Search Results for author:
Found 101 papers, 50 papers with code
Weakly Supervised Semantic Parsing by Learning from Mistakes
Using only 10% of utterance-denotation pairs, the parser achieves 84. 2 denotation accuracy on WikiSQL, which is competitive with the previous state-of-the-art approaches using 100% labeled data.
``What Do You Mean by That?'' A Parser-Independent Interactive Approach for Enhancing Text-to-SQL
In Natural Language Interfaces to Databases systems, the text-to-SQL technique allows users to query databases by using natural language questions.
CONLINE: Complex Code Generation and Refinement with Online Searching and Correctness Testing
Large Language Models (LLMs) have revolutionized code generation ability by converting natural language descriptions into executable code.
LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression
The challenge is that information entropy may be a suboptimal compression metric: (i) it only leverages unidirectional context and may fail to capture all essential information needed for prompt compression; (ii) it is not aligned with the prompt compression objective.
Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments
We instantiate the path on structured environments and provide feedback to edit the path if anything goes wrong.
Ploutos: Towards interpretable stock movement prediction with financial large language model
Recent advancements in large language models (LLMs) have opened new pathways for many domains.
UFO: A UI-Focused Agent for Windows OS Interaction
We introduce UFO, an innovative UI-Focused agent to fulfill user requests tailored to applications on Windows OS, harnessing the capabilities of GPT-Vision.
Revisiting VAE for Unsupervised Time Series Anomaly Detection: A Frequency Perspective
To ensure an accurate AD, FCVAE exploits an innovative approach to concurrently integrate both the global and local frequency features into the condition of Conditional Variational Autoencoder (CVAE) to significantly increase the accuracy of reconstructing the normal data.
COIN: Chance-Constrained Imitation Learning for Uncertainty-aware Adaptive Resource Oversubscription Policy
We address the challenge of learning safe and robust decision policies in presence of uncertainty in context of the real scientific problem of adaptive resource oversubscription to enhance resource efficiency while ensuring safety against resource congestion risk.
Contrastive Learning with Negative Sampling Correction
To correct the negative sampling bias, we propose a novel contrastive learning method named Positive-Unlabeled Contrastive Learning (PUCL).
Why does Prediction Accuracy Decrease over Time? Uncertain Positive Learning for Cloud Failure Prediction
Using two real-world datasets of disk failure prediction and conducting node prediction experiments in Microsoft Azure, which is a top-tier cloud provider that serves millions of users, we demonstrate Uptake can significantly improve the failure prediction accuracy by 5% on average.
FM-OV3D: Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection
In this work, we propose FM-OV3D, a method of Foundation Model-based Cross-modal Knowledge Blending for Open-Vocabulary 3D Detection, which improves the open-vocabulary localization and recognition abilities of 3D model by blending knowledge from multiple pre-trained foundation models, achieving true open-vocabulary without facing constraints from original 3D datasets.
Text2Analysis: A Benchmark of Table Question Answering with Advanced Data Analysis and Unclear Queries
We evaluate five state-of-the-art models using three different metrics and the results show that our benchmark presents introduces considerable challenge in the field of tabular data analysis, paving the way for more advanced research opportunities.
Xpert: Empowering Incident Management with Query Recommendations via Large Language Models
This paper presents a thorough empirical study on the utilization of queries of KQL, a DSL employed for incident management in a large-scale cloud management system at Microsoft.
TAP4LLM: Table Provider on Sampling, Augmenting, and Packing Semi-structured Data for Large Language Model Reasoning
Table-based reasoning has shown remarkable progress in combining deep models with discrete reasoning, which requires reasoning over both free-form natural language (NL) questions and semi-structured tabular data.
Is Bigger and Deeper Always Better? Probing LLaMA Across Scales and Layers
This paper presents an in-depth analysis of Large Language Models (LLMs), focusing on LLaMA, a prominent open-source foundational model in natural language processing.
TaskWeaver: A Code-First Agent Framework
TaskWeaver provides support for rich data structures, flexible plugin usage, and dynamic plugin selection, and leverages LLM coding capabilities for complex logic.
LayoutPrompter: Awaken the Design Ability of Large Language Models
In this work, we propose LayoutPrompter, which leverages large language models (LLMs) to address the above problems through in-context learning.
