Search Results for author:
Found 54 papers, 23 papers with code
Pre-training and Fine-tuning Neural Topic Model: A Simple yet Effective Approach to Incorporating External Knowledge
Recent years have witnessed growing interests in incorporating external knowledge such as pre-trained word embeddings (PWEs) or pre-trained language models (PLMs) into neural topic modeling.
Diversity and Consistency: Exploring Visual Question-Answer Pair Generation
Moreover, this task can be used to improve visual question generation and visual question answering.
Entity Relative Position Representation based Multi-head Selection for Joint Entity and Relation Extraction
Joint entity and relation extraction has received increasing interests recently, due to the capability of utilizing the interactions between both steps.
G4: Grounding-guided Goal-oriented Dialogues Generation with Multiple Documents
Goal-oriented dialogues generation grounded in multiple documents(MultiDoc2Dial) is a challenging and realistic task.
A Divide-And-Conquer Approach for Multi-label Multi-hop Relation Detection in Knowledge Base Question Answering
However, most of existing approaches only detect one single path to obtain the answer without considering other correct paths, which might affect the final performance.
IEKM: A Model Incorporating External Keyword Matrices
In this paper, we propose an incorporation external keywords matrices model (IEKM) to address these challenges.
Making Large Language Models Better Reasoners with Alignment
To address this problem, we introduce an \textit{Alignment Fine-Tuning (AFT)} paradigm, which involves three steps: 1) fine-tuning LLMs with COT training data; 2) generating multiple COT responses for each question, and categorizing them into positive and negative ones based on whether they achieve the correct answer; 3) calibrating the scores of positive and negative responses given by LLMs with a novel constraint alignment loss.
Unifying Token and Span Level Supervisions for Few-Shot Sequence Labeling
However, these methods are only trained at a single granularity (i. e., either token level or span level) and have some weaknesses of the corresponding granularity.
SkillNet-X: A Multilingual Multitask Model with Sparsely Activated Skills
Traditional multitask learning methods basically can only exploit common knowledge in task- or language-wise, which lose either cross-language or cross-task knowledge.
Soft Language Clustering for Multilingual Model Pre-training
Multilingual pre-trained language models have demonstrated impressive (zero-shot) cross-lingual transfer abilities, however, their performance is hindered when the target language has distant typology from source languages or when pre-training data is limited in size.
Large Language Models are not Fair Evaluators
In this paper, we uncover a systematic bias in the evaluation paradigm of adopting large language models~(LLMs), e. g., GPT-4, as a referee to score and compare the quality of responses generated by candidate models.
Bi-Drop: Enhancing Fine-tuning Generalization via Synchronous sub-net Estimation and Optimization
Also, Bi-Drop needs only one mini-batch to estimate the sub-net so it achieves higher utility of training data.
DialogVCS: Robust Natural Language Understanding in Dialogue System Upgrade
In the constant updates of the product dialogue systems, we need to retrain the natural language understanding (NLU) model as new data from the real users would be merged into the existent data accumulated in the last updates.
Denoising Bottleneck with Mutual Information Maximization for Video Multimodal Fusion
However, unlike other image-text multimodal tasks, video has longer multimodal sequences with more redundancy and noise in both visual and audio modalities.
QURG: Question Rewriting Guided Context-Dependent Text-to-SQL Semantic Parsing
Context-dependent Text-to-SQL aims to translate multi-turn natural language questions into SQL queries.
Enhancing Continual Relation Extraction via Classifier Decomposition
In this work, we point out that there exist two typical biases after training of this vanilla strategy: classifier bias and representation bias, which causes the previous knowledge that the model learned to be shaded.
Finding Similar Exercises in Retrieval Manner
When students make a mistake in an exercise, they can consolidate it by ``similar exercises'' which have the same concepts, purposes and methods.
TQ-Net: Mixed Contrastive Representation Learning For Heterogeneous Test Questions
Finally, supervised contrastive learning was conducted on relevance prediction-related downstream tasks, which helped the model to learn the representation of questions effectively.
DialogQAE: N-to-N Question Answer Pair Extraction from Customer Service Chatlog
Harvesting question-answer (QA) pairs from customer service chatlog in the wild is an efficient way to enrich the knowledge base for customer service chatbots in the cold start or continuous integration scenarios.
DualNER: A Dual-Teaching framework for Zero-shot Cross-lingual Named Entity Recognition
We present DualNER, a simple and effective framework to make full use of both annotated source language corpus and unlabeled target language text for zero-shot cross-lingual named entity recognition (NER).
Contrastive Learning with Prompt-derived Virtual Semantic Prototypes for Unsupervised Sentence Embedding
Specifically, with the help of prompts, we construct virtual semantic prototypes to each instance, and derive negative prototypes by using the negative form of the prompts.
Instance Segmentation for Chinese Character Stroke Extraction, Datasets and Benchmarks
Moreover, there are no standardized benchmarks to provide a fair comparison between different stroke extraction methods, which, we believe, is a major impediment to the development of Chinese character stroke understanding and related tasks.
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection
While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance.
Linguistic Rules-Based Corpus Generation for Native Chinese Grammatical Error Correction
Extensive experiments and detailed analyses not only demonstrate that the training data constructed by our method effectively improves the performance of CGEC models, but also reflect that our benchmark is an excellent resource for further development of the CGEC field.
