Search Results for author:
Found 106 papers, 63 papers with code
LayoutReader: Pre-training of Text and Layout for Reading Order Detection
Reading order detection is the cornerstone to understanding visually-rich documents (e. g., receipts and forms).
Ranked #2 on
Reading Order Detection
on ReadingBank
Document Layout Analysis
Optical Character Recognition (OCR)
+1
Neural-Symbolic Inference for Robust Autoregressive Graph Parsing via Compositional Uncertainty Quantification
Pre-trained seq2seq models excel at graph semantic parsing with rich annotated data, but generalize worse to out-of-distribution (OOD) and long-tail examples.
Automated Phrase Mining from Massive Text Corpora
As one of the fundamental tasks in text analysis, phrase mining aims at extracting quality phrases from a text corpus.
Empower Sequence Labeling with Task-Aware Neural Language Model
In this study, we develop a novel neural framework to extract abundant knowledge hidden in raw texts to empower the sequence labeling task.
Ranked #13 on
Part-Of-Speech Tagging
on Penn Treebank
Learning Named Entity Tagger using Domain-Specific Dictionary
Recent advances in deep neural models allow us to build reliable named entity recognition (NER) systems without handcrafting features.
CrossWeigh: Training Named Entity Tagger from Imperfect Annotations
Therefore, we manually correct these label mistakes and form a cleaner test set.
Ranked #3 on
Named Entity Recognition (NER)
on CoNLL++
(using extra training data)
LDB: A Large Language Model Debugger via Verifying Runtime Execution Step-by-step
Large language models (LLMs) are leading significant progress in code generation.
Ranked #1 on
Code Generation
on HumanEval
UCPhrase: Unsupervised Context-aware Quality Phrase Tagging
Training a conventional neural tagger based on silver labels usually faces the risk of overfitting phrase surface names.
Ranked #1 on
Phrase Tagging
on KPTimes
Efficient Contextualized Representation: Language Model Pruning for Sequence Labeling
Many efforts have been made to facilitate natural language processing tasks with pre-trained language models (LMs), and brought significant improvements to various applications.
Ranked #47 on
Named Entity Recognition (NER)
on CoNLL 2003 (English)
Cross-type Biomedical Named Entity Recognition with Deep Multi-Task Learning
Motivation: State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases.
Large Language Models for Time Series: A Survey
Large Language Models (LLMs) have seen significant use in domains such as natural language processing and computer vision.
Learning a Decision Tree Algorithm with Transformers
We then train MetaTree to produce the trees that achieve strong generalization performance.
X-Class: Text Classification with Extremely Weak Supervision
Finally, we pick the most confident documents from each cluster to train a text classifier.
Text Is All You Need: Learning Language Representations for Sequential Recommendation
In this paper, we propose to model user preferences and item features as language representations that can be generalized to new items and datasets.
Contextualized Weak Supervision for Text Classification
Weakly supervised text classification based on a few user-provided seed words has recently attracted much attention from researchers.
Integrating Local Context and Global Cohesiveness for Open Information Extraction
However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.
Unsupervised Deep Keyphrase Generation
Keyphrase generation aims to summarize long documents with a collection of salient phrases.
Meta-Path Guided Embedding for Similarity Search in Large-Scale Heterogeneous Information Networks
It models vertices as low-dimensional vectors to explore network structure-embedded similarity.
Empower Entity Set Expansion via Language Model Probing
Existing set expansion methods bootstrap the seed entity set by adaptively selecting context features and extracting new entities.
SetExpan: Corpus-Based Set Expansion via Context Feature Selection and Rank Ensemble
In this study, we propose a novel framework, SetExpan, which tackles this problem, with two techniques: (1) a context feature selection method that selects clean context features for calculating entity-entity distributional similarity, and (2) a ranking-based unsupervised ensemble method for expanding entity set based on denoised context features.
ClusterLLM: Large Language Models as a Guide for Text Clustering
First, we prompt ChatGPT for insights on clustering perspective by constructing hard triplet questions <does A better correspond to B than C>, where A, B and C are similar data points that belong to different clusters according to small embedder.
Goal-Driven Explainable Clustering via Language Descriptions
We propose a new task formulation, "Goal-Driven Clustering with Explanations" (GoalEx), which represents both the goal and the explanations as free-form language descriptions.