Everything of Thoughts: Defying the Law of Penrose Triangle for Thought Generation
To address these limitations, we introduce a novel thought prompting approach called "Everything of Thoughts" (XoT) to defy the law of "Penrose triangle of existing thought paradigms.
Breaking Language Barriers in Multilingual Mathematical Reasoning: Insights and Observations
This indicates that crafting multilingual corpora can be regarded as a vital strategy for enhancing model performance in a specific language, especially in mathematical reasoning tasks.
Table-GPT: Table-tuned GPT for Diverse Table Tasks
Language models, such as GPT-3. 5 and ChatGPT, demonstrate remarkable abilities to follow diverse human instructions and perform a wide range of tasks.
Text-to-Image Generation for Abstract Concepts
Recent years have witnessed the substantial progress of large-scale models across various domains, such as natural language processing and computer vision, facilitating the expression of concrete concepts.
SoTaNa: The Open-Source Software Development Assistant
To meet the demands of this dynamic field, there is a growing need for an effective software development assistant.
A Parse-Then-Place Approach for Generating Graphic Layouts from Textual Descriptions
To model combined and incomplete constraints, we use a Transformer-based layout generation model and carefully design a way to represent constraints and layouts as sequences.
WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct
Through extensive experiments on two mathematical reasoning benchmarks, namely GSM8k and MATH, we reveal the extraordinary capabilities of our model.
Ranked #49 on
Arithmetic Reasoning
on GSM8K
(using extra training data)
End-to-End Beam Retrieval for Multi-Hop Question Answering
This approach models the multi-hop retrieval process in an end-to-end manner by jointly optimizing an encoder and two classification heads across all hops.
Ranked #1 on
Question Answering
on HotpotQA
Diffusion-based Time Series Data Imputation for Microsoft 365
However, they suffer from poor data quality like data missing in model training and prediction, which limits the performance.
Robust Positive-Unlabeled Learning via Noise Negative Sample Self-correction
To mitigate the impact of label uncertainty and improve the robustness of learning with positive and unlabeled data, we propose a new robust PU learning method with a training strategy motivated by the nature of human learning: easy cases should be learned first.
ImDiffusion: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
To the best of our knowledge, ImDiffusion represents a pioneering approach that combines imputation-based techniques with time series anomaly detection, while introducing the novel use of diffusion models to the field.
On Manipulating Signals of User-Item Graph: A Jacobi Polynomial-based Graph Collaborative Filtering
Graph CF has attracted more and more attention in recent years due to its effectiveness in leveraging high-order information in the user-item bipartite graph for better recommendations.
Auto-Validate by-History: Auto-Program Data Quality Constraints to Validate Recurring Data Pipelines
Data pipelines are widely employed in modern enterprises to power a variety of Machine-Learning (ML) and Business-Intelligence (BI) applications.
Enabling and Analyzing How to Efficiently Extract Information from Hybrid Long Documents with LLMs
We propose an Automated Financial Information Extraction (AFIE) framework that enhances LLMs' ability to comprehend and extract information from financial reports.
Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study
Although tables can be used as input to LLMs with serialization, there is a lack of comprehensive studies that examine whether LLMs can truly comprehend such data.
Introspective Tips: Large Language Model for In-Context Decision Making
The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks.
Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering
Large Language Model (LLM) has gained popularity and achieved remarkable results in open-domain tasks, but its performance in real industrial domain-specific scenarios is average due to its lack of specific domain knowledge.
How Do In-Context Examples Affect Compositional Generalization?
Compositional generalization--understanding unseen combinations of seen primitives--is an essential reasoning capability in human intelligence.
Towards Efficient Fine-tuning of Pre-trained Code Models: An Experimental Study and Beyond
Our experimental study shows that (1) lexical, syntactic and structural properties of source code are encoded in the lower, intermediate, and higher layers, respectively, while the semantic property spans across the entire model.
Demonstration of InsightPilot: An LLM-Empowered Automated Data Exploration System
In brief, an IQuery is an abstraction and automation of data analysis operations, which mimics the approach of data analysts and simplifies the exploration process for users.
LayoutDiffusion: Improving Graphic Layout Generation by Discrete Diffusion Probabilistic Models
To tackle the challenge, we summarize three critical factors for achieving a mild forward process for the layout, i. e., legality, coordinate proximity and type disruption.
