Search Results for author:
Found 261 papers, 120 papers with code
A Re-ranking Model for Dependency Parser with Recursive Convolutional Neural Network
In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations.
Overview of the NLPCC 2015 Shared Task: Chinese Word Segmentation and POS Tagging for Micro-blog Texts
In this paper, we give an overview for the shared task at the 4th CCF Conference on Natural Language Processing \& Chinese Computing (NLPCC 2015): Chinese word segmentation and part-of-speech (POS) tagging for micro-blog texts.
Gaussian Mixture Embeddings for Multiple Word Prototypes
In this paper, we propose the Gaussian mixture skip-gram (GMSG) model to learn the Gaussian mixture embeddings for words based on skip-gram framework.
Bridging LSTM Architecture and the Neural Dynamics during Reading
Recently, the long short-term memory neural network (LSTM) has attracted wide interest due to its success in many tasks.
Recurrent Neural Network for Text Classification with Multi-Task Learning
Neural network based methods have obtained great progress on a variety of natural language processing tasks.
Ranked #10 on
Emotion Recognition in Conversation
on CPED
Emotion Recognition in Conversation
General Classification
+3
Modelling Interaction of Sentence Pair with coupled-LSTMs
Recently, there is rising interest in modelling the interactions of two sentences with deep neural networks.
Ranked #73 on
Natural Language Inference
on SNLI
Syntax-based Attention Model for Natural Language Inference
Introducing attentional mechanism in neural network is a powerful concept, and has achieved impressive results in many natural language processing tasks.
Neural Sentence Ordering
Sentence ordering is a general and critical task for natural language generation applications.
Learning Word Embeddings from Intrinsic and Extrinsic Views
To prove the effectiveness of our model, we evaluate it on four tasks, including word similarity, reverse dictionaries, Wiki link prediction, and document classification.
Deep Multi-Task Learning with Shared Memory
Neural network based models have achieved impressive results on various specific tasks.
End-to-End Neural Sentence Ordering Using Pointer Network
However, it is nontrivial for pair-wise models to incorporate the contextual sentence information.
A Feature-Enriched Neural Model for Joint Chinese Word Segmentation and Part-of-Speech Tagging
Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering.
Knowledge Graph Representation with Jointly Structural and Textual Encoding
In this paper, we propose a novel deep architecture to utilize both structural and textual information of entities.
Attention-Based Convolutional Neural Network for Semantic Relation Extraction
Nowadays, neural networks play an important role in the task of relation classification.
Ranked #26 on
Relation Extraction
on SemEval-2010 Task-8
Hashtag Recommendation Using End-To-End Memory Networks with Hierarchical Attention
By incorporating the hierarchical attention mechanism, the relative improvement in the proposed method over the state-of-the-art method is around 67. 9{\%} in the F1-score.
Adversarial Multi-task Learning for Text Classification
Neural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features.
Adversarial Multi-Criteria Learning for Chinese Word Segmentation
Different linguistic perspectives causes many diverse segmentation criteria for Chinese word segmentation (CWS).
Dynamic Compositional Neural Networks over Tree Structure
Tree-structured neural networks have proven to be effective in learning semantic representations by exploiting syntactic information.
Overview of the NLPCC 2017 Shared Task: Chinese News Headline Categorization
In this paper, we give an overview for the shared task at the CCF Conference on Natural Language Processing \& Chinese Computing (NLPCC 2017): Chinese News Headline Categorization.
DAG-based Long Short-Term Memory for Neural Word Segmentation
In this paper, we propose a new neural model to incorporate the word-level information for Chinese word segmentation.
Idiom-Aware Compositional Distributed Semantics
Idioms are peculiar linguistic constructions that impose great challenges for representing the semantics of language, especially in current prevailing end-to-end neural models, which assume that the semantics of a phrase or sentence can be literally composed from its constitutive words.
Part-of-Speech Tagging for Twitter with Adversarial Neural Networks
In this work, we study the problem of part-of-speech tagging for Tweets.
Ranked #3 on
Part-Of-Speech Tagging
on Ritter
A Learning Error Analysis for Structured Prediction with Approximate Inference
In this work, we try to understand the differences between exact and approximate inference algorithms in structured prediction.
