Search Results for author:
Found 31 papers, 2 papers with code
PINGAN Omini-Sinitic at SemEval-2022 Task 4: Multi-prompt Training for Patronizing and Condescending Language Detection
This paper describes the second-placed system for subtask 2 and the ninth-placed system for subtask 1 in SemEval 2022 Task 4: Patronizing and Condescending Language Detection.
Sentinel: Attention Probing of Proxy Models for LLM Context Compression with an Understanding Perspective
Retrieval-augmented generation (RAG) enhances large language models (LLMs) with external context, but retrieved passages are often lengthy, noisy, or exceed input limits.
CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts
We introduce CHOrD, a novel framework for scalable synthesis of 3D indoor scenes, designed to create house-scale, collision-free, and hierarchically structured indoor digital twins.
Dynamic Attention-Guided Context Decoding for Mitigating Context Faithfulness Hallucinations in Large Language Models
Large language models (LLMs) often suffer from context faithfulness hallucinations, where outputs deviate from retrieved information due to insufficient context utilization and high output uncertainty.
Rethinking Layer Removal: Preserving Critical Components with Task-Aware Singular Value Decomposition
Layer removal has emerged as a promising approach for compressing large language models (LLMs) by leveraging redundancy within layers to reduce model size and accelerate inference.
Learning to Adapt to Low-Resource Paraphrase Generation
LAPA has three-stage training on three types of related resources to solve this problem: 1. pre-training PLMs on unsupervised corpora, 2. inserting an adapter layer and meta-training on source domain labeled data, and 3. fine-tuning adapters on a small amount of target domain labeled data.
Controllable Conversations: Planning-Based Dialogue Agent with Large Language Models
Conversational agents powered by Large Language Models (LLMs) show superior performance in various tasks.
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval
To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage.
A Study of Different Ways to Use The Conformer Model For Spoken Language Understanding
In this paper, we compare different ways to combine ASR and NLU, in particular using a single Conformer model with different ways to use its components, to better understand the strengths and weaknesses of each approach.
Adding Connectionist Temporal Summarization into Conformer to Improve Its Decoder Efficiency For Speech Recognition
The Conformer model is an excellent architecture for speech recognition modeling that effectively utilizes the hybrid losses of connectionist temporal classification (CTC) and attention to train model parameters.
PINGAN Omini-Sinitic at SemEval-2021 Task 4:Reading Comprehension of Abstract Meaning
This paper describes the winning system for subtask 2 and the second-placed system for subtask 1 in SemEval 2021 Task 4: ReadingComprehension of Abstract Meaning.
PHMOSpell: Phonological and Morphological Knowledge Guided Chinese Spelling Check
Chinese Spelling Check (CSC) is a challenging task due to the complex characteristics of Chinese characters.
Ranked #1 on
Chinese Spell Checking
on SIGHAN 2015
Structure Controllable Text Generation
Controlling the presented forms (or structures) of generated text are as important as controlling the generated contents during neural text generation.
KETG: A Knowledge Enhanced Text Generation Framework
Embedding logical knowledge information into text generation is a challenging NLP task.
Contextualized Emotion Recognition in Conversation as Sequence Tagging
Emotion recognition in conversation (ERC) is an important topic for developing empathetic machines in a variety of areas including social opinion mining, health-care and so on.
Ranked #2 on
Emotion Recognition in Conversation
on DailyDialog
Emotion Classification
Emotion Recognition in Conversation
+1
BS-NAS: Broadening-and-Shrinking One-Shot NAS with Searchable Numbers of Channels
One-Shot methods have evolved into one of the most popular methods in Neural Architecture Search (NAS) due to weight sharing and single training of a supernet.
An Iterative Polishing Framework based on Quality Aware Masked Language Model for Chinese Poetry Generation
In this paper, we propose a novel iterative polishing framework for highly qualified Chinese poetry generation.
A Quality-Diversity Controllable GAN for Text Generation
Text generation is a critical and difficult natural language processing task.
A simple discriminative training method for machine translation with large-scale features
Margin infused relaxed algorithms (MIRAs) dominate model tuning in statistical machine translation in the case of large scale features, but also they are famous for the complexity in implementation.
Plackett-Luce model for learning-to-rank task
List-wise based learning to rank methods are generally supposed to have better performance than point- and pair-wise based.
Analysis of Regression Tree Fitting Algorithms in Learning to Rank
In learning to rank area, industry-level applications have been dominated by gradient boosting framework, which fits a tree using least square error principle.
Automatic Acrostic Couplet Generation with Three-Stage Neural Network Pipelines
In this paper, we comprehensively study on automatic generation of acrostic couplet with the first characters defined by users.
A Syllable-Structured, Contextually-Based Conditionally Generation of Chinese Lyrics
This paper presents a novel, syllable-structured Chinese lyrics generation model given a piece of original melody.
A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
In this paper, we comprehensively study on context-aware generation of Chinese song lyrics.
Slim Embedding Layers for Recurrent Neural Language Models
When the vocabulary size is large, the space taken to store the model parameters becomes the bottleneck for the use of recurrent neural language models.
Une m\'ethode discriminant formation simple pour la traduction automatique avec Grands Caract\'eristiques
Marge infus{\'e} algorithmes d{\'e}tendus (MIRAS) dominent mod{\`e}le de tuning dans la traduction automatique statistique dans le cas des grandes caract{\'e}ristiques de l{'}{\'e}chelle, mais ils sont {\'e}galement c{\'e}l{\`e}bres pour la complexit{\'e} de mise en {\oe}uvre.
Direct 0-1 Loss Minimization and Margin Maximization with Boosting
We propose a boosting method, DirectBoost, a greedy coordinate descent algorithm that builds an ensemble classifier of weak classifiers through directly minimizing empirical classification error over labeled training examples; once the training classification error is reduced to a local coordinatewise minimum, DirectBoost runs a greedy coordinate ascent algorithm that continuously adds weak classifiers to maximize any targeted arbitrarily defined margins until reaching a local coordinatewise maximum of the margins in a certain sense.
A Rate Distortion Approach for Semi-Supervised Conditional Random Fields
We propose a novel information theoretic approach for semi-supervised learning of conditional random fields.