Robust Mid-Pass Filtering Graph Convolutional Networks
Theoretical analyses guarantee the robustness of signals through the mid-pass filter, and we also shed light on the properties of different frequency signals under adversarial attacks.
Conservative State Value Estimation for Offline Reinforcement Learning
In this paper, we propose Conservative State Value Estimation (CSVE), a new approach that learns conservative V-function via directly imposing penalty on OOD states.
Homophily-oriented Heterogeneous Graph Rewiring
To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN.
Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy
In more detail, penultimate layer outputs on the training set are considered as the representations of in-distribution (ID) data.
Ranked #11 on
Out-of-Distribution Detection
on ImageNet-1k vs Places
LUNA: Language Understanding with Number Augmentations on Transformers via Number Plugins and Pre-training
But current approaches to rich-number tasks with transformer-based language models abandon or lose some of the numeracy information - e. g., breaking numbers into sub-word tokens - which leads to many number-related errors.
Learning Cooperative Oversubscription for Cloud by Chance-Constrained Multi-Agent Reinforcement Learning
To address these two limitations, this paper formulates the oversubscription for cloud as a chance-constrained optimization problem and propose an effective Chance Constrained Multi-Agent Reinforcement Learning (C2MARL) method to solve this problem.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Towards Robust Numerical Question Answering: Diagnosing Numerical Capabilities of NLP Systems
Numerical Question Answering is the task of answering questions that require numerical capabilities.
FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information
To assist form designers, in this work we present FormLM to model online forms (by enhancing pre-trained language model with form structural information) and recommend form creation ideas (including question / options recommendations and block type suggestion).
Reflection of Thought: Inversely Eliciting Numerical Reasoning in Language Models via Solving Linear Systems
Numerical reasoning over natural language has been a long-standing goal for the research community.
Unveiling the Black Box of PLMs with Semantic Anchors: Towards Interpretable Neural Semantic Parsing
The recent prevalence of pretrained language models (PLMs) has dramatically shifted the paradigm of semantic parsing, where the mapping from natural language utterances to structured logical forms is now formulated as a Seq2Seq task.
Make Heterophily Graphs Better Fit GNN: A Graph Rewiring Approach
Graph Neural Networks (GNNs) are popular machine learning methods for modeling graph data.
Ranked #5 on
Node Classification
on Squirrel
Enhanced Fairness Testing via Generating Effective Initial Individual Discriminatory Instances
In this paper, we propose an approach for the selection of the initial seeds to generate IDIs for fairness testing.
AnaMeta: A Table Understanding Dataset of Field Metadata Knowledge Shared by Multi-dimensional Data Analysis Tasks
Tabular data analysis is performed every day across various domains.
Learning Rate Perturbation: A Generic Plugin of Learning Rate Schedule towards Flatter Local Minima
Learning rate is one of the most important hyper-parameters that has a significant influence on neural network training.
LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction
First, to flexibly handle diverse constraints, we propose a constraint serialization scheme, which represents different user constraints as sequences of tokens with a predefined format.
MM-GNN: Mix-Moment Graph Neural Network towards Modeling Neighborhood Feature Distribution
Graph Neural Networks (GNNs) have shown expressive performance on graph representation learning by aggregating information from neighbors.
ASTA: Learning Analytical Semantics over Tables for Intelligent Data Analysis and Visualization
ASTA framework extracts data features by designing signatures based on expert knowledge, and enables data referencing at field- (chart) or cell-level (conditional formatting) with pre-trained models.
XInsight: eXplainable Data Analysis Through The Lens of Causality
XInsight is a three-module, end-to-end pipeline designed to extract causal graphs, translate causal primitives into XDA semantics, and quantify the quantitative contribution of each explanation to a data fact.
Solving the Batch Stochastic Bin Packing Problem in Cloud: A Chance-constrained Optimization Approach
This paper investigates a critical resource allocation problem in the first party cloud: scheduling containers to machines.
TaCube: Pre-computing Data Cubes for Answering Numerical-Reasoning Questions over Tabular Data
Existing auto-regressive pre-trained language models (PLMs) like T5 and BART, have been well applied to table question answering by UNIFIEDSKG and TAPEX, respectively, and demonstrated state-of-the-art results on multiple benchmarks.
