Search Results for author:
Found 53 papers, 23 papers with code
Human-Centered Evaluation of Explanations
The NLP community are increasingly interested in providing explanations for NLP models to help people make sense of model behavior and potentially improve human interaction with models.
Learning to Improve Persona Consistency in Multi-party Dialogue Generation via Text Knowledge Enhancement
In an open-domain dialogue system, the consistent persona is a key factor to generate real and coherent dialogues.
KC-ISA: An Implicit Sentiment Analysis Model Combining Knowledge Enhancement and Context Features
Moreover, to verify the generality of the model, we also conduct experiments on two common sentiment analysis datasets.
A Correction of Pseudo Log-Likelihood Method
Pseudo log-likelihood is a type of maximum likelihood estimation (MLE) method used in various fields including contextual bandits, influence maximization of social networks, and causal bandits.
FEEL: A Framework for Evaluating Emotional Support Capability with Large Language Models
The model meticulously considers var-ious evaluative aspects of ESC to apply a more comprehensive and accurate evaluation method for ESC.
Is Mamba Effective for Time Series Forecasting?
Furthermore, we conduct extensive experiments to delve deeper into the potential of Mamba compared to the Transformer in the TSF.
LangGPT: Rethinking Structured Reusable Prompt Design Framework for LLMs from the Programming Language
We have built a community on LangGPT to facilitate the tuition and sharing of prompt design.
KARL: Knowledge-Aware Retrieval and Representations aid Retention and Learning in Students
Flashcard schedulers are tools that rely on 1) student models to predict the flashcards a student knows; and 2) teaching policies to schedule cards based on these predictions.
HiFT: A Hierarchical Full Parameter Fine-Tuning Strategy
As LMs grow in size, fine-tuning the full parameters of LMs requires a prohibitively large amount of GPU memory.
STICKERCONV: Generating Multimodal Empathetic Responses from Scratch
Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets.
Large Language Models Help Humans Verify Truthfulness -- Except When They Are Convincingly Wrong
To reduce over-reliance on LLMs, we ask LLMs to provide contrastive information - explain both why the claim is true and false, and then we present both sides of the explanation to users.
MM-BigBench: Evaluating Multimodal Models on Multimodal Content Comprehension Tasks
Consequently, our work complements research on the performance of MLLMs in multimodal comprehension tasks, achieving a more comprehensive and holistic evaluation of MLLMs.
Machine learning assist nyc subway navigation safer and faster
Mainstream navigation software, like Google and Apple Maps, often lacks the ability to provide routes prioritizing safety.
T-COL: Generating Counterfactual Explanations for General User Preferences on Variable Machine Learning Systems
The application of CEs encounters two main challenges: general user preferences and variable ML systems.
RoCar: A Relationship Network-based Evaluation Method to Large Language Models
Large language models (LLMs) have received increasing attention.
Machine learning reveals features of spinon Fermi surface
With rapid progress in simulation of strongly interacting quantum Hamiltonians, the challenge in characterizing unknown phases becomes a bottleneck for scientific progress.
Evaluate What You Can't Evaluate: Unassessable Quality for Generated Response
There are risks in using eference-free evaluators based on LLMs to evaluate the quality of dialogue responses.
Measuring Inductive Biases of In-Context Learning with Underspecified Demonstrations
We investigate the inductive biases of ICL from the perspective of feature bias: which feature ICL is more likely to use given a set of underspecified demonstrations in which two features are equally predictive of the labels.
Learning Human-Compatible Representations for Case-Based Decision Support
Despite the promising performance of supervised learning, representations learned by supervised models may not align well with human intuitions: what models consider as similar examples can be perceived as distinct by humans.
Combinatorial Causal Bandits without Graph Skeleton
This paper studies the CCB problem without the graph structure on binary general causal models and BGLMs.
PVGRU: Generating Diverse and Relevant Dialogue Responses via Pseudo-Variational Mechanism
We investigate response generation for multi-turn dialogue in generative-based chatbots.
Few-shot Multimodal Sentiment Analysis based on Multimodal Probabilistic Fusion Prompts
To tackle this problem, we propose a novel method called Multimodal Probabilistic Fusion Prompts (MultiPoint) that leverages diverse cues from different modalities for multimodal sentiment detection in the few-shot scenario.
Active Example Selection for In-Context Learning
For GPT-2, our learned policies demonstrate strong abilities of generalizing to unseen tasks in training, with a $5. 8\%$ improvement on average.
Alleviating Sparsity of Open Knowledge Graphs with Ternary Contrastive Learning
Sparsity of formal knowledge and roughness of non-ontological construction make sparsity problem particularly prominent in Open Knowledge Graphs (OpenKGs).
DialogConv: A Lightweight Fully Convolutional Network for Multi-view Response Selection
Current end-to-end retrieval-based dialogue systems are mainly based on Recurrent Neural Networks or Transformers with attention mechanisms.