Learning Concise and Descriptive Attributes for Visual Recognition
Recent advances in foundation models present new opportunities for interpretable visual recognition -- one can first query Large Language Models (LLMs) to obtain a set of attributes that describe each class, then apply vision-language models to classify images via these attributes.
OA-Mine: Open-World Attribute Mining for E-Commerce Products with Weak Supervision
Most prior works on this matter mine new values for a set of known attributes but cannot handle new attributes that arose from constantly changing data.
An Attention-based Collaboration Framework for Multi-View Network Representation Learning
Existing approaches usually study networks with a single type of proximity between nodes, which defines a single view of a network.
Weakly Supervised Named Entity Tagging with Learnable Logical Rules
We study the problem of building entity tagging systems by using a few rules as weak supervision.
Entity Set Search of Scientific Literature: An Unsupervised Ranking Approach
Different from Web or general domain search, a large portion of queries in scientific literature search are entity-set queries, that is, multiple entities of possibly different types.
Raw-to-End Name Entity Recognition in Social Media
Our model neither requires the conversion from character sequences to word sequences, nor assumes tokenizer can correctly detect all word boundaries.
Towards Adaptive Residual Network Training: A Neural-ODE Perspective
Serving as a crucial factor, the depth of residual networks balances model capacity, performance, and training efficiency.
Towards Few-shot Entity Recognition in Document Images: A Label-aware Sequence-to-Sequence Framework
To overcome the data limitation, we propose to leverage the label surface names to better inform the model of the target entity type semantics and also embed the labels into the spatial embedding space to capture the spatial correspondence between regions and labels.
TOOLVERIFIER: Generalization to New Tools via Self-Verification
Teaching language models to use tools is an important milestone towards building general assistants, but remains an open problem.
PrimeNet: Pre-Training for Irregular Multivariate Time Series
In this work, we propose PrimeNet to learn a self-supervised representation for irregular multivariate time series.
Investigating Rumor News Using Agreement-Aware Search
We build Maester based on the following two key observations: (1) relatedness can commonly be determined by keywords and entities occurring in both questions and articles, and (2) the level of agreement between the investigative question and the related news article can often be decided by a few key sentences.
Answer is All You Need: Instruction-following Text Embedding via Answering the Question
This work aims to build a text embedder that can capture characteristics of texts specified by user instructions.
User-Guided Aspect Classification for Domain-Specific Texts
Aspect classification, identifying aspects of text segments, facilitates numerous applications, such as sentiment analysis and review summarization.
Overfitting or Underfitting? Understand Robustness Drop in Adversarial Training
Our goal is to understand why the robustness drops after conducting adversarial training for too long.
UCEpic: Unifying Aspect Planning and Lexical Constraints for Generating Explanations in Recommendation
Then, to obtain personalized explanations under this framework of insertion-based generation, we design a method of incorporating aspect planning and personalized references into the insertion process.
Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language Models
In this paper, we introduce a novel training data selection based on the learning percentage of the samples.
META: Metadata-Empowered Weak Supervision for Text Classification
Based on seed words, we rank and filter motif instances to distill highly label-indicative ones as {``}seed motifs{''}, which provide additional weak supervision.
SeNsER: Learning Cross-Building Sensor Metadata Tagger
Sensor metadata tagging, akin to the named entity recognition task, provides key contextual information (e. g., measurement type and location) about sensors for running smart building applications.
Generating Efficient Training Data via LLM-based Attribute Manipulation
In this paper, we propose a novel method, Chain-of-Thoughts Attribute Manipulation (CoTAM), to guide few-shot learning by carefully crafted data from Large Language Models (LLMs).
Formulating Few-shot Fine-tuning Towards Language Model Pre-training: A Pilot Study on Named Entity Recognition
Fine-tuning pre-trained language models has recently become a common practice in building NLP models for various tasks, especially few-shot tasks.
Leveraging QA Datasets to Improve Generative Data Augmentation
The ability of generative language models (GLMs) to generate text has improved considerably in the last few years, enabling their use for generative data augmentation.