PLOG: Table-to-Logic Pretraining for Logical Table-to-Text Generation
However, directly learning the logical inference knowledge from table-text pairs is very difficult for neural models because of the ambiguity of natural language and the scarcity of parallel data.
CoCoSoDa: Effective Contrastive Learning for Code Search
However, there is still a lot of room for improvement in using contrastive learning for code search.
Accelerating Code Search with Deep Hashing and Code Classification
Code search is to search reusable code snippets from source code corpus based on natural languages queries.
OneLabeler: A Flexible System for Building Data Labeling Tools
In this paper, we propose a conceptual framework for data labeling and OneLabeler based on the conceptual framework to support easy building of labeling tools for diverse usage scenarios.
RACE: Retrieval-Augmented Commit Message Generation
Furthermore, RACE can boost the performance of existing Seq2Seq models in commit message generation.
Table Pre-training: A Survey on Model Architectures, Pre-training Objectives, and Downstream Tasks
Since a vast number of tables can be easily collected from web pages, spreadsheets, PDFs, and various other document types, a flurry of table pre-training frameworks have been proposed following the success of text and images, and they have achieved new state-of-the-arts on various tasks such as table question answering, table type recognition, column relation classification, table search, formula prediction, etc.
Source Free Unsupervised Graph Domain Adaptation
To address the non-trivial adaptation challenges in this practical scenario, we propose a model-agnostic algorithm called SOGA for domain adaptation to fully exploit the discriminative ability of the source model while preserving the consistency of structural proximity on the target graph.
A Surrogate Objective Framework for Prediction+Programming with Soft Constraints
Prediction+optimization is a common real-world paradigm where we have to predict problem parameters before solving the optimization problem.
Neuron with Steady Response Leads to Better Generalization
Based on the analysis results, we articulate the Neuron Steadiness Hypothesis: the neuron with similar responses to instances of the same class leads to better generalization.
A Surrogate Objective Framework for Prediction+Optimization with Soft Constraints
Prediction+optimization is a common real-world paradigm where we have to predict problem parameters before solving the optimization problem.
A Unified and Fast Interpretable Model for Predictive Analytics
Predictive analytics is human involved, thus the machine learning model is preferred to be interpretable.
GBK-GNN: Gated Bi-Kernel Graph Neural Networks for Modeling Both Homophily and Heterophily
For node-level tasks, GNNs have strong power to model the homophily property of graphs (i. e., connected nodes are more similar) while their ability to capture the heterophily property is often doubtful.
ML4C: Seeing Causality Through Latent Vicinity
Starting from seeing that SCL is not better than random guessing if the learning target is non-identifiable a priori, we propose a two-phase paradigm for SCL by explicitly considering structure identifiability.
FORTAP: Using Formulas for Numerical-Reasoning-Aware Table Pretraining
In this paper, we find that the spreadsheet formula, which performs calculations on numerical values in tables, is naturally a strong supervision of numerical reasoning.
HiTab: A Hierarchical Table Dataset for Question Answering and Natural Language Generation
HiTab provides 10, 686 QA pairs and descriptive sentences with well-annotated quantity and entity alignment on 3, 597 tables with broad coverage of table hierarchies and numerical reasoning types.
Neuron Campaign for Initialization Guided by Information Bottleneck Theory
Initialization plays a critical role in the training of deep neural networks (DNN).
On the Evaluation of Neural Code Summarization
To achieve a profound understanding of how far we are from solving this problem and provide suggestions to future research, in this paper, we conduct a systematic and in-depth analysis of 5 state-of-the-art neural code summarization models on 6 widely used BLEU variants, 4 pre-processing operations and their combinations, and 3 widely used datasets.
Learning Algebraic Recombination for Compositional Generalization
In this paper, we propose LeAR, an end-to-end neural model to learn algebraic recombination for compositional generalization.
Ranked #2 on
Semantic Parsing
on CFQ
On the Evaluation of Commit Message Generation Models: An Experimental Study
We find that: (1) Different variants of the BLEU metric are used in previous works, which affects the evaluation and understanding of existing methods.
