important information and create confusion and incorrect interpretations of the intended meaning, misinforming the general public. The study specifically focuses on possible effects in a news and story context. This study highlights the significance …

Go to article

Artificial Intelligence-Based Smarter Accessibility Evaluations For Comprehensive And Personalized Assessment, Sayeda Farzana Aktar Jul 2023

Artificial Intelligence-Based Smarter Accessibility Evaluations For Comprehensive And Personalized Assessment, Sayeda Farzana Aktar

Dissertations (1934 -)

The research focuses on utilizing artificial intelligence (AI) and machine learning (ML) algorithms to enhance accessibility for people with disabilities (PwD) in three areas: public buildings, homes, and medical devices. The overarching goal is to improve the accuracy, reliability, and effectiveness of accessibility evaluation systems by leveraging smarter technologies. For public buildings, the challenge lies in developing an accurate and reliable accessibility evaluation system. AI can play a crucial role by analyzing data, identifying potential barriers, and assessing the accessibility of various features within buildings. By training ML algorithms on relevant data, the system can learn to make accurate predictions …

Go to article

A Comparative Effectiveness Study On Opioid Use Disorder Prediction Using Artificial Intelligence And Existing Risk Models, Sajjad Fouladvand, Jeffery Talbert, Linda Phyliss Dwoskin, Heather M. Bush, Amy L. Meadows, Lars E. Peterson, Yash R. Mishra, Steven K. Roggenkamp, Fei Wang, Ramakanth Kavuluru, Jin Chen Jul 2023

A Comparative Effectiveness Study On Opioid Use Disorder Prediction Using Artificial Intelligence And Existing Risk Models, Sajjad Fouladvand, Jeffery Talbert, Linda Phyliss Dwoskin, Heather M. Bush, Amy L. Meadows, Lars E. Peterson, Yash R. Mishra, Steven K. Roggenkamp, Fei Wang, Ramakanth Kavuluru, Jin Chen

Markey Cancer Center Faculty Publications

Opioid use disorder (OUD) is a leading cause of death in the United States placing a tremendous burden on patients, their families, and health care systems. Artificial intelligence (AI) can be harnessed with available healthcare data to produce automated OUD prediction tools. In this retrospective study, we developed AI based models for OUD prediction and showed that AI can predict OUD more effectively than existing clinical tools including the unweighted opioid risk tool (ORT). Data include 474,208 patients’ data over 10 years; 269,748 were females with an average age of 56.78 years. Cases are prescription opioid users with at least …

Go to article

Do-Good: Towards Distribution Shift Evaluation For Pre-Trained Visual Document Understanding Models, Jiabang He, Yi Hu, Lei Wang, Xing Xu, Ning Liu, Hui Liu Jul 2023

Do-Good: Towards Distribution Shift Evaluation For Pre-Trained Visual Document Understanding Models, Jiabang He, Yi Hu, Lei Wang, Xing Xu, Ning Liu, Hui Liu

Research Collection School Of Computing and Information Systems

Numerous pre-training techniques for visual document understanding (VDU) have recently shown substantial improvements in performance across a wide range of document tasks. However, these pre-trained VDU models cannot guarantee continued success when the distribution of test data differs from the distribution of training data. In this paper, to investigate how robust existing pre-trained VDU models are to various distribution shifts, we first develop an out-of-distribution (OOD) benchmark termed Do-GOOD for the fine-Grained analysis on Document image-related tasks specifically. The Do-GOOD benchmark defines the underlying mechanisms that result in different distribution shifts and contains 9 OOD datasets covering 3 VDU related …

Go to article

Few-Shot Event Detection: An Empirical Study And A Unified View, Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun Jul 2023

Few-Shot Event Detection: An Empirical Study And A Unified View, Yubo Ma, Zehao Wang, Yixin Cao, Aixin Sun