Meta Multi-Task Learning for Sequence Modeling
Specifically, we use a shared meta-network to capture the meta-knowledge of semantic composition and generate the parameters of the task-specific semantic composition models.
Incorporating Discriminator in Sentence Generation: a Gibbs Sampling Method
Generating plausible and fluent sentence with desired properties has long been a challenge.
Toward Diverse Text Generation with Inverse Reinforcement Learning
Similar to the adversarial models, the reward and policy function in IRL are optimized alternately.
Information Aggregation via Dynamic Routing for Sequence Encoding
The dynamic routing policy is dynamically deciding that what and how much information need be transferred from each word to the final encoding of the text sequence.
Ranked #43 on
Sentiment Analysis
on IMDb
Task-oriented Dialogue System for Automatic Diagnosis
In this paper, we make a move to build a dialogue system for automatic diagnosis.
Cross-Domain Sentiment Classification with Target Domain Specific Information
And we introduce a few target domain labeled data for learning domain-specific information.
Incorporating Argument-Level Interactions for Persuasion Comments Evaluation using Co-attention Model
In this paper, we investigate the issue of persuasiveness evaluation for argumentative comments.
A Lexicon-Based Supervised Attention Model for Neural Sentiment Analysis
Attention mechanisms have been leveraged for sentiment classification tasks because not all words have the same importance.
A Reinforcement Learning Framework for Natural Question Generation using Bi-discriminators
Visual Question Generation (VQG) aims to ask natural questions about an image automatically.
Gaussian Word Embedding with a Wasserstein Distance Loss
Therefore, with the aim of representing words in a highly efficient way, we propose to operate a Gaussian word embedding model with a loss function based on the Wasserstein distance.
Exploring Shared Structures and Hierarchies for Multiple NLP Tasks
Designing shared neural architecture plays an important role in multi-task learning.
Deformable Stacked Structure for Named Entity Recognition
Neural architecture for named entity recognition has achieved great success in the field of natural language processing.
Automatic Essay Scoring Incorporating Rating Schema via Reinforcement Learning
Automatic essay scoring (AES) is the task of assigning grades to essays without human interference.
Convolutional Interaction Network for Natural Language Inference
Attention-based neural models have achieved great success in natural language inference (NLI).
Transferring from Formal Newswire Domain with Hypernet for Twitter POS Tagging
However, from a linguistic perspective, Twitter users not only tend to mimic the formal expressions of traditional media, like news, but they also appear to be developing linguistically informal styles.
Ranked #2 on
Part-Of-Speech Tagging
on Ritter
Meta-Learning Multi-task Communication
In this paper, we describe a general framework: Parameters Read-Write Networks (PRaWNs) to systematically analyze current neural models for multi-task learning, in which we find that existing models expect to disentangle features into different spaces while features learned in practice are still entangled in shared space, leaving potential hazards for other training or unseen tasks.
Incorporating Topic Aspects for Online Comment Convincingness Evaluation
In this paper, we propose to incorporate topic aspects information for online comments convincingness evaluation.
Long Short-Term Memory with Dynamic Skip Connections
In recent years, long short-term memory (LSTM) has been successfully used to model sequential data of variable length.
Ranked #33 on
Sentiment Analysis
on IMDb
Contextualized Non-local Neural Networks for Sequence Learning
Recently, a large number of neural mechanisms and models have been proposed for sequence learning, of which self-attention, as exemplified by the Transformer model, and graph neural networks (GNNs) have attracted much attention.
VCWE: Visual Character-Enhanced Word Embeddings
Chinese is a logographic writing system, and the shape of Chinese characters contain rich syntactic and semantic information.
A Graph-based Model for Joint Chinese Word Segmentation and Dependency Parsing
Our graph-based joint model achieves better performance than previous joint models and state-of-the-art results in both Chinese word segmentation and dependency parsing.
How to Fine-Tune BERT for Text Classification?
Language model pre-training has proven to be useful in learning universal language representations.
Ranked #1 on
Text Classification
on Yahoo! Answers
Style Transformer: Unpaired Text Style Transfer without Disentangled Latent Representation
Disentangling the content and style in the latent space is prevalent in unpaired text style transfer.
