Search Results for author:
Found 99 papers, 52 papers with code
ZEN: Pre-training Chinese Text Encoder Enhanced by N-gram Representations
Moreover, it is shown that reasonable performance can be obtained when ZEN is trained on a small corpus, which is important for applying pre-training techniques to scenarios with limited data.
Ranked #1 on
Chinese Part-of-Speech Tagging
on CTB5 Dev
Chinese Named Entity Recognition
Chinese Word Segmentation
+5
A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check
Chinese spelling check (CSC) is a challenging yet meaningful task, which not only serves as a preprocessing in many natural language processing(NLP) applications, but also facilitates reading and understanding of running texts in peoples{'} daily lives.
Improving Chinese Word Segmentation with Wordhood Memory Networks
Contextual features always play an important role in Chinese word segmentation (CWS).
Ranked #1 on
Chinese Word Segmentation
on CITYU
Generating Radiology Reports via Memory-driven Transformer
Particularly, this is the first work reporting the generation results on MIMIC-CXR to the best of our knowledge.
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities that have different facts in two KGs.
An Empirical Study on Google Research Football Multi-agent Scenarios
Few multi-agent reinforcement learning (MARL) research on Google Research Football (GRF) focus on the 11v11 multi-agent full-game scenario and to the best of our knowledge, no open benchmark on this scenario has been released to the public.
Learning Semantic Relationship Among Instances for Image-Text Matching
Image-text matching, a bridge connecting image and language, is an important task, which generally learns a holistic cross-modal embedding to achieve a high-quality semantic alignment between the two modalities.
Joint Chinese Word Segmentation and Part-of-speech Tagging via Two-way Attentions of Auto-analyzed Knowledge
Chinese word segmentation (CWS) and part-of-speech (POS) tagging are important fundamental tasks for Chinese language processing, where joint learning of them is an effective one-step solution for both tasks.
Cross-modal Memory Networks for Radiology Report Generation
Medical imaging plays a significant role in clinical practice of medical diagnosis, where the text reports of the images are essential in understanding them and facilitating later treatments.
Dependency-driven Relation Extraction with Attentive Graph Convolutional Networks
Syntactic information, especially dependency trees, has been widely used by existing studies to improve relation extraction with better semantic guidance for analyzing the context information associated with the given entities.
Ranked #12 on
Relation Extraction
on SemEval-2010 Task-8
ChiMed-GPT: A Chinese Medical Large Language Model with Full Training Regime and Better Alignment to Human Preferences
Recently, the increasing demand for superior medical services has highlighted the discrepancies in the medical infrastructure.
A Systematic Review of Deep Learning-based Research on Radiology Report Generation
Specifically, we firstly cover pivotal RRG approaches based on the task-specific features of radiographs, reports, and the cross-modal relations between them, and then illustrate the benchmark datasets conventionally used for this task with evaluation metrics, subsequently analyze the performance of different approaches and finally offer our summary on the challenges and the trends in future directions.
Named Entity Recognition for Social Media Texts with Semantic Augmentation
In particular, we obtain the augmented semantic information from a large-scale corpus, and propose an attentive semantic augmentation module and a gate module to encode and aggregate such information, respectively.
Ranked #4 on
Named Entity Recognition (NER)
on WNUT 2016
Chinese Named Entity Recognition
named-entity-recognition
+3
Iterative Document Representation Learning Towards Summarization with Polishing
In this paper, we introduce Iterative Text Summarization (ITS), an iteration-based model for supervised extractive text summarization, inspired by the observation that it is often necessary for a human to read an article multiple times in order to fully understand and summarize its contents.
Ranked #14 on
Extractive Text Summarization
on CNN / Daily Mail
Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble
It is popular that neural graph-based models are applied in existing aspect-based sentiment analysis (ABSA) studies for utilizing word relations through dependency parses to facilitate the task with better semantic guidance for analyzing context and aspect words.
Ranked #2 on
Aspect-Based Sentiment Analysis (ABSA)
on MAMS
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
Improving Named Entity Recognition with Attentive Ensemble of Syntactic Information
Named entity recognition (NER) is highly sensitive to sentential syntactic and semantic properties where entities may be extracted according to how they are used and placed in the running text.
Ranked #3 on
Named Entity Recognition (NER)
on WNUT 2016
Chinese Named Entity Recognition
named-entity-recognition
+2
Summarizing Medical Conversations via Identifying Important Utterances
For the particular dataset used in this study, we show that high-quality summaries can be generated by extracting two types of utterances, namely, problem statements and treatment recommendations.
ZEN 2.0: Continue Training and Adaption for N-gram Enhanced Text Encoders
Pre-trained text encoders have drawn sustaining attention in natural language processing (NLP) and shown their capability in obtaining promising results in different tasks.