Research Collection School Of Computing and Information Systems

Few-shot event detection (ED) has been widely studied, while this brings noticeable discrepancies, e.g., various motivations, tasks, and experimental settings, that hinder the understanding of models for future progress. This paper presents a thorough empirical study, a unified view of ED models, and a better unified baseline. For fair evaluation, we compare 12 representative methods on three datasets, which are roughly grouped into prompt-based and prototype-based models for detailed analysis. Experiments consistently demonstrate that prompt-based methods, including ChatGPT, still significantly trail prototype-based methods in terms of overall performance. To investigate their superior performance, we break down their design elements along …

Go to article

Take A Break In The Middle: Investigating Subgoals Towards Hierarhical Script Generation, Xinze Li, Yixin Cao, Muhao Chen, Aixin Sun Jul 2023

Take A Break In The Middle: Investigating Subgoals Towards Hierarhical Script Generation, Xinze Li, Yixin Cao, Muhao Chen, Aixin Sun

Research Collection School Of Computing and Information Systems

Goal-oriented Script Generation is a new task of generating a list of steps that can fulfill the given goal. In this paper, we propose to extend the task from the perspective of cognitive theory. Instead of a simple flat structure, the steps are typically organized hierarchically — Human often decompose a complex task into subgoals, where each subgoal can be further decomposed into steps. To establish the benchmark, we contribute a new dataset, propose several baseline methods, and set up evaluation metrics. Both automatic and human evaluation verify the high-quality of dataset, as well as the effectiveness of incorporating subgoals …

Go to article

Cheer: Centrality-Aware High-Order Event Reasoning Network For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Yan Zhang, Zhiwei Liu Jul 2023

Cheer: Centrality-Aware High-Order Event Reasoning Network For Document-Level Event Causality Identification, Meiqi Chen, Yixin Cao, Yan Zhang, Zhiwei Liu

Research Collection School Of Computing and Information Systems

Document-level Event Causality Identification (DECI) aims to recognize causal relations between events within a document. Recent studies focus on building a document-level graph for cross-sentence reasoning, but ignore important causal structures — there are one or two “central” events that prevail throughout the document, with most other events serving as either their cause or consequence. In this paper, we manually annotate central events for a systematical investigation and propose a novel DECI model, CHEER, which performs high-order reasoning while considering event centrality. First, we summarize a general GNN-based DECI model and provide a unified view for better understanding. Second, we …

Go to article

Synthesizing Speech Test Cases With Text-To-Speech? An Empirical Study On The False Alarms In Automated Speech Recognition Testing, Julia Kaiwen Lau, Kelvin Kai Wen Kong, Julian Hao Yong, Per Hoong Tan, Zhou Yang, Zi Qian Yong, Joshua Chern Wey Low, Chun Yong Chong, Mei Kuan Lim, David Lo Jul 2023

Synthesizing Speech Test Cases With Text-To-Speech? An Empirical Study On The False Alarms In Automated Speech Recognition Testing, Julia Kaiwen Lau, Kelvin Kai Wen Kong, Julian Hao Yong, Per Hoong Tan, Zhou Yang, Zi Qian Yong, Joshua Chern Wey Low, Chun Yong Chong, Mei Kuan Lim, David Lo

Research Collection School Of Computing and Information Systems

Recent studies have proposed the use of Text-To-Speech (TTS) systems to automatically synthesise speech test cases on a scale and uncover a large number of failures in ASR systems. However, the failures uncovered by synthetic test cases may not reflect the actual performance of an ASR system when it transcribes human audio, which we refer to as false alarms. Given a failed test case synthesised from TTS systems, which consists of TTS-generated audio and the corresponding ground truth text, we feed the human audio stating the same text to an ASR system. If human audio can be correctly transcribed, an …

Go to article

Impact Of Difficult Negatives On Twitter Crisis Detection, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint Jul 2023

Impact Of Difficult Negatives On Twitter Crisis Detection, Yuhao Zhang, Siaw Ling Lo, Phyo Yi Win Myint

Research Collection School Of Computing and Information Systems

Twitter has become an alternative information source during a crisis. However, the short, noisy nature of tweets hinders information extraction. While models trained with standard Twitter crisis datasets accomplished decent performance, it remained a challenge to generalize to unseen crisis events. Thus, we proposed adding “difficult” negative examples during training to improve model generalization for Twitter crisis detection. Although adding random noise is a common practice, the impact of difficult negatives, i.e., negative data semantically similar to true examples, was never examined in NLP. Most of existing research focuses on the classification task, without considering the primary information need of …

Go to article

A Unified Multi-Task Learning Framework For Multi-Goal Conversational Recommender Systems, Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam Jul 2023

A Unified Multi-Task Learning Framework For Multi-Goal Conversational Recommender Systems, Yang Deng, Wenxuan Zhang, Weiwen Xu, Wenqiang Lei, Tat-Seng Chua, Wai Lam

Research Collection School Of Computing and Information Systems

Question generation (QG) aims to automatically generate fluent and relevant questions, where the two most mainstream directions are generating questions from unstructured contextual texts (CQG), such as news articles, and generating questions from structured factoid texts (FQG), such as knowledge graphs or tables. Existing methods for these two tasks mainly face challenges of limited internal structural information as well as scarce background information, while these two tasks can benefit each other for alleviating these issues. For example, when meeting the entity mention “United Kingdom” in CQG, it can be inferred that it is a country in European continent based on …

Go to article

Peerda: Data Augmentation Via Modeling Peer Relation For Span Identification Tasks, Weiwen Xu, Xin Li, Yang Deng, Wai Lam, Lidong Bing Jul 2023

Peerda: Data Augmentation Via Modeling Peer Relation For Span Identification Tasks, Weiwen Xu, Xin Li, Yang Deng, Wai Lam, Lidong Bing

Research Collection School Of Computing and Information Systems

Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the Subordinate (SUB) relation (i.e. if a span is an instance of a certain category) to train models, this paper for the first time explores the Peer (PR) relation, which indicates that two spans are instances of the same category and share similar features. Specifically, a novel Peer Data Augmentation (PeerDA) approach is proposed which employs span pairs with the PR relation as the augmentation data for training. PeerDA has two unique advantages: (1) There are …

Go to article

Plan-And-Solve Prompting: Improving Zero-Shot Chain-Of-Thought Reasoning By Large Language Models, Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, Ee-Peng Lim Jul 2023

Plan-And-Solve Prompting: Improving Zero-Shot Chain-Of-Thought Reasoning By Large Language Models, Lei Wang, Wanyu Xu, Yihuai Lan, Zhiqiang Hu, Yunshi Lan, Roy Ka-Wei Lee, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Large language models (LLMs) have recently been shown to deliver impressive performance in various NLP tasks. To tackle multi-step reasoning tasks, few-shot chain-of-thought (CoT) prompting includes a few manually crafted step-by-step reasoning demonstrations which enable LLMs to explicitly generate reasoning steps and improve their reasoning task accuracy. To eliminate the manual effort, Zeroshot-CoT concatenates the target problem statement with “Let’s think step by step” as an input prompt to LLMs. Despite the success of Zero-shot-CoT, it still suffers from three pitfalls: calculation errors, missing-step errors, and semantic misunderstanding errors. To address the missing-step errors, we propose Planand-Solve (PS) Prompting. It …

Go to article

Modularized Zero-Shot Vqa With Pre-Trained Models, Rui Cao, Jing Jiang Jul 2023

Modularized Zero-Shot Vqa With Pre-Trained Models, Rui Cao, Jing Jiang

Research Collection School Of Computing and Information Systems

Large-scale pre-trained models (PTMs) show great zero-shot capabilities. In this paper, we study how to leverage them for zero-shot visual question answering (VQA).Our approach is motivated by a few observations. First, VQA questions often require multiple steps of reasoning, which is still a capability that most PTMs lack. Second, different steps in VQA reasoning chains require different skills such as object detection and relational reasoning, but a single PTM may not possess all these skills. Third, recent work on zero-shot VQA does not explicitly consider multi-step reasoning chains, which makes them less interpretable compared with a decomposition-based approach. We propose …

Go to article

First Prev Next Last