Learning Task-specific Representation for Novel Words in Sequence Labeling
However, representations of unseen or rare words trained on the end task are usually poor for appreciable performance.
Distantly Supervised Named Entity Recognition using Positive-Unlabeled Learning
In this work, we explore the way to perform named entity recognition (NER) using only unlabeled data and named entity dictionaries.
A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder
Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion.
Bridging by Word: Image Grounded Vocabulary Construction for Visual Captioning
Existing research usually employs the architecture of CNN-RNN that views the generation as a sequential decision-making process and the entire dataset vocabulary is used as decoding space.
Generating Responses with a Specific Emotion in Dialog
It is desirable for dialog systems to have capability to express specific emotions during a conversation, which has a direct, quantifiable impact on improvement of their usability and user satisfaction.
Searching for Effective Neural Extractive Summarization: What Works and What's Next
The recent years have seen remarkable success in the use of deep neural networks on text summarization.
Ranked #6 on
Extractive Text Summarization
on CNN / Daily Mail
DropAttention: A Regularization Method for Fully-Connected Self-Attention Networks
Variants dropout methods have been designed for the fully-connected layer, convolutional layer and recurrent layer in neural networks, and shown to be effective to avoid overfitting.
Simplify the Usage of Lexicon in Chinese NER
This method avoids designing a complicated sequence modeling architecture, and for any neural NER model, it requires only subtle adjustment of the character representation layer to introduce the lexicon information.
Ranked #8 on
Chinese Named Entity Recognition
on Resume NER
Chinese Named Entity Recognition
named-entity-recognition
+2
GlossBERT: BERT for Word Sense Disambiguation with Gloss Knowledge
Word Sense Disambiguation (WSD) aims to find the exact sense of an ambiguous word in a particular context.
Ranked #3 on
Word Sense Disambiguation
on WiC-TSV
Exploring Domain Shift in Extractive Text Summarization
Although domain shift has been well explored in many NLP applications, it still has received little attention in the domain of extractive text summarization.
Weighed Domain-Invariant Representation Learning for Cross-domain Sentiment Analysis
To address this problem, we propose a modification to DIRL, obtaining a novel weighted domain-invariant representation learning (WDIRL) framework.
Towards Interpretable Evaluations: A Case Study of Named Entity Recognition
With the proliferation of models for natural language processing (NLP) tasks, it is even harder to understand the differences between models and their relative merits.
A Closer Look at Data Bias in Neural Extractive Summarization Models
In this paper, we take stock of the current state of summarization datasets and explore how different factors of datasets influence the generalization behaviour of neural extractive summarization models.
Asynchronous Deep Interaction Network for Natural Language Inference
However, in the process of reasoning, the role of the two sentences is obviously different, and the sentence pairs for NLI are asymmetrical corpora.
A Lexicon-Based Graph Neural Network for Chinese NER
Recurrent neural networks (RNN) used for Chinese named entity recognition (NER) that sequentially track character and word information have achieved great success.
Ranked #13 on
Chinese Named Entity Recognition
on OntoNotes 4
Chinese Named Entity Recognition
named-entity-recognition
+3
Discrete Argument Representation Learning for Interactive Argument Pair Identification
In this paper, we focus on extracting interactive argument pairs from two posts with opposite stances to a certain topic.
Keep it Consistent: Topic-Aware Storytelling from an Image Stream via Iterative Multi-agent Communication
Visual storytelling aims to generate a narrative paragraph from a sequence of images automatically.
Ranked #9 on
Visual Storytelling
on VIST
Learning Sparse Sharing Architectures for Multiple Tasks
Most existing deep multi-task learning models are based on parameter sharing, such as hard sharing, hierarchical sharing, and soft sharing.
Constructing Multiple Tasks for Augmentation: Improving Neural Image Classification With K-means Features
In order to effectively reduce the impact of non-ideal auxiliary tasks on the main task, we further proposed a novel meta-learning-based multi-task learning approach, which trained the shared hidden layers on auxiliary tasks, while the meta-optimization objective was to minimize the loss on the main task, ensuring that the optimizing direction led to an improvement on the main task.
