Bing Liu

Analyzing and Detecting Opinion Spam on a Large-scale Dataset via Temporal and Spatial Patterns

2021 · Proceedings of the International AAAI Conference on Web and Social Media

Although opinion spam (or fake review) detection has attracted significant research attention in recent years, the problem is far from solved. One key reason is that there is no large-scale ground truth labeled dataset available …

Joint Online Spoken Language Understanding and Language Modeling with Recurrent Neural Networks

2016 · arXiv (Cornell University)

Speaker intent detection and semantic slot filling are two critical tasks in spoken language understanding (SLU) for dialogue systems. In this paper, we describe a recurrent neural network (RNN) model that jointly performs intent detection, …

Modeling Review Spam Using Temporal Patterns and Co-bursting Behaviors

2016 · arXiv (Cornell University)

Online reviews play a crucial role in helping consumers evaluate and compare products and services. However, review hosting sites are often targeted by opinion spamming. In recent years, many such sites have put a great …

Bimodal Distribution and Co-Bursting in Review Spam Detection

2017

Online reviews play a crucial role in helping consumers evaluate and compare products and services. This critical importance of reviews also incentivizes fraudsters (or spammers) to write fake or spam reviews to secretly promote or …

Dialogue Learning with Human Teaching and Feedback in End-to-End Trainable Task-Oriented Dialogue Systems

2018 · arXiv (Cornell University)

In this work, we present a hybrid learning method for training task-oriented dialogue systems through online user interactions. Popular methods for learning task-oriented dialogues include applying reinforcement learning with user feedback on supervised pre-training models. …

Relation classification via recurrent neural network with attention and tensor layers

2018 · Big Data Mining and Analytics

Relation classification is a crucial component in many Natural Language Processing (NLP) systems. In this paper, we propose a novel bidirectional recurrent neural network architecture (using Long Short-Term Memory, LSTM, cells) for relation classification, with …

Review Conversational Reading Comprehension

2019 · arXiv (Cornell University)

Inspired by conversational reading comprehension (CRC), this paper studies a novel task of leveraging reviews as a source to build an agent that can answer multi-turn questions from potential consumers of online businesses. We first …

User Memory Reasoning for Conversational Recommendation

2020

We study an end-to-end approach for conversational recommendation that dynamically manages and reasons over users' past (offline) preferences and current (online) requests through a structured and cumulative user memory knowledge graph. This formulation extends existing …

Adapting BERT for Continual Learning of a Sequence of Aspect Sentiment Classification Tasks

2021 · arXiv (Cornell University)

This paper studies continual learning (CL) of a sequence of aspect sentiment classification (ASC) tasks. Although some CL techniques have been proposed for document sentiment classification, we are not aware of any CL work on …

KETOD: Knowledge-Enriched Task-Oriented Dialogue

2022 · Findings of the Association for Computational Linguistics: NAACL 2022

Existing studies in dialogue system research mostly treat task-oriented dialogue and chitchat as separate domains. Towards building a human-like assistant that can converse naturally and seamlessly with users, it is important to build a dialogue …

Open-World Continual Learning: Unifying Novelty Detection and Continual Learning

2023 · arXiv (Cornell University)

As AI agents are increasingly used in the real open world with unknowns or novelties, they need the ability to (1) recognize objects that (a) they have learned before and (b) detect items that they …

Grounding for Artificial Intelligence

2023 · arXiv (Cornell University)

A core function of intelligence is grounding, which is the process of connecting the natural language and abstract knowledge to the internal representation of the real world in an intelligent being, e.g., a human. Human …

A Matrix Decomposition Recommendation Algorithm Introducing Untrusted Information between Users

2023

In response to the problems of poor recommendation performance caused by sparse data in traditional recommendation algorithms and slow convergence speed caused by the fact that the values of trust matrix elements can be any …

Probing Language Models for Pre-training Data Detection

2024 · arXiv (Cornell University)

Large Language Models (LLMs) have shown their impressive capabilities, while also raising concerns about the data contamination problems due to privacy issues and leakage of benchmark datasets in the pre-training phase. Therefore, it is vital …

Ontologies-based Knowledge Representation Method for Improving Learning Performance in the Engineering Drawing Course

2024 · Computer-Aided Design and Applications

Computer-Aided Design and Applications is an international journal on the applications of CAD and CAM. It publishes papers in the general domain of CAD plus in emerging fields like bio-CAD, nano-CAD, soft-CAD, garment-CAD, PLM, PDM, …

Differentiated Risk Assessment of Power Grid Engineering Cost Data Based on 5G and Blockchain Technologies

2024

Due to the complex geographical locations, vast spans, and lengthy construction periods of power grid projects, these undertakings are heavily influenced by external environmental factors, market dynamics, and human interventions, leading to frequent data variability …

Beyond Seeing: Evaluating Multimodal LLMs on Tool-Enabled Image Perception, Transformation, and Reasoning

2025 · arXiv (Cornell University)

Multimodal Large Language Models (MLLMs) are increasingly applied in real-world scenarios where user-provided images are often imperfect, requiring active image manipulations such as cropping, editing, or enhancement to uncover salient visual cues. Beyond static visual …

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

2017 · arXiv (Cornell University)

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose …

Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Perception and expression of emotion are key factors to the success of dialogue systems or conversational agents. However, this problem has not been studied in large-scale conversation generation so far. In this paper, we propose …

Iterative policy learning in end-to-end trainable task-oriented neural dialog models

2017 · 2017 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

In this paper, we present a deep reinforcement learning (RL) framework for iterative dialog policy optimization in end-to-end task-oriented dialog systems. Popular approaches in learning dialog policy with RL include letting a dialog agent to …

Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling

2016

Attention-based encoder-decoder neural network models have recently shown promising results in machine translation and speech recognition. In this work, we propose an attention-based neural network model for joint intent detection and slot filling, both of …