Search Results for author:
Found 40 papers, 20 papers with code
Cross-domain Named Entity Recognition via Graph Matching
Cross-domain NER is a practical yet challenging problem since the data scarcity in the real-world scenario.
CATE: A Contrastive Pre-trained Model for Metaphor Detection with Semi-supervised Learning
Metaphors are ubiquitous in natural language, and detecting them requires contextual reasoning about whether a semantic incongruence actually exists.
MODE-LSTM: A Parameter-efficient Recurrent Network with Multi-Scale for Sentence Classification
The central problem of sentence classification is to extract multi-scale n-gram features for understanding the semantic meaning of sentences.
Self-Adaptive Reconstruction with Contrastive Learning for Unsupervised Sentence Embeddings
However, due to the token bias in pretrained language models, the models can not capture the fine-grained semantics in sentences, which leads to poor predictions.
Conditional Logical Message Passing Transformer for Complex Query Answering
In this paper, we propose Conditional Logical Message Passing Transformer (CLMPT), which considers the difference between constants and variables in the case of using pre-trained neural link predictors and performs message passing conditionally on the node type.
Incremental Sequence Labeling: A Tale of Two Shifts
As for the E2O problem, we use knowledge distillation to maintain the model's discriminative ability for old entities.
Balancing the Causal Effects in Class-Incremental Learning
In this way, the model is encouraged to adapt to all classes with causal effects from both new and old data and thus alleviates the causal imbalance problem.
Class Incremental Learning
Continual Named Entity Recognition
+6
Concept-1K: A Novel Benchmark for Instance Incremental Learning
However, existing IL scenarios and datasets are unqualified for assessing forgetting in PLMs, giving an illusion that PLMs do not suffer from catastrophic forgetting.
Beyond Anti-Forgetting: Multimodal Continual Instruction Tuning with Positive Forward Transfer
The discrepancy results in the model learning irrelevant information for old and pre-trained tasks, which leads to catastrophic forgetting and negative forward transfer.
InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks
In this paper, we introduce InfiAgent-DABench, the first benchmark specifically designed to evaluate LLM-based agents on data analysis tasks.
Learn or Recall? Revisiting Incremental Learning with Pre-trained Language Models
Most assume that catastrophic forgetting is the biggest obstacle to achieving superior IL performance and propose various techniques to overcome this issue.
Improving Factual Consistency of Text Summarization by Adversarially Decoupling Comprehension and Embellishment Abilities of LLMs
Despite the recent progress in text summarization made by large language models (LLMs), they often generate summaries that are factually inconsistent with original articles, known as "hallucinations" in text generation.
LoBaSS: Gauging Learnability in Supervised Fine-tuning Data
In this paper, we introduce a new dimension in SFT data selection: learnability.
Let's reward step by step: Step-Level reward model as the Navigators for Reasoning
Recent years have seen considerable advancements in multi-step reasoning with Large Language Models (LLMs).
Neural Operator Variational Inference based on Regularized Stein Discrepancy for Deep Gaussian Processes
Furthermore, our method guarantees theoretically controlled prediction error for DGP models and demonstrates remarkable performance on various datasets.
Preserving Commonsense Knowledge from Pre-trained Language Models via Causal Inference
Intriguingly, the unified objective can be seen as the sum of the vanilla fine-tuning objective, which learns new knowledge from target data, and the causal objective, which preserves old knowledge from PLMs.
Perturbation-based Self-supervised Attention for Attention Bias in Text Classification
In text classification, the traditional attention mechanisms usually focus too much on frequent words, and need extensive labeled data in order to learn.
A Survey on Time-Series Pre-Trained Models
Time-Series Mining (TSM) is an important research area since it shows great potential in practical applications.
Probabilistic Human Mesh Recovery in 3D Scenes from Egocentric Views
One of the biggest challenges of this task is severe body truncation due to close social distances in egocentric scenarios, which brings large pose ambiguities for unseen body parts.