Chinese Named Entity Recognition Augmented with Lexicon Memory
Inspired by a concept of content-addressable retrieval from cognitive science, we propose a novel fragment-based model augmented with a lexicon-based memory for Chinese NER, in which both the character-level and word-level features are combined to generate better feature representations for possible name candidates.
Chinese Named Entity Recognition
named-entity-recognition
+4
Rethinking Generalization of Neural Models: A Named Entity Recognition Case Study
While neural network-based models have achieved impressive performance on a large body of NLP tasks, the generalization behavior of different models remains poorly understood: Does this excellent performance imply a perfect generalization model, or are there still some limitations?
K-Adapter: Infusing Knowledge into Pre-Trained Models with Adapters
We study the problem of injecting knowledge into large pre-trained models like BERT and RoBERTa.
Ranked #1 on
Entity Typing
on Open Entity
Improving BERT Fine-Tuning via Self-Ensemble and Self-Distillation
Fine-tuning pre-trained language models like BERT has become an effective way in NLP and yields state-of-the-art results on many downstream tasks.
Pre-trained Models for Natural Language Processing: A Survey
Recently, the emergence of pre-trained models (PTMs) has brought natural language processing (NLP) to a new era.
Storytelling from an Image Stream Using Scene Graphs
In particular, on the within-image level, we employ a Graph Convolution Network (GCN) to enrich local fine-grained region representations of objects on scene graphs.
Ranked #7 on
Visual Storytelling
on VIST
Unified Multi-Criteria Chinese Word Segmentation with BERT
Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework.
Extractive Summarization as Text Matching
This paper creates a paradigm shift with regard to the way we build neural extractive summarization systems.
Ranked #1 on
Text Summarization
on BBC XSum
FLAT: Chinese NER Using Flat-Lattice Transformer
Recently, the character-word lattice structure has been proved to be effective for Chinese named entity recognition (NER) by incorporating the word information.
Ranked #5 on
Chinese Named Entity Recognition
on MSRA
Chinese Named Entity Recognition
named-entity-recognition
+3
Heterogeneous Graph Neural Networks for Extractive Document Summarization
An intuitive way is to put them in the graph-based neural network, which has a more complex structure for capturing inter-sentence relationships.
Leveraging Declarative Knowledge in Text and First-Order Logic for Fine-Grained Propaganda Detection
We study the detection of propagandistic text fragments in news articles.
Hierarchical Reinforcement Learning for Automatic Disease Diagnosis
Existing approaches usually employ a flat policy structure that treat all symptoms and diseases equally for action making.
Hierarchical Reinforcement Learning
reinforcement-learning
+1
Defense against Adversarial Attacks in NLP via Dirichlet Neighborhood Ensemble
Despite neural networks have achieved prominent performance on many natural language processing (NLP) tasks, they are vulnerable to adversarial examples.
Evaluating and Enhancing the Robustness of Neural Network-based Dependency Parsing Models with Adversarial Examples
Despite achieving prominent performance on many important tasks, it has been reported that neural networks are vulnerable to adversarial examples.
Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis
Based on the SemEval 2014 dataset, we construct the Aspect Robustness Test Set (ARTS) as a comprehensive probe of the aspect robustness of ABSA models.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
fastHan: A BERT-based Multi-Task Toolkit for Chinese NLP
The joint-model is trained and evaluated on 13 corpora of four tasks, yielding near state-of-the-art (SOTA) performance in dependency parsing and NER, achieving SOTA performance in CWS and POS.
CoLAKE: Contextualized Language and Knowledge Embedding
With the emerging branch of incorporating factual knowledge into pre-trained language models such as BERT, most existing models consider shallow, static, and separately pre-trained entity embeddings, which limits the performance gains of these models.
CDEvalSumm: An Empirical Study of Cross-Dataset Evaluation for Neural Summarization Systems
In this paper, we perform an in-depth analysis of characteristics of different datasets and investigate the performance of different summarization models under a cross-dataset setting, in which a summarizer trained on one corpus will be evaluated on a range of out-of-domain corpora.
Cross-Lingual Dependency Parsing by POS-Guided Word Reordering
The words in each sentence of a source language corpus are rearranged to meet the word order in a target language under the guidance of a part-of-speech based language model (LM).