Joint Aspect Extraction and Sentiment Analysis with Directional Graph Convolutional Networks
End-to-end aspect-based sentiment analysis (EASA) consists of two sub-tasks: the first extracts the aspect terms in a sentence and the second predicts the sentiment polarities for such terms.
Reinforced Training Data Selection for Domain Adaptation
Supervised models suffer from the problem of domain shifting where distribution mismatch in the data across domains greatly affect model performance.
What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues
To tackle this challenge, in this paper, we formally define the task of visual-aware pronoun coreference resolution (PCR) and introduce VisPro, a large-scale dialogue PCR dataset, to investigate whether and how the visual information can help resolve pronouns in dialogues.
Keyphrase Generation with Cross-Document Attention
Keyphrase generation aims to produce a set of phrases summarizing the essentials of a given document.
Taming Pre-trained Language Models with N-gram Representations for Low-Resource Domain Adaptation
In this paper, we aim to adapt a generic pretrained model with a relatively small amount of domain-specific data.
ChiMed: A Chinese Medical Corpus for Question Answering
Question answering (QA) is a challenging task in natural language processing (NLP), especially when it is applied to specific domains.
Supertagging Combinatory Categorial Grammar with Attentive Graph Convolutional Networks
Specifically, we build the graph from chunks (n-grams) extracted from a lexicon and apply attention over the graph, so that different word pairs from the contexts within and across chunks are weighted in the model and facilitate the supertagging accordingly.
Ranked #2 on
CCG Supertagging
on CCGbank
Knowledge-aware Pronoun Coreference Resolution
Resolving pronoun coreference requires knowledge support, especially for particular domains (e. g., medicine).
Incorporating Context and External Knowledge for Pronoun Coreference Resolution
Linking pronominal expressions to the correct references requires, in many cases, better analysis of the contextual information and external knowledge.
Enhancing Aspect-level Sentiment Analysis with Word Dependencies
Aspect-level sentiment analysis (ASA) has received much attention in recent years.
Word Graph Guided Summarization for Radiology Findings
In this paper, we propose a novel method for automatic impression generation, where a word graph is constructed from the findings to record the critical words and their relations, then a Word Graph guided Summarization model (WGSum) is designed to generate impressions with the help of the word graph.
Improving Constituency Parsing with Span Attention
Constituency parsing is a fundamental and important task for natural language understanding, where a good representation of contextual information can help this task.
Ranked #1 on
Constituency Parsing
on ATB
RevCore: Review-augmented Conversational Recommendation
Existing conversational recommendation (CR) systems usually suffer from insufficient item information when conducted on short dialogue history and unfamiliar items.
Joint Chinese Word Segmentation and Part-of-speech Tagging via Multi-channel Attention of Character N-grams
However, their work on modeling such contextual features is limited to concatenating the features or their embeddings directly with the input embeddings without distinguishing whether the contextual features are important for the joint task in the specific context.
Improving Biomedical Named Entity Recognition with Syntactic Information
The experimental results on six English benchmark datasets demonstrate that auto-processed syntactic information can be a useful resource for BioNER and our method with KVMN can appropriately leverage such information to improve model performance.
Ranked #1 on
Named Entity Recognition (NER)
on Species-800
WTMED at MEDIQA 2019: A Hybrid Approach to Biomedical Natural Language Inference
Natural language inference (NLI) is challenging, especially when it is applied to technical domains such as biomedical settings.
ChiMST: A Chinese Medical Corpus for Word Segmentation and Medical Term Recognition
Chinese word segmentation (CWS) and named entity recognition (NER) are two important tasks in Chinese natural language processing.
Hashtag-Guided Low-Resource Tweet Classification
Social media classification tasks (e. g., tweet sentiment analysis, tweet stance detection) are challenging because social media posts are typically short, informal, and ambiguous.
Reading Like HER: Human Reading Inspired Extractive Summarization
In this work, we re-examine the problem of extractive text summarization for long documents.
Ranked #8 on
Extractive Text Summarization
on CNN / Daily Mail
Exploring Unknown States with Action Balance
In this paper, we focus on improving the effectiveness of finding unknown states and propose action balance exploration, which balances the frequency of selecting each action at a given state and can be treated as an extension of upper confidence bound (UCB) to deep reinforcement learning.
Improving Relation Extraction through Syntax-induced Pre-training with Dependency Masking
Relation extraction (RE) is an important natural language processing task that predicts the relation between two given entities, where a good understanding of the contextual information is essential to achieve an outstanding model performance.
Ranked #11 on
Relation Extraction
on SemEval-2010 Task-8
Enhancing Relation Extraction via Adversarial Multi-task Learning
Relation extraction (RE) is a sub-field of information extraction, which aims to extract the relation between two given named entities (NEs) in a sentence and thus requires a good understanding of contextual information, especially the entities and their surrounding texts.
hyperdoc2vec: Distributed Representations of Hypertext Documents
Hypertext documents, such as web pages and academic papers, are of great importance in delivering information in our daily life.