Learning from the Dictionary: Heterogeneous Knowledge Guided Fine-tuning for Chinese Spell Checking
Chinese Spell Checking (CSC) aims to detect and correct Chinese spelling errors.
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
In this paper, through empirical studies we argue that this assumption may not hold, and an important reason for catastrophic forgetting is that the learned representations do not have good robustness against the appearance of analogous relations in the subsequent learning process.
Less is More: Rethinking State-of-the-art Continual Relation Extraction Models with a Frustratingly Easy but Effective Approach
2) Balanced Tuning (BT) finetunes the model on the balanced memory data.
AiM: Taking Answers in Mind to Correct Chinese Cloze Tests in Educational Applications
To automatically correct handwritten assignments, the traditional approach is to use an OCR model to recognize characters and compare them to answers.
Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for Chinese Spell Checking
Chinese Spell Checking (CSC) task aims to detect and correct Chinese spelling errors.
Automatic Context Pattern Generation for Entity Set Expansion
In addition, we propose the GAPA, a novel ESE framework that leverages the aforementioned GenerAted PAtterns to expand target entities.
CQR-SQL: Conversational Question Reformulation Enhanced Context-Dependent Text-to-SQL Parsers
Context-dependent text-to-SQL is the task of translating multi-turn questions into database-related SQL queries.
HPT: Hierarchy-aware Prompt Tuning for Hierarchical Text Classification
However, in this paradigm, there exists a huge gap between the classification tasks with sophisticated label hierarchy and the masked language model (MLM) pretraining tasks of PLMs and thus the potentials of PLMs can not be fully tapped.
SmartSales: Sales Script Extraction and Analysis from Sales Chatlog
2) Customer objection response assists the salespeople to figure out the typical customer objections and corresponding winning sales scripts, as well as search for proper sales responses for a certain customer objection.
Type-Driven Multi-Turn Corrections for Grammatical Error Correction
First, they simply mix additionally-constructed training instances and original ones to train models, which fails to help models be explicitly aware of the procedure of gradual corrections.
The Past Mistake is the Future Wisdom: Error-driven Contrastive Probability Optimization for Chinese Spell Checking
However, there exists a gap between the learned knowledge of PLMs and the goal of CSC task.
Pretraining without Wordpieces: Learning Over a Vocabulary of Millions of Words
(2) how to predict a word via cloze test without knowing the number of wordpieces in advance?
Exploring Student Representation For Neural Cognitive Diagnosis
In this paper, we propose a method of student representation with the exploration of the hierarchical relations of knowledge concepts and student embedding.
A non-hierarchical attention network with modality dropout for textual response generation in multimodal dialogue systems
Existing text- and image-based multimodal dialogue systems use the traditional Hierarchical Recurrent Encoder-Decoder (HRED) framework, which has an utterance-level encoder to model utterance representation and a context-level encoder to model context representation.
Seeking Patterns, Not just Memorizing Procedures: Contrastive Learning for Solving Math Word Problems
Math Word Problem (MWP) solving needs to discover the quantitative relationships over natural language narratives.
Hierarchical Curriculum Learning for AMR Parsing
Abstract Meaning Representation (AMR) parsing aims to translate sentences to semantic representation with a hierarchical structure, and is recently empowered by pretrained sequence-to-sequence models.
An Enhanced Span-based Decomposition Method for Few-Shot Sequence Labeling
Few-Shot Sequence Labeling (FSSL) is a canonical paradigm for the tagging models, e. g., named entity recognition and slot filling, to generalize on an emerging, resource-scarce domain.
Ranked #4 on
Few-shot NER
on Few-NERD (INTER)
Enhancing Label Correlation Feedback in Multi-Label Text Classification via Multi-Task Learning
In MLTC task, a document-label cross attention (CA) mechanism is adopted to generate a more discriminative document representation.
Multi Label Text Classification
Multi-Label Text Classification
+2
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
LANA: Towards Personalized Deep Knowledge Tracing Through Distinguishable Interactive Sequences
With pivot module reconstructed the decoder for individual students and leveled learning specialized encoders for groups, personalized DKT was achieved.
Improving BERT with Syntax-aware Local Attention
Pre-trained Transformer-based neural language models, such as BERT, have achieved remarkable results on varieties of NLP tasks.
Dialogue Response Selection with Hierarchical Curriculum Learning
As for IC, it progressively strengthens the model's ability in identifying the mismatching information between the dialogue context and a response candidate.
Ranked #3 on
Conversational Response Selection
on RRS
Difference-aware Knowledge Selection for Knowledge-grounded Conversation Generation
In a multi-turn knowledge-grounded dialog, the difference between the knowledge selected at different turns usually provides potential clues to knowledge selection, which has been largely neglected in previous research.
Asking Effective and Diverse Questions: A Machine Reading Comprehension based Framework for Joint Entity-Relation Extraction
Then, we propose to predict a subset of potential relations and filter out irrelevant ones to generate questions effectively.
Ranked #1 on
Relation Extraction
on ACE 2005
(Sentence Encoder metric)
The SPPD System for Schema Guided Dialogue State Tracking Challenge
This paper introduces one of our group's work on the Dialog System Technology Challenges 8 (DSTC8), the SPPD system for Schema Guided dialogue state tracking challenge.
Dialogue State Tracking
Multi-domain Dialogue State Tracking
A Statistical Framework for Product Description Generation
We present in this paper a statistical framework that generates accurate and fluent product description from product attributes.