LOPS: Learning Order Inspired Pseudo-Label Selection for Weakly Supervised Text Classification
Weakly supervised text classification methods typically train a deep neural classifier based on pseudo-labels.
FUSE: Multi-Faceted Set Expansion by Coherent Clustering of Skip-grams
In this paper, we study the task of multi-faceted set expansion, which aims to capture all semantic facets in the seed set and return multiple sets of entities, one for each semantic facet.
A Benchmark on Extremely Weakly Supervised Text Classification: Reconcile Seed Matching and Prompting Approaches
Etremely Weakly Supervised Text Classification (XWS-TC) refers to text classification based on minimal high-level human guidance, such as a few label-indicative seed words or classification instructions.
EmojiLM: Modeling the New Emoji Language
With the rapid development of the internet, online social media welcomes people with different backgrounds through its diverse content.
MetaIE: Distilling a Meta Model from LLM for All Kinds of Information Extraction Tasks
We construct the distillation dataset via sampling sentences from language model pre-training datasets (e. g., OpenWebText in our implementation) and prompting an LLM to identify the typed spans of "important information".
Sensei: Self-Supervised Sensor Name Segmentation
A sensor name, typically an alphanumeric string, encodes the key context (e. g., function and location) of a sensor needed for deploying smart building applications.
Data Quality Matters For Adversarial Training: An Empirical Study
Specifically, we first propose a strategy to measure the data quality based on the learning behaviors of the data during adversarial training and find that low-quality data may not be useful and even detrimental to the adversarial robustness.
Navigating Alignment for Non-identical Client Class Sets: A Label Name-Anchored Federated Learning Framework
Traditional federated classification methods, even those designed for non-IID clients, assume that each client annotates its local data with respect to the same universal class set.
Towards Open-World Product Attribute Mining: A Lightly-Supervised Approach
We present a new task setting for attribute mining on e-commerce products, serving as a practical solution to extract open-world attributes without extensive human intervention.
Fine-grained Contrastive Learning for Relation Extraction
Recent relation extraction (RE) works have shown encouraging improvements by conducting contrastive learning on silver labels generated by distant supervision before fine-tuning on gold labels.
Ranked #36 on
Relation Extraction
on DocRED
Progressive Sentiment Analysis for Code-Switched Text Data
Instead of training on the entire code-switched corpus at once, we create buckets based on the fraction of words in the resource-rich language and progressively train from resource-rich language dominated samples to low-resource language dominated samples.
READ: Improving Relation Extraction from an ADversarial Perspective
This strategy enables a larger attack budget for entities and coaxes the model to leverage relational patterns embedded in the context.
WOT-Class: Weakly Supervised Open-world Text Classification
State-of-the-art weakly supervised text classification methods, while significantly reduced the required human supervision, still requires the supervision to cover all the classes of interest.
Less than One-shot: Named Entity Recognition via Extremely Weak Supervision
We study the named entity recognition (NER) problem under the extremely weak supervision (XWS) setting, where only one example entity per type is given in a context-free way.
MetaPAD: Meta Pattern Discovery from Massive Text Corpora
We propose an efficient framework, called MetaPAD, which discovers meta patterns from massive corpora with three techniques: (1) it develops a context-aware segmentation method to carefully determine the boundaries of patterns with a learnt pattern quality assessment function, which avoids costly dependency parsing and generates high-quality patterns; (2) it identifies and groups synonymous meta patterns from multiple facets---their types, contexts, and extractions; and (3) it examines type distributions of entities in the instances extracted by each group of patterns, and looks for appropriate type levels to make discovered patterns precise.
DPPred: An Effective Prediction Framework with Concise Discriminative Patterns
In the literature, two series of models have been proposed to address prediction problems including classification and regression.
A Parallel and Efficient Algorithm for Learning to Match
In this paper, we tackle this challenge with a novel parallel and efficient algorithm for feature-based matrix factorization.
Arabic Named Entity Recognition: What Works and What's Next
This paper presents the winning solution to the Arabic Named Entity Recognition challenge run by Topcoder. com.
SynSetExpan: An Iterative Framework for Joint Entity Set Expansion and Synonym Discovery
To facilitate the research on studying the interplays of these two tasks, we create the first large-scale Synonym-Enhanced Set Expansion (SE2) dataset via crowdsourcing.
Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
Specifically, we jointly train two modules with different inductive biases -- a text analysis module for text understanding and a network learning module for class-discriminative, scalable network learning.
"Average" Approximates "First Principal Component"? An Empirical Analysis on Representations from Neural Language Models
In this paper, we present an empirical property of these representations -- "average" approximates "first principal component".
News Meets Microblog: Hashtag Annotation via Retriever-Generator
Hashtag annotation for microblog posts has been recently formulated as a sequence generation problem to handle emerging hashtags that are unseen in the training set.
TaxoClass: Hierarchical Multi-Label Text Classification Using Only Class Names
Hierarchical multi-label text classification (HMTC) aims to tag each document with a set of classes from a taxonomic class hierarchy.
Multi Label Text Classification
Multi-Label Text Classification
+3
Coarse2Fine: Fine-grained Text Classification on Coarsely-grained Annotated Data
Existing text classification methods mainly focus on a fixed label set, whereas many real-world applications require extending to new fine-grained classes as the number of samples per label increases.
BFClass: A Backdoor-free Text Classification Framework
To recognize the poisoned subset, we examine the training samples with these identified triggers as the most suspicious token, and check if removing the trigger will change the poisoned model's prediction.
Label Noise in Adversarial Training: A Novel Perspective to Study Robust Overfitting
We show that label noise exists in adversarial training.
Perturbation Deterioration: The Other Side of Catastrophic Overfitting
While this phenomenon is commonly explained as overfitting, we observe that it is a twin process: not only does the model catastrophic overfits to one type of perturbation, but also the perturbation deteriorates into random noise.
“Average” Approximates “First Principal Component”? An Empirical Analysis on Representations from Neural Language Models
In this paper, we present an empirical property of these representations—”average” approximates “first principal component”.
Learning Adaptive Axis Attentions in Fine-tuning: Beyond Fixed Sparse Attention Patterns
We present a comprehensive study of sparse attention patterns in Transformer models.
Towards Collaborative Neural-Symbolic Graph Semantic Parsing via Uncertainty
Recent work in task-independent graph semantic parsing has shifted from grammar-based symbolic approaches to neural models, showing strong performance on different types of meaning representations.
Phrase-aware Unsupervised Constituency Parsing
Recent studies have achieved inspiring success in unsupervised grammar induction using masked language modeling (MLM) as the proxy task.
WeDef: Weakly Supervised Backdoor Defense for Text Classification
Inspired by this observation, in WeDef, we define the reliability of samples based on whether the predictions of the weak classifier agree with their labels in the poisoned training set.
SoTeacher: A Student-oriented Teacher Network Training Framework for Knowledge Distillation
To fill this gap, we propose a novel student-oriented teacher network training framework SoTeacher, inspired by recent findings that student performance hinges on teacher's capability to approximate the true label distribution of training samples.
WavSpA: Wavelet Space Attention for Boosting Transformers' Long Sequence Learning Ability
Recent works show that learning attention in the Fourier space can improve the long sequence learning capability of Transformers.
MGDoc: Pre-training with Multi-granular Hierarchy for Document Image Understanding
In contrast, region-level models attempt to encode regions corresponding to paragraphs or text blocks into a single embedding, but they perform worse with additional word-level features.
Unleashing the Power of Shared Label Structures for Human Activity Recognition
In this paper, we propose SHARE, a HAR framework that takes into account shared structures of label names for different activities.
Gradient-based Wang-Landau Algorithm: A Novel Sampler for Output Distribution of Neural Networks over the Input Space
We first draw the connection between the output distribution of a NN and the density of states (DOS) of a physical system.
Towards Diverse and Coherent Augmentation for Time-Series Forecasting
We note that augmentation designed for forecasting requires diversity as well as coherence with the original temporal dynamics.
Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path
In this paper, we propose a new approach, ReXMiner, for zero-shot relation extraction in web mining.
Open-world Semi-supervised Generalized Relation Discovery Aligned in a Real-world Setting
Motivated by these insights, we present a novel method called KNoRD (Known and Novel Relation Discovery), which effectively classifies explicitly and implicitly expressed relations from known and novel classes within unlabeled data.