Learning Word Embeddings with Domain Awareness
Word embeddings are traditionally trained on a large corpus in an unsupervised setting, with no specific design for incorporating domain knowledge.
Multiplex Word Embeddings for Selectional Preference Acquisition
Therefore, in this paper, we propose a multiplex word embedding model, which can be easily extended according to various relations among words.
Dilation-Erosion for Single-Frame Supervised Temporal Action Localization
To balance the annotation labor and the granularity of supervision, single-frame annotation has been introduced in temporal action localization.
Complementary Learning of Aspect Terms for Aspect-based Sentiment Analysis
Aspect-based sentiment analysis (ABSA) aims to predict the sentiment polarity towards a given aspect term in a sentence on the fine-grained level, which usually requires a good understanding of contextual information, especially appropriately distinguishing of a given aspect and its contexts, to achieve good performance.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+1
Syntax-driven Approach for Semantic Role Labeling
To achieve a better performance in SRL, a model is always required to have a good understanding of the context information.
Ranked #2 on
Semantic Role Labeling
on CoNLL 2005
Enhancing Structure-aware Encoder with Extremely Limited Data for Graph-based Dependency Parsing
Dependency parsing is an important fundamental natural language processing task which analyzes the syntactic structure of an input sentence by illustrating the syntactic relations between words.
Ranked #2 on
Dependency Parsing
on Penn Treebank
A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems
This paper presents a large-scale corpus for non-task-oriented dialogue response selection, which contains over 27K distinct prompts more than 82K responses collected from social media.
Concurrence-Aware Long Short-Term Sub-Memories for Person-Person Action Recognition
To this end, we propose a novel Concurrence-Aware Long Short-Term Sub-Memories (Co-LSTSM) to model the long-term inter-related dynamics between two interacting people on the bounding boxes covering people.
Ranked #2 on
Human Interaction Recognition
on BIT
A Joint Model of Conversational Discourse and Latent Topics on Microblogs
To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: 1) different roles of conversational discourse, 2) various latent topics in reflecting content information.
Topic Memory Networks for Short Text Classification
Many classification models work poorly on short texts due to data sparsity.
Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training
It is a challenging task to automatically compose poems with not only fluent expressions but also aesthetic wording.
Learning User Embeddings from Emails
Many important email-related tasks, such as email classification or search, highly rely on building quality document representations (e. g., bag-of-words or key phrases) to assist matching and understanding.
Encoding Conversation Context for Neural Keyphrase Extraction from Microblog Posts
Existing keyphrase extraction methods suffer from data sparsity problem when they are conducted on short and informal texts, especially microblog messages.
Directional Skip-Gram: Explicitly Distinguishing Left and Right Context for Word Embeddings
In this paper, we present directional skip-gram (DSG), a simple but effective enhancement of the skip-gram model by explicitly distinguishing left and right context in word prediction.
Learning Word Representations with Regularization from Prior Knowledge
This paper presents a unified framework that leverages pre-learned or external priors, in the form of a regularizer, for enhancing conventional language model-based embedding learning.
Coding Structures and Actions with the COSTA Scheme in Medical Conversations
This paper describes the COSTA scheme for coding structures and actions in conversation.
Domain Adaptation for Disease Phrase Matching with Adversarial Networks
With the development of medical information management, numerous medical data are being classified, indexed, and searched in various systems.
A Joint Model of Conversational Discourse Latent Topics on Microblogs
To address this issue, we organize microblog messages as conversation trees based on their reposting and replying relations, and propose an unsupervised model that jointly learns word distributions to represent: (1) different roles of conversational discourse, and (2) various latent topics in reflecting content information.
Modern Chinese Helps Archaic Chinese Processing: Finding and Exploiting the Shared Properties
Languages change over time and ancient languages have been studied in linguistics and other related fields.
Using a Goodness Measurement for Domain Adaptation: A Case Study on Chinese Word Segmentation
Domain adaptation is an important topic for natural language processing.
Coordinated Reasoning for Cross-Lingual Knowledge Graph Alignment
Existing entity alignment methods mainly vary on the choices of encoding the knowledge graph, but they typically use the same decoding method, which independently chooses the local optimal match for each source entity.
Conditional Augmentation for Aspect Term Extraction via Masked Sequence-to-Sequence Generation
In this paper, we formulate the data augmentation as a conditional generation task: generating a new sentence while preserving the original opinion targets and labels.
Studying Challenges in Medical Conversation with Structured Annotation
Medical conversation is a central part of medical care.
XLST: Cross-lingual Self-training to Learn Multilