Search Results for author:
Found 56 papers, 25 papers with code
Enlivening Redundant Heads in Multi-head Self-attention for Machine Translation
Multi-head self-attention recently attracts enormous interest owing to its specialized functions, significant parallelizable computation, and flexible extensibility.
Mix-Initiative Response Generation with Dynamic Prefix Tuning
Specifically, IDPT decouples initiative factors into different prefix parameters and uses the attention mechanism to adjust the selection of initiatives in guiding generation dynamically.
ProtLLM: An Interleaved Protein-Language LLM with Protein-as-Word Pre-Training
We propose ProtLLM, a versatile cross-modal large language model (LLM) for both protein-centric and protein-language tasks.
CriticBench: Evaluating Large Language Models as Critic
Critique ability are crucial in the scalable oversight and self-improvement of Large Language Models (LLMs).
Online Sequential Decision-Making with Unknown Delays
Specifically, we introduce a family of Follow the Delayed Regularized Leader algorithms for feedback with full information on the loss function, a family of Delayed Mirror Descent algorithms for feedback with gradient information on the loss function and a family of Simplified Delayed Mirror Descent algorithms for feedback with the value information of the loss function's gradients at corresponding decision points.
CoFiNet: Unveiling Camouflaged Objects with Multi-Scale Finesse
Camouflaged Object Detection (COD) is a critical aspect of computer vision aimed at identifying concealed objects, with applications spanning military, industrial, medical and monitoring domains.
Identifying and Analyzing Task-Encoding Tokens in Large Language Models
In-context learning (ICL) has become an effective solution for few-shot learning in natural language processing.
Helping Language Models Learn More: Multi-dimensional Task Prompt for Few-shot Tuning
In interaction with large language models, embedding more task-related information into prompts will make it easier to stimulate knowledge embedded in large language models.
Graph vs. Sequence: An Empirical Study on Knowledge Forms for Knowledge-Grounded Dialogue
Knowledge-grounded dialogue is a task of generating an informative response based on both the dialogue history and external knowledge source.
Boosting legal case retrieval by query content selection with large language models
Legal case retrieval, which aims to retrieve relevant cases to a given query case, benefits judgment justice and attracts increasing attention.
S2F-NER: Exploring Sequence-to-Forest Generation for Complex Entity Recognition
Named Entity Recognition (NER) remains challenging due to the complex entities, like nested, overlapping, and discontinuous entities.
MindLLM: Pre-training Lightweight Large Language Model from Scratch, Evaluations and Domain Applications
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language tasks, marking significant strides towards general artificial intelligence.
Copy Is All You Need
The dominant text generation models compose the output by sequentially selecting words from a fixed vocabulary.
SciMRC: Multi-perspective Scientific Machine Reading Comprehension
However, the dataset has ignored the fact that different readers may have different levels of understanding of the text, and only includes single-perspective question-answer pairs, leading to a lack of consideration of different perspectives.
Boosting Event Extraction with Denoised Structure-to-Text Augmentation
Event extraction aims to recognize pre-defined event triggers and arguments from texts, which suffer from the lack of high-quality annotations.
Measuring Cross-Lingual Transferability of Multilingual Transformers on Sentence Classification
Recent studies have exhibited remarkable capabilities of pre-trained multilingual Transformers, especially cross-lingual transferability.
AttenWalker: Unsupervised Long-Document Question Answering via Attention-based Graph Walking
To alleviate the problem, it might be possible to generate long-document QA pairs via unsupervised question answering (UQA) methods.
Bridging The Gap: Entailment Fused-T5 for Open-retrieval Conversational Machine Reading Comprehension
Open-retrieval conversational machine reading comprehension (OCMRC) simulates real-life conversational interaction scenes.
Momentum Decoding: Open-ended Text Generation As Graph Exploration
In this study, we formulate open-ended text generation from a new perspective, i. e., we view it as an exploration process within a directed graph.