Dynamic Point Fields
In this work, we present a dynamic point field model that combines the representational benefits of explicit point-based graphics with implicit deformation networks to allow efficient modeling of non-rigid 3D surfaces.
Pair-Based Joint Encoding with Relational Graph Convolutional Networks for Emotion-Cause Pair Extraction
Emotion-cause pair extraction (ECPE) aims to extract emotion clauses and corresponding cause clauses, which have recently received growing attention.
Distilling Causal Effect from Miscellaneous Other-Class for Continual Named Entity Recognition
Thanks to the causal inference, we identify that the forgetting is caused by the missing causal effect from the old data.
Ranked #1 on
FG-1-PG-1
on conll2003
Neural Point-based Shape Modeling of Humans in Challenging Clothing
Specifically, we extend point-based methods with a coarse stage, that replaces canonicalization with a learned pose-independent "coarse shape" that can capture the rough surface geometry of clothing like skirts.
EgoBody: Human Body Shape and Motion of Interacting People from Head-Mounted Devices
Key to reasoning about interactions is to understand the body pose and motion of the interaction partner from the egocentric view.
The Power of Points for Modeling Humans in Clothing
The geometry feature can be optimized to fit a previously unseen scan of a person in clothing, enabling the scan to be reposed realistically.
Hierarchy-aware Label Semantics Matching Network for Hierarchical Text Classification
We then introduce a joint embedding loss and a matching learning loss to model the matching relationship between the text semantics and the label semantics.
A Span-based Dynamic Local Attention Model for Sequential Sentence Classification
Sequential sentence classification aims to classify each sentence in the document based on the context in which sentences appear.
MetaAvatar: Learning Animatable Clothed Human Models from Few Depth Images
In contrast, we propose an approach that can quickly generate realistic clothed human avatars, represented as controllable neural SDFs, given only monocular depth images.
Embedding-based Product Retrieval in Taobao Search
We evaluate MGDSPR on Taobao Product Search with significant metrics gains observed in offline experiments and online A/B tests.
Learning Representations for Incomplete Time Series Clustering
Also, to reduce the error propagation from imputation to clustering, we introduce a discriminator to make the distribution of imputation values close to the true one and train CRLI in an alternating train- ing manner.
SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements
We demonstrate the efficacy of our surface representation by learning models of complex clothing from point clouds.
SCANimate: Weakly Supervised Learning of Skinned Clothed Avatar Networks
We present SCANimate, an end-to-end trainable framework that takes raw 3D scans of a clothed human and turns them into an animatable avatar.
PLACE: Proximity Learning of Articulation and Contact in 3D Environments
To synthesize realistic human-scene interactions, it is essential to effectively represent the physical contact and proximity between the body and the world.
Learning Representations for Time Series Clustering
When applying seq2seq to time series clustering, obtaining a representation that effectively represents the temporal dynamics of the sequence, multi-scale features, and good clustering properties remains a challenge.
Learning to Dress 3D People in Generative Clothing
To our knowledge, this is the first generative model that directly dresses 3D human body meshes and generalizes to different poses.
Unified Attentional Generative Adversarial Network for Brain Tumor Segmentation From Multimodal Unpaired Images
Currently, most deep models for multimodal segmentation rely on paired registered images.
Frontal Low-rank Random Tensors for Fine-grained Action Segmentation
In this paper, we propose an approach to representing high-order information for temporal action segmentation via a simple yet effective bilinear form.
Classification of lung nodules in CT images based on Wasserstein distance in differential geometry
The Wasserstein distance between the nodules is calculated based on our new spherical optimal mass transport, this new algorithm works directly on sphere by using spherical metric, which is much more accurate and efficient than previous methods.
Deep-ESN: A Multiple Projection-encoding Hierarchical Reservoir Computing Framework
As an efficient recurrent neural network (RNN) model, reservoir computing (RC) models, such as Echo State Networks, have attracted widespread attention in the last decade.
Theano: A Python framework for fast computation of mathematical expressions
Since its introduction, it has been one of the most used CPU and GPU mathematical compilers - especially in the machine learning community - and has shown steady performance improvements.