Toward Recognizing More Entity Types in NER: An Efficient Implementation using Only Entity Lexicons
In this work, we explore the way to quickly adjust an existing named entity recognition (NER) system to make it capable of recognizing entity types not defined in the system.
Automatic Term Name Generation for Gene Ontology: Task and Dataset
Terms contained in Gene Ontology (GO) have been widely used in biology and bio-medicine.
RethinkCWS: Is Chinese Word Segmentation a Solved Task?
The performance of the Chinese Word Segmentation (CWS) systems has gradually reached a plateau with the rapid development of deep neural networks, especially the successful use of large pre-trained models.
Text Information Aggregation with Centrality Attention
A lot of natural language processing problems need to encode the text sequence as a fix-length vector, which usually involves aggregation process of combining the representations of all the words, such as pooling or self-attention.
Modeling Evolution of Message Interaction for Rumor Resolution
Previous work for rumor resolution concentrates on exploiting time-series characteristics or modeling topology structure separately.
An Enhanced Knowledge Injection Model for Commonsense Generation
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts.
SenSeNet: Neural Keyphrase Generation with Document Structure
Keyphrase Generation (KG) is the task of generating central topics from a given document or literary work, which captures the crucial information necessary to understand the content.
Topic-Oriented Spoken Dialogue Summarization for Customer Service with Saliency-Aware Topic Modeling
In a customer service system, dialogue summarization can boost service efficiency by automatically creating summaries for long spoken dialogues in which customers and agents try to address issues about specific topics.
Unsupervised Summarization for Chat Logs with Topic-Oriented Ranking and Context-Aware Auto-Encoders
Automatic chat summarization can help people quickly grasp important information from numerous chat messages.
Uncertainty-Aware Label Refinement for Sequence Labeling
Conditional random fields (CRF) for label decoding has become ubiquitous in sequence labeling tasks.
Generating Adversarial Examples in Chinese Texts Using Sentence-Pieces
The substitutions in the generated adversarial examples are not characters or words but \textit{'pieces'}, which are more natural to Chinese readers.
TextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language Processing
To guarantee user acceptability, all the text transformations are linguistically based, and we provide a human evaluation for each one.
An Unsupervised Sampling Approach for Image-Sentence Matching Using Document-Level Structural Information
In this paper, we focus on the problem of unsupervised image-sentence matching.
Alleviate Exposure Bias in Sequence Prediction \\ with Recurrent Neural Networks
The key idea is that at each time step, the network takes as input a ``bundle'' of similar words predicted at the previous step instead of a single ground truth.
Mask Attention Networks: Rethinking and Strengthen Transformer
We therefore introduce a new layer named dynamic mask attention network (DMAN) with a learnable mask matrix which is able to model localness adaptively.
Ranked #11 on
Machine Translation
on WMT2014 English-German
Enhancing Scientific Papers Summarization with Citation Graph
Previous work for text summarization in scientific domain mainly focused on the content of the input document, but seldom considering its citation network.
Larger-Context Tagging: When and Why Does It Work?
The development of neural networks and pretraining techniques has spawned many sentence-level tagging systems that achieved superior performance on typical benchmarks.
Who Responded to Whom: The Joint Effects of Latent Topics and Discourse in Conversation Structure
Numerous online conversations are produced on a daily basis, resulting in a pressing need to conversation understanding.
Certified Robustness to Text Adversarial Attacks by Randomized [MASK]
Recently, few certified defense methods have been developed to provably guarantee the robustness of a text classifier to adversarial synonym substitutions.
Early Exiting with Ensemble Internal Classifiers
In this paper, we show that a novel objective function for the training of the ensemble internal classifiers can be naturally induced from the perspective of ensemble learning and information theory.
Accelerating BERT Inference for Sequence Labeling via Early-Exit
To alleviate this problem, we extend the recent successful early-exit mechanism to accelerate the inference of PTMs for sequence labeling tasks.
Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models
A sequence-to-sequence learning with neural networks has empirically proven to be an effective framework for Chinese Spelling Correction (CSC), which takes a sentence with some spelling errors as input and outputs the corrected one.
SpanNER: Named Entity Re-/Recognition as Span Prediction
Recent years have seen the paradigm shift of Named Entity Recognition (NER) systems from sequence labeling to span prediction.
TCIC: Theme Concepts Learning Cross Language and Vision for Image Captioning
Considering that theme concepts can be learned from both images and captions, we propose two settings for their representations learning based on TTN.
SENT: Sentence-level Distant Relation Extraction via Negative Training
In this work, we propose the use of negative training (NT), in which a model is trained using complementary labels regarding that ``the instance does not belong to these complementary labels".
Math Word Problem Solving with Explicit Numerical Values
In recent years, math word problem solving has received considerable attention and achieved promising results, but previous methods rarely take numerical values into consideration.
Defense against Synonym Substitution-based Adversarial Attacks via Dirichlet Neighborhood Ensemble
Although deep neural networks have achieved prominent performance on many NLP tasks, they are vulnerable to adversarial examples.
Align Voting Behavior with Public Statements for Legislator Representation Learning
In addition, we propose a novel task, namely hashtag usage prediction to model the ideology of legislators on Twitter.
Fine-Grained Element Identification in Complaint Text of Internet Fraud
Existing system dealing with online complaint provides a final decision without explanations.
Learning to Teach with Student Feedback
This one-way interaction leads to the teacher's inability to perceive the characteristics of the student and its training progress.
Constructing Phrase-level Semantic Labels to Form Multi-Grained Supervision for Image-Text Retrieval
Existing research for image text retrieval mainly relies on sentence-level supervision to distinguish matched and mismatched sentences for a query image.
Template-free Prompt Tuning for Few-shot NER
Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words.
KNN-BERT: Fine-Tuning Pre-Trained Models with KNN Classifier
Pre-trained models are widely used in fine-tuning downstream tasks with linear classifiers optimized by the cross-entropy loss, which might face robustness and stability problems.
Towards Efficient NLP: A Standard Evaluation and A Strong Baseline
ELUE is dedicated to depict the Pareto Frontier for various language understanding tasks, such that it can tell whether and how much a method achieves Pareto improvement.
Plug-Tagger: A Pluggable Sequence Labeling Framework Using Language Models
Specifically, for each task, a label word set is first constructed by selecting a high-frequency word for each class respectively, and then, task-specific vectors are inserted into the inputs and optimized to manipulate the model predictions towards the corresponding label words.
Black-Box Tuning for Language-Model-as-a-Service
In such a scenario, which we call Language-Model-as-a-Service (LMaaS), the gradients of PTMs are usually unavailable.
MVPTR: Multi-Level Semantic Alignment for Vision-Language Pre-Training via Multi-Stage Learning
In MVPTR, we follow the nested structure of both modalities to introduce concepts as high-level semantics.
Decorrelate Irrelevant, Purify Relevant: Overcome Textual Spurious Correlations from a Feature Perspective
Most of the existing debiasing methods often identify and weaken these samples with biased features (i. e., superficial surface features that cause such spurious correlations).
A Simple Hash-Based Early Exiting Approach For Language Understanding and Generation
Previous works usually adopt heuristic metrics such as the entropy of internal outputs to measure instance difficulty, which suffers from generalization and threshold-tuning.
MINER: Improving Out-of-Vocabulary Named Entity Recognition from an Information Theoretic Perspective
NER model has achieved promising performance on standard NER benchmarks.
Ranked #8 on
Named Entity Recognition (NER)
on WNUT 2017
A Benchmark for Automatic Medical Consultation System: Frameworks, Tasks and Datasets
In recent years, interest has arisen in using machine learning to improve the efficiency of automatic medical consultation and enhance patient experience.
BBTv2: Towards a Gradient-Free Future with Large Language Models
By contrast, gradient-free methods only require the forward computation of the PTM to tune the prompt, retaining the benefits of efficient tuning and deployment.
What Dense Graph Do You Need for Self-Attention?
Transformers have made progress in miscellaneous tasks, but suffer from quadratic computational and memory complexities.
CoNT: Contrastive Neural Text Generation
We validate CoNT on five generation tasks with ten benchmarks, including machine translation, summarization, code comment generation, data-to-text generation and commonsense generation.
A Unified Continuous Learning Framework for Multi-modal Knowledge Discovery and Pre-training
These two steps are iteratively performed in our framework for continuous learning.
Causal Intervention Improves Implicit Sentiment Analysis
In this work, we propose a causal intervention model for Implicit Sentiment Analysis using Instrumental Variable (ISAIV).
Locate Then Ask: Interpretable Stepwise Reasoning for Multi-hop Question Answering
In this paper, we propose an interpretable stepwise reasoning framework to incorporate both single-hop supporting sentence identification and single-hop question generation at each intermediate step, and utilize the inference of the current hop for the next until reasoning out the final result.
A Multi-Format Transfer Learning Model for Event Argument Extraction via Variational Information Bottleneck
Event argument extraction (EAE) aims to extract arguments with given roles from texts, which have been widely studied in natural language processing.
COLO: A Contrastive Learning based Re-ranking Framework for One-Stage Summarization
Traditional training paradigms for extractive and abstractive summarization systems always only use token-level or sentence-level training objectives.
BERTScore is Unfair: On Social Bias in Language Model-Based Metrics for Text Generation
Automatic evaluation metrics are crucial to the development of generative systems.
Multitask Pre-training of Modular Prompt for Chinese Few-Shot Learning
MP2 is a set of combinable prompts pre-trained on 38 Chinese tasks.
Kernel-Whitening: Overcome Dataset Bias with Isotropic Sentence Embedding
Dataset bias has attracted increasing attention recently for its detrimental effect on the generalization ability of fine-tuned models.
Late Prompt Tuning: A Late Prompt Could Be Better Than Many Prompts
Through extensive experimental results across various tasks and PTMs, we show that LPT can achieve competitive performance to full model tuning and other PETuning methods under both full-data and few-shot scenarios while possessing faster training speed and lower memory cost.
Robust Lottery Tickets for Pre-trained Language Models
Recent works on Lottery Ticket Hypothesis have shown that pre-trained language models (PLMs) contain smaller matching subnetworks(winning tickets) which are capable of reaching accuracy comparable to the original models.
Efficient Adversarial Training with Robust Early-Bird Tickets
Adversarial training is one of the most powerful methods to improve the robustness of pre-trained language models (PLMs).
DiffusionBERT: Improving Generative Masked Language Models with Diffusion Models
We present DiffusionBERT, a new generative masked language model based on discrete diffusion models.
Rethinking Label Smoothing on Multi-hop Question Answering
Multi-Hop Question Answering (MHQA) is a significant area in question answering, requiring multiple reasoning components, including document retrieval, supporting sentence prediction, and answer span extraction.
Cross-Linguistic Syntactic Difference in Multilingual BERT: How Good is It and How Does It Affect Transfer?
We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.
How Robust is GPT-3.5 to Predecessors? A Comprehensive Study on Language Understanding Tasks
The GPT-3. 5 models have demonstrated impressive performance in various Natural Language Processing (NLP) tasks, showcasing their strong understanding and reasoning capabilities.
Natural Language Inference
Natural Language Understanding
+1
A Comprehensive Capability Analysis of GPT-3 and GPT-3.5 Series Models
GPT series models, such as GPT-3, CodeX, InstructGPT, ChatGPT, and so on, have gained considerable attention due to their exceptional natural language processing capabilities.
CausalAPM: Generalizable Literal Disentanglement for NLU Debiasing
Dataset bias, i. e., the over-reliance on dataset-specific literal heuristics, is getting increasing attention for its detrimental effect on the generalization ability of NLU models.
CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
A common practice is to recast the task into a text-to-text format such that generative LLMs of natural language (NL-LLMs) like GPT-3 can be prompted to solve it.
Enhancing Contrastive Learning with Noise-Guided Attack: Towards Continual Relation Extraction in the Wild
The principle of continual relation extraction~(CRE) involves adapting to emerging novel relations while preserving od knowledge.
Modeling the Q-Diversity in a Min-max Play Game for Robust Optimization
Models trained with empirical risk minimization (ERM) are revealed to easily rely on spurious correlations, resulting in poor generalization.
A Confidence-based Partial Label Learning Model for Crowd-Annotated Named Entity Recognition
Particularly, we propose a Confidence-based Partial Label Learning (CPLL) method to integrate the prior confidence (given by annotators) and posterior confidences (learned by models) for crowd-annotated NER.