Is a Single Model Enough? MuCoS: A Multi-Model Ensemble Learning for Semantic Code Search
On the other hand, as a specific query may focus on one or several perspectives, it is difficult for a single query representation module to represent different user intents.
TableSense: Spreadsheet Table Detection with Convolutional Neural Networks
Spreadsheet table detection is the task of detecting all tables on a given sheet and locating their respective ranges.
TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
To simultaneously extract spatial and relational information from tables, we propose a novel neural network architecture, TabularNet.
Understanding and Improvement of Adversarial Training for Network Embedding from an Optimization Perspective
Network Embedding aims to learn a function mapping the nodes to Euclidean space contribute to multiple learning analysis tasks on networks.
Iterative Utterance Segmentation for Neural Semantic Parsing
Experiments on Geo, ComplexWebQuestions, and Formulas show that our framework can consistently improve performances of neural semantic parsers in different domains.
Revisiting Iterative Back-Translation from the Perspective of Compositional Generalization
Human intelligence exhibits compositional generalization (i. e., the capacity to understand and produce unseen combinations of seen components), but current neural seq2seq models lack such ability.
"What Do You Mean by That?" A Parser-Independent Interactive Approach for Enhancing Text-to-SQL
In Natural Language Interfaces to Databases systems, the text-to-SQL technique allows users to query databases by using natural language questions.
TUTA: Tree-based Transformers for Generally Structured Table Pre-training
First, we devise a unified tree-based structure, called a bi-dimensional coordinate tree, to describe both the spatial and hierarchical information of generally structured tables.
Hierarchical Poset Decoding for Compositional Generalization in Language
We formalize human language understanding as a structured prediction task where the output is a partially ordered set (poset).
Ranked #4 on
Semantic Parsing
on CFQ
Incomplete Utterance Rewriting as Semantic Segmentation
Recent years the task of incomplete utterance rewriting has raised a large attention.
Ranked #1 on
Dialogue Rewriting
on Rewrite
Table2Charts: Recommending Charts by Learning Shared Table Representations
It is common for people to create different types of charts to explore a multi-dimensional dataset (table).
Compositional Generalization by Learning Analytical Expressions
Compositional generalization is a basic and essential intellective capability of human beings, which allows us to recombine known parts readily.
You Impress Me: Dialogue Generation via Mutual Persona Perception
Despite the continuing efforts to improve the engagingness and consistency of chit-chat dialogue systems, the majority of current work simply focus on mimicking human-like responses, leaving understudied the aspects of modeling understanding between interlocutors.
Ranked #2 on
Dialogue Generation
on Persona-Chat
(using extra training data)
How Far are We from Effective Context Modeling? An Exploratory Study on Semantic Parsing in Context
Recently semantic parsing in context has received considerable attention, which is challenging since there are complex contextual phenomena.
Data-Anonymous Encoding for Text-to-SQL Generation
On text-to-SQL generation, the input utterance usually contains lots of tokens that are related to column names or cells in the table, called \textit{table-related tokens}.
A Hybrid Semantic Parsing Approach for Tabular Data Analysis
This paper presents a novel approach to translating natural language questions to SQL queries for given tables, which meets three requirements as a real-world data analysis application: cross-domain, multilingualism and enabling quick-start.
A Split-and-Recombine Approach for Follow-up Query Analysis
To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent natural language queries with contextual information.
Semantic Structure Extraction for Spreadsheet Tables with a Multi-task Learning Architecture
To learn spatial correlations and capture semantics on spreadsheets, we have developed a novel learning-based framework for spreadsheet semantic structure extraction.
Towards Complex Text-to-SQL in Cross-Domain Database with Intermediate Representation
We present a neural approach called IRNet for complex and cross-domain Text-to-SQL.
FANDA: A Novel Approach to Perform Follow-up Query Analysis
NLIDB allow users to search databases using natural language instead of SQL-like query languages.
SemRegex: A Semantics-Based Approach for Generating Regular Expressions from Natural Language Specifications
Recent research proposes syntax-based approaches to address the problem of generating programs from natural language specifications.
DeepAM: Migrate APIs with Multi-modal Sequence to Sequence Learning
They rely on the sparse availability of bilingual projects, thus producing a limited number of API mappings.
Deep API Learning
We propose DeepAPI, a deep learning based approach to generate API usage sequences for a given natural language query.