ConsPrompt: Exploiting Contrastive Samples for Fewshot Prompt Learning
The prompt has become an effective linguistic tool for utilizing pre-trained language models.
Revisiting Grammatical Error Correction Evaluation and Beyond
Pretraining-based (PT-based) automatic evaluation metrics (e. g., BERTScore and BARTScore) have been widely used in several sentence generation tasks (e. g., machine translation and text summarization) due to their better correlation with human judgments over traditional overlap-based methods.
Capturing Global Structural Information in Long Document Question Answering with Compressive Graph Selector Network
The proposed model mainly focuses on the evidence selection phase of long document question answering.
ET5: A Novel End-to-end Framework for Conversational Machine Reading Comprehension
Conversational machine reading comprehension (CMRC) aims to assist computers to understand an natural language text and thereafter engage in a multi-turn conversation to answer questions related to the text.
Unsupervised Hashing with Semantic Concept Mining
Recently, to improve the unsupervised image retrieval performance, plenty of unsupervised hashing methods have been proposed by designing a semantic similarity matrix, which is based on the similarities between image features extracted by a pre-trained CNN model.
Unsupervised Question Answering via Answer Diversifying
Previous works usually make use of heuristic rules as well as pre-trained models to construct data and train QA models.
Location-based Twitter Filtering for the Creation of Low-Resource Language Datasets in Indonesian Local Languages
Twitter contains an abundance of linguistic data from the real world.
Dynamic Prefix-Tuning for Generative Template-based Event Extraction
We consider event extraction in a generative manner with template-based conditional generation.
Relational Triple Extraction: One Step is Enough
Extracting relational triples from unstructured text is an essential task in natural language processing and knowledge graph construction.
$G^2$: Enhance Knowledge Grounded Dialogue via Ground Graph
Besides, a Ground Graph Aware Transformer ($G^2AT$) is proposed to enhance knowledge grounded response generation.
On the Representation Collapse of Sparse Mixture of Experts
We also present a comprehensive analysis on the representation and routing behaviors of our models.
Cross-Lingual Phrase Retrieval
In this paper, we propose XPR, a cross-lingual phrase retriever that extracts phrase representations from unlabeled example sentences.
PSP: Pre-trained Soft Prompts for Few-Shot Abstractive Summarization
Few-shot abstractive summarization has become a challenging task in natural language generation.
Hammer PDF: An Intelligent PDF Reader for Scientific Papers
Specifically, taking a paper as a basic and separate unit, existing PDF Readers cannot access extended information about the paper, such as corresponding videos, blogs and codes.
Efficient Non-Autoregressive GAN Voice Conversion using VQWav2vec Features and Dynamic Convolution
It was shown recently that a combination of ASR and TTS models yield highly competitive performance on standard voice conversion tasks such as the Voice Conversion Challenge 2020 (VCC2020).
TCM-SD: A Benchmark for Probing Syndrome Differentiation via Natural Language Processing
Therefore, in this paper, we focus on the core task of the TCM diagnosis and treatment system -- syndrome differentiation (SD) -- and we introduce the first public large-scale dataset for SD, called TCM-SD.
OneRel:Joint Entity and Relation Extraction with One Module in One Step
Joint entity and relation extraction is an essential task in natural language processing and knowledge graph construction.
Unifying Cross-lingual Summarization and Machine Translation with Compression Rate
Through introducing compression rate, the information ratio between the source and the target text, we regard the MT task as a special CLS task with a compression rate of 100%.
Exploring Dense Retrieval for Dialogue Response Selection
In this study, we present a solution to directly select proper responses from a large corpus or even a nonparallel corpus that only consists of unpaired sentences, using a dense retrieval model.
Cross-Lingual Language Model Meta-Pretraining
The success of pretrained cross-lingual language models relies on two essential abilities, i. e., generalization ability for learning downstream tasks in a source language, and cross-lingual transferability for transferring the task knowledge to other languages.
XLM-E: Cross-lingual Language Model Pre-training via ELECTRA
In this paper, we introduce ELECTRA-style tasks to cross-lingual language model pre-training.
Ranked #1 on
Zero-Shot Cross-Lingual Transfer
on XTREME
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
The cross-lingual language models are typically pretrained with masked language modeling on multilingual text or parallel sentences.
Prediction or Comparison: Toward Interpretable Qualitative Reasoning
Qualitative relationships illustrate how changing one property (e. g., moving velocity) affects another (e. g., kinetic energy) and constitutes a considerable portion of textual knowledge.
Cross-Lingual Abstractive Summarization with Limited Parallel Resources
Employing one unified decoder to generate the sequential concatenation of monolingual and cross-lingual summaries, MCLAS makes the monolingual summarization task a prerequisite of the cross-lingual summarization (CLS) task.
Abstractive Text Summarization
Cross-Lingual Abstractive Summarization
+1
Read, Listen, and See: Leveraging Multimodal Information Helps Chinese Spell Checking
Chinese Spell Checking (CSC) aims to detect and correct erroneous characters for user-generated text in the Chinese language.
Ranked #2 on
Chinese Spell Checking
on SIGHAN 2015
Comprehensive Study: How the Context Information of Different Granularity Affects Dialogue State Tracking?
Thus, in this paper, we will study and discuss how the context information of different granularity affects dialogue state tracking.
MT6: Multilingual Pretrained Text-to-Text Transformer with Translation Pairs
Multilingual T5 (mT5) pretrains a sequence-to-sequence model on massive monolingual texts, which has shown promising results on many cross-lingual tasks.
A Robust and Domain-Adaptive Approach for Low-Resource Named Entity Recognition
Recently, it has attracted much attention to build reliable named entity recognition (NER) systems using limited annotated data.
Ranked #3 on
Named Entity Recognition (NER)
on SciERC
(using extra training data)
Low Resource Named Entity Recognition
named-entity-recognition
+2
News-Driven Stock Prediction Using Noisy Equity State Representation
News-driven stock prediction investigates the correlation between news events and stock price movements.
Self-attention Comparison Module for Boosting Performance on Retrieval-based Open-Domain Dialog Systems
Since the pre-trained language models are widely used, retrieval-based open-domain dialog systems, have attracted considerable attention from researchers recently.
Ultra-Fast, Low-Storage, Highly Effective Coarse-grained Selection in Retrieval-based Chatbot by Using Deep Semantic Hashing
Specifically, in our proposed DSHC model, a hashing optimizing module that consists of two autoencoder models is stacked on a trained dense representation model, and three loss functions are designed to optimize it.
Deep Cross-modal Hashing via Margin-dynamic-softmax Loss
Finally, by minimizing the novel \textit{margin-dynamic-softmax loss}, the modality-specific hashing networks can be trained to generate hash codes which can simultaneously preserve the cross-modal similarity and abundant semantic information well.
Deep Kernel Supervised Hashing for Node Classification in Structural Networks
However, nearly all the existing network embedding based methods are hard to capture the actual category features of a node because of the linearly inseparable problem in low-dimensional space; meanwhile they cannot incorporate simultaneously network structure information and node label information into network embedding.
STN4DST: A Scalable Dialogue State Tracking based on Slot Tagging Navigation
Scalability for handling unknown slot values is a important problem in dialogue state tracking (DST).
Towards Interpretable Reasoning over Paragraph Effects in Situation
We focus on the task of reasoning over paragraph effects in situation, which requires a model to understand the cause and effect described in a background paragraph, and apply the knowledge to a novel situation.
Learning Relation Ties with a Force-Directed Graph in Distant Supervised Relation Extraction
Then, we borrow the idea of Coulomb's Law from physics and introduce the concept of attractive force and repulsive force to this graph to learn correlation and mutual exclusion between relations.