Self-Polish: Enhance Reasoning in Large Language Models via Problem Refinement
To enhance the multi-step reasoning capabilities of large language models, researchers have extensively explored prompting methods, notably the Chain-of-Thought (CoT) method which explicitly elicits human-like rationales.
Query Structure Modeling for Inductive Logical Reasoning Over Knowledge Graphs
The results demonstrate the effectiveness of our method on logical reasoning over KGs in both inductive and transductive settings.
KNSE: A Knowledge-aware Natural Language Inference Framework for Dialogue Symptom Status Recognition
Symptom diagnosis in medical conversations aims to correctly extract both symptom entities and their status from the doctor-patient dialogue.
Do Large Language Models Know What They Don't Know?
Large language models (LLMs) have a wealth of knowledge that allows them to excel in various Natural Language Processing (NLP) tasks.
Open Set Relation Extraction via Unknown-Aware Training
Inspired by text adversarial attacks, we adaptively apply small but critical perturbations to original training instances and thus synthesizing negative instances that are more likely to be mistaken by the model as known relations.
From Hypergraph Energy Functions to Hypergraph Neural Networks
Hypergraphs are a powerful abstraction for representing higher-order interactions between entities of interest.
On the Universal Adversarial Perturbations for Efficient Data-free Adversarial Detection
Detecting adversarial samples that are carefully crafted to fool the model is a critical step to socially-secure applications.
Secrets of RLHF in Large Language Models Part I: PPO
Therefore, we explore the PPO-max, an advanced version of PPO algorithm, to efficiently improve the training stability of the policy model.
DISC-MedLLM: Bridging General Large Language Models and Real-World Medical Consultation
We propose DISC-MedLLM, a comprehensive solution that leverages Large Language Models (LLMs) to provide accurate and truthful medical response in end-to-end conversational healthcare services.
SpikeBERT: A Language Spikformer Learned from BERT with Knowledge Distillation
Spiking neural networks (SNNs) offer a promising avenue to implement deep neural networks in a more energy-efficient way.
The Rise and Potential of Large Language Model Based Agents: A Survey
Many efforts have been made to develop intelligent agents, but they mainly focus on advancement in algorithms or training strategies to enhance specific capabilities or performance on particular tasks.
DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services
We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services.
ReForm-Eval: Evaluating Large Vision Language Models via Unified Re-Formulation of Task-Oriented Benchmarks
Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs).
Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning from Human Feedback
Reinforcement learning from human feedback serves as a crucial bridge, aligning large language models with human and societal values.
SpikeCLIP: A Contrastive Language-Image Pretrained Spiking Neural Network
Spiking neural networks (SNNs) have demonstrated the capability to achieve comparable performance to deep neural networks (DNNs) in both visual and linguistic domains while offering the advantages of improved energy efficiency and adherence to biological plausibility.
TRACE: A Comprehensive Benchmark for Continual Learning in Large Language Models
In this paper, we introduce TRACE, a novel benchmark designed to evaluate continual learning in LLMs.
RethinkingTMSC: An Empirical Study for Target-Oriented Multimodal Sentiment Classification
Recently, Target-oriented Multimodal Sentiment Classification (TMSC) has gained significant attention among scholars.
Efficient Link Prediction via GNN Layers Induced by Negative Sampling
Graph neural networks (GNNs) for link prediction can loosely be divided into two broad categories.
RealBehavior: A Framework for Faithfully Characterizing Foundation Models' Human-like Behavior Mechanisms
Reports of human-like behaviors in foundation models are growing, with psychological theories providing enduring tools to investigate these behaviors.
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
In this work, we propose a novel approach that can learn a consistent policy via RL across various data groups or domains.
Are Structural Concepts Universal in Transformer Language Models? Towards Interpretable Cross-Lingual Generalization
We then propose a meta-learning-based method to learn to align conceptual spaces of different languages, which facilitates zero-shot and few-shot generalization in concept classification and also offers insights into the cross-lingual in-context learning phenomenon.
Orthogonal Subspace Learning for Language Model Continual Learning
In this paper, we propose orthogonal low-rank adaptation (O-LoRA), a simple and efficient approach for continual learning in language models, effectively mitigating catastrophic forgetting while learning new tasks.