MulZDG: Multilingual Code-Switching Framework for Zero-shot Dialogue Generation
Building dialogue generation systems in a zero-shot scenario remains a huge challenge, since the typical zero-shot approaches in dialogue generation rely heavily on large-scale pre-trained language generation models such as GPT-3 and T5.
Combinatorial Causal Bandits
For the special case of linear models with hidden variables, we apply causal inference techniques such as the do-calculus to convert the original model into a Markovian model, and then show that our BGLM-OFU algorithm and another algorithm based on the linear regression both solve such linear models with hidden variables.
Machine Explanations and Human Understanding
Our key result is that without assumptions about task-specific intuitions, explanations may potentially improve human understanding of model decision boundary, but they cannot improve human understanding of task decision boundary or model error.
Multimodal Sentiment Detection Based on Multi-channel Graph Neural Networks
In this paper, we propose Multi-channel Graph Neural Networks with Sentiment-awareness (MGNNS) for image-text sentiment detection.
Calibrate Before Use: Improving Few-Shot Performance of Language Models
We show that this type of few-shot learning can be unstable: the choice of prompt format, training examples, and even the order of the training examples can cause accuracy to vary from near chance to near state-of-the-art.
A Graph Reasoning Network for Multi-turn Response Selection via Customized Pre-training
We investigate response selection for multi-turn conversation in retrieval-based chatbots.
Concealed Data Poisoning Attacks on NLP Models
In this work, we develop a new data poisoning attack that allows an adversary to control model predictions whenever a desired trigger phrase is present in the input.
How Pre-trained Word Representations Capture Commonsense Physical Comparisons
One type of common sense is how two objects compare on physical properties such as size and weight: e. g., {`}is a house bigger than a person?{'}.
Answer-guided and Semantic Coherent Question Generation in Open-domain Conversation
We observe that the answer has strong semantic coherence to its question and post, which can be used to guide question generation.
Answer-Supervised Question Reformulation for Enhancing Conversational Machine Comprehension
Moreover, pretraining is essential in reinforcement learning models, so we provide a high-quality annotated dataset for question reformulation by sampling a part of QuAC dataset.
Universal Adversarial Triggers for Attacking and Analyzing NLP
We define universal adversarial triggers: input-agnostic sequences of tokens that trigger a model to produce a specific prediction when concatenated to any input from a dataset.
Misleading Failures of Partial-input Baselines
Recent work establishes dataset difficulty and removes annotation artifacts via partial-input baselines (e. g., hypothesis-only models for SNLI or question-only models for VQA).
Quizbowl: The Case for Incremental Question Answering
Throughout this paper, we show that collaborations with the vibrant trivia community have contributed to the quality of our dataset, spawned new research directions, and doubled as an exciting way to engage the public with research in machine learning and natural language processing.
Understanding Impacts of High-Order Loss Approximations and Features in Deep Learning Interpretation
Second, we compute the importance of group-features in deep learning interpretation by introducing a sparsity regularization term.
What can AI do for me: Evaluating Machine Learning Interpretations in Cooperative Play
Machine learning is an important tool for decision making, but its ethical and responsible application requires rigorous vetting of its interpretability and utility: an understudied problem, particularly for natural language processing models.
Personalized Microblog Sentiment Classification via Adversarial Cross-lingual Multi-task Learning
Then the attention-based CNN model is incorporated into a novel adversarial cross-lingual learning framework, in which with the help of user properties as bridge between languages, we can extract the language-specific features and language-independent features to enrich the user post representation so as to alleviate the data insufficiency problem.
A Co-Attention Neural Network Model for Emotion Cause Analysis with Emotional Context Awareness
Emotion cause analysis has been a key topic in natural language processing.
Interpreting Neural Networks With Nearest Neighbors
However, the confidence of neural networks is not a robust measure of model uncertainty.
Trick Me If You Can: Human-in-the-loop Generation of Adversarial Examples for Question Answering
We propose human-in-the-loop adversarial generation, where human authors are guided to break models.
Pathologies of Neural Models Make Interpretations Difficult
In existing interpretation methods for NLP, a word's importance is determined by either input perturbation---measuring the decrease in model confidence when that word is removed---or by the gradient with respect to that word.
The UMD Neural Machine Translation Systems at WMT17 Bandit Learning Task
We describe the University of Maryland machine translation systems submitted to the WMT17 German-English Bandit Learning Task.
Improving Attention Modeling with Implicit Distortion and Fertility for Machine Translation
In neural machine translation, the attention mechanism facilitates the translation process by producing a soft alignment between the source sentence and the target sentence.
Implicit Distortion and Fertility Models for Attention-based Encoder-Decoder NMT Model
Aiming to resolve these problems, we propose new variations of attention-based encoder-decoder and compare them with other models on machine translation.