Debiasing Made State-of-the-art: Revisiting the Simple Seed-based Weak Supervision for Text Classification
We show that the limited performance of seed matching is largely due to the label bias injected by the simple seed-match rule, which prevents the classifier from learning reliable confidence for selecting high-quality pseudo-labels.
SELFOOD: Self-Supervised Out-Of-Distribution Detection via Learning to Rank
To address the annotation bottleneck, we introduce SELFOOD, a self-supervised OOD detection method that requires only in-distribution samples as supervision.
Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation
Recent advances of incorporating layout information, typically bounding box coordinates, into pre-trained language models have achieved significant performance in entity recognition from document images.
PV2TEA: Patching Visual Modality to Textual-Established Information Extraction
Information extraction, e. g., attribute value extraction, has been extensively studied and formulated based only on text.
Concept2Box: Joint Geometric Embeddings for Learning Two-View Knowledge Graphs
We propose Concept2Box, a novel approach that jointly embeds the two views of a KG using dual geometric representations.
Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Models
Medical image classification is a critical problem for healthcare, with the potential to alleviate the workload of doctors and facilitate diagnoses of patients.
Critique Ability of Large Language Models
In the era of large language models (LLMs), this study explores the ability of LLMs to deliver accurate critiques across various tasks.
Fast-ELECTRA for Efficient Pre-training
Although ELECTRA offers a significant boost in efficiency, its potential is constrained by the training cost brought by the auxiliary model.
Eliminating Reasoning via Inferring with Planning: A New Framework to Guide LLMs' Non-linear Thinking
Chain-of-Thought(CoT) prompting and its variants explore equipping large language models (LLMs) with high-level reasoning abilities by emulating human-like linear cognition and logic.
ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation
This benchmark contains the rich, nuanced phenomena that can be tricky for current toxicity detection models to identify, revealing a significant domain difference compared to social media content.
DAIL: Data Augmentation for In-Context Learning via Self-Paraphrase
DAIL leverages the intuition that large language models are more familiar with the content generated by themselves.
Physics-Informed Data Denoising for Real-Life Sensing Systems
By obviating the need for ground truth clean data, our method offers a practical denoising solution for real-world applications.
OMNIINPUT: A Model-centric Evaluation Framework through Output Distribution
We propose a novel model-centric evaluation framework, OmniInput, to evaluate the quality of an AI/ML model's predictions on all possible inputs (including human-unrecognizable ones), which is crucial for AI safety and reliability.
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
We propose the Chain-of-Table framework, where tabular data is explicitly used in the reasoning chain as a proxy for intermediate thoughts.
Ranked #3 on
Table-based Fact Verification
on TabFact
Multi-step Problem Solving Through a Verifier: An Empirical Analysis on Model-induced Process Supervision
Process supervision, using a trained verifier to evaluate the intermediate steps generated by reasoner, has demonstrated significant improvements in multi-step problem solving.
MEMORYLLM: Towards Self-Updatable Large Language Models
Existing Large Language Models (LLMs) usually remain static after deployment, which might make it hard to inject new knowledge into the model.
Can LLMs Learn from Previous Mistakes? Investigating LLMs' Errors to Boost for Reasoning
We conduct a series of experiments to prove LLMs can obtain benefits from mistakes in both directions.
DOCMASTER: A Unified Platform for Annotation, Training, & Inference in Document Question-Answering
The application of natural language processing models to PDF documents is pivotal for various business applications yet the challenge of training models for this purpose persists in businesses due to specific hurdles.
Learn from Failure: Fine-Tuning LLMs with Trial-and-Error Data for Intuitionistic Propositional Logic Proving
Recent advances in Automated Theorem Proving have shown the effectiveness of leveraging a (large) language model that generates tactics (i. e. proof steps) to search through proof states.
Incubating Text Classifiers Following User Instruction with Nothing but LLM
In this paper, we aim to generate text classification data given arbitrary class definitions (i. e., user instruction), so one can train a small text classifier without any human annotation or raw corpus.
Beyond Scaling: Predicting Patent Approval with Domain-specific Fine-grained Claim Dependency Graph
In this paper, we delve into the patent approval pre-diction task and unveil that simple domain-specific graph methods outperform enlarging the model, using the intrinsic dependencies within the patent data.
