Search Results for author:
Found 45 papers, 22 papers with code
Data Interpreter: An LLM Agent For Data Science
Large Language Model (LLM)-based agents have demonstrated remarkable effectiveness.
$S^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy efficient compared to conventional neural networks.
DenseShift: Towards Accurate and Efficient Low-Bit Power-of-Two Quantization
We further propose a sign-scale decomposition design to enhance training efficiency and a low-variance random initialization strategy to improve the model's transfer learning performance.
Matching Article Pairs with Graphical Decomposition and Convolutions
Identifying the relationship between two articles, e. g., whether two articles published from different sources describe the same breaking news, is critical to many document understanding tasks.
MuKEA: Multimodal Knowledge Extraction and Accumulation for Knowledge-based Visual Question Answering
Knowledge-based visual question answering requires the ability of associating external knowledge for open-ended cross-modal scene understanding.
Asking Questions the Human Way: Scalable Question-Answer Generation from Text Corpus
In this paper, we propose Answer-Clue-Style-aware Question Generation (ACS-QG), which aims at automatically generating high-quality and diverse question-answer pairs from unlabeled text corpus at scale by imitating the way a human asks questions.
Growing Story Forest Online from Massive Breaking News
We describe our experience of implementing a news content organization system at Tencent that discovers events from vast streams of breaking news and evolves news story structures in an online fashion.
Ranked #3 on
Information Threading
on NewSHead
GIANT: Scalable Creation of a Web-scale Ontology
These services will benefit from a highly structured and web-scale ontology of entities, concepts, events, topics and categories.
Improving Multi-turn Emotional Support Dialogue Generation with Lookahead Strategy Planning
Providing Emotional Support (ES) to soothe people in emotional distress is an essential capability in social interactions.
MCSCSet: A Specialist-annotated Dataset for Medical-domain Chinese Spelling Correction
In this work, we define the task of Medical-domain Chinese Spelling Correction and propose MCSCSet, a large scale specialist-annotated dataset that contains about 200k samples.
Optical Character Recognition
Optical Character Recognition (OCR)
+1
HoneyBee: Progressive Instruction Finetuning of Large Language Models for Materials Science
We propose an instruction-based process for trustworthy data curation in materials science (MatSci-Instruct), which we then apply to finetune a LLaMa-based language model targeted for materials science (HoneyBee).
Resonance RoPE: Improving Context Length Generalization of Large Language Models
This paper addresses the challenge of train-short-test-long (TSTL) scenarios in Large Language Models (LLMs) equipped with Rotary Position Embedding (RoPE), where models pre-trained on shorter sequences face difficulty with out-of-distribution (OOD) token positions in longer sequences.
Enquire One's Parent and Child Before Decision: Fully Exploit Hierarchical Structure for Self-Supervised Taxonomy Expansion
Taxonomy is a hierarchically structured knowledge graph that plays a crucial role in machine intelligence.
Attend and select: A segment selective transformer for microblog hashtag generation
These tokens or phrases may originate from primary fragmental textual pieces (e. g., segments) in the original text and are separated into different segments.
MatSci-NLP: Evaluating Scientific Language Models on Materials Science Language Tasks Using Text-to-Schema Modeling
Our experiments in this low-resource training setting show that language models pretrained on scientific text outperform BERT trained on general text.
Refining BERT Embeddings for Document Hashing via Mutual Information Maximization
As a first try, we modify existing generative hashing models to accommodate the BERT embeddings.
Learning What You Need from What You Did: Product Taxonomy Expansion with User Behaviors Supervision
Specifically, i) to fully exploit user behavioral information, we extract candidate hyponymy relations that match user interests from query-click concepts; ii) to enhance the semantic information of new concepts and better detect hyponymy relations, we model concepts and relations through both user-generated content and structural information in existing taxonomies and user click logs, by leveraging Pre-trained Language Models and Graph Neural Network combined with Contrastive Learning; iii) to reduce the cost of dataset construction and overcome data skews, we construct a high-quality and balanced training dataset from existing taxonomy with no supervision.
Tell Me How to Survey: Literature Review Made Simple with Automatic Reading Path Generation
In this paper, we introduce a new task named Reading Path Generation (RPG) which aims at automatically producing a path of papers to read for a given query.
Imperfect also Deserves Reward: Multi-Level and Sequential Reward Modeling for Better Dialog Management
For task-oriented dialog systems, training a Reinforcement Learning (RL) based Dialog Management module suffers from low sample efficiency and slow convergence speed due to the sparse rewards in RL. To solve this problem, many strategies have been proposed to give proper rewards when training RL, but their rewards lack interpretability and cannot accurately estimate the distribution of state-action pairs in real dialogs.
Integrating Semantics and Neighborhood Information with Graph-Driven Generative Models for Document Retrieval
With the need of fast retrieval speed and small memory footprint, document hashing has been playing a crucial role in large-scale information retrieval.
R5: Rule Discovery with Reinforced and Recurrent Relational Reasoning
Systematicity, i. e., the ability to recombine known parts and rules to form new sequences while reasoning over relational data, is critical to machine intelligence.
GOAt: Explaining Graph Neural Networks via Graph Output Attribution
Understanding the decision-making process of Graph Neural Networks (GNNs) is crucial to their interpretability.
Matching Natural Language Sentences with Hierarchical Sentence Factorization
The proposed sentence factorization technique leads to the invention of: 1) a new unsupervised distance metric which calculates the semantic distance between a pair of text snippets by solving a penalized optimal transport problem while preserving the logical relationship of words in the reordered sentences, and 2) new multi-scale deep learning models for supervised semantic training, based on factorized sentence hierarchies.
Multiresolution Graph Attention Networks for Relevance Matching
In this paper, we are especially interested in relevance matching between a piece of short text and a long document, which is critical to problems like query-document matching in information retrieval and web searching.
Learning to Generate Questions by Learning What not to Generate
In CGC-QG, we design a multi-task labeling strategy to identify whether a question word should be copied from the input passage or be generated instead, guiding the model to learn the accurate boundaries between copying and generation.
A User-Centered Concept Mining System for Query and Document Understanding at Tencent
We further present our techniques to tag documents with user-centered concepts and to construct a topic-concept-instance taxonomy, which has helped to improve search as well as news feeds recommendation in Tencent QQ Browser.
QBSUM: a Large-Scale Query-Based Document Summarization Dataset from Real-world Applications
In this paper, we present QBSUM, a high-quality large-scale dataset consisting of 49, 000+ data samples for the task of Chinese query-based document summarization.
Guiding the Growth: Difficulty-Controllable Question Generation through Step-by-Step Rewriting
This paper explores the task of Difficulty-Controllable Question Generation (DCQG), which aims at generating questions with required difficulty levels.
Noised Consistency Training for Text Summarization
In this paper, we argue that this limitation can be overcome by a semi-supervised approach: consistency training which is to leverage large amounts of unlabeled data to improve the performance of supervised learning over a small corpus.
Encoder-Decoder Neural Architecture Optimization for Keyword Spotting
Keyword spotting aims to identify specific keyword audio utterances.
Semantic and Syntactic Enhanced Aspect Sentiment Triplet Extraction
Aspect Sentiment Triplet Extraction (ASTE) aims to extract triplets from sentences, where each triplet includes an entity, its associated sentiment, and the opinion span explaining the reason for the sentiment.
TAG: Toward Accurate Social Media Content Tagging with a Concept Graph
Although conceptualization has been widely studied in semantics and knowledge representation, it is still challenging to find the most accurate concept phrases to characterize the main idea of a text snippet on the fast-growing social media.
S$^3$: Sign-Sparse-Shift Reparametrization for Effective Training of Low-bit Shift Networks
Shift neural networks reduce computation complexity by removing expensive multiplication operations and quantizing continuous weights into low-bit discrete values, which are fast and energy-efficient compared to conventional neural networks.
Better Modeling the Programming World with Code Concept Graphs-augmented Multi-modal Learning
The progress made in code modeling has been tremendous in recent years thanks to the design of natural language processing learning approaches based on state-of-the-art model architectures.
Grow-and-Clip: Informative-yet-Concise Evidence Distillation for Answer Explanation
In this research, we argue that the evidences of an answer is critical to enhancing the interpretability of QA models.
Deep learning enhanced Rydberg multifrequency microwave recognition
Recognition of multifrequency microwave (MW) electric fields is challenging because of the complex interference of multifrequency fields in practical applications.
Feeding What You Need by Understanding What You Learned
In this paper, we argue that a deep understanding of model capabilities and data properties can help us feed a model with appropriate training data based on its learning status.
QRelScore: Better Evaluating Generated Questions with Deeper Understanding of Context-aware Relevance
Existing metrics for assessing question generation not only require costly human reference but also fail to take into account the input context of generation, rendering the lack of deep understanding of the relevance between the generated questions and input contexts.
Tackling Math Word Problems with Fine-to-Coarse Abstracting and Reasoning
Math Word Problems (MWP) is an important task that requires the ability of understanding and reasoning over mathematical text.
SkillQG: Learning to Generate Question for Reading Comprehension Assessment
We present $\textbf{$\texttt{SkillQG}$}$: a question generation framework with controllable comprehension types for assessing and improving machine reading comprehension models.
Fine-tuning Happens in Tiny Subspaces: Exploring Intrinsic Task-specific Subspaces of Pre-trained Language Models
Pre-trained language models (PLMs) are known to be overly parameterized and have significant redundancy, indicating a small degree of freedom of the PLMs.
Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models
We employ a tool-interacting divide-and-conquer strategy enabling large language models (LLMs) to answer complex multimodal multi-hop questions.
Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games
In this study, we explore the application of Large Language Models (LLMs) in \textit{Jubensha}, a Chinese detective role-playing game and a novel area in Artificial Intelligence (AI) driven gaming.
FAC$^2$E: Better Understanding Large Language Model Capabilities by Dissociating Language and Cognition
In this paper, we present FAC$^2$E, a framework for Fine-grAined and Cognition-grounded LLMs' Capability Evaluation.
OPEx: A Component-Wise Analysis of LLM-Centric Agents in Embodied Instruction Following
Embodied Instruction Following (EIF) is a crucial task in embodied learning, requiring agents to interact with their environment through egocentric observations to fulfill natural language instructions.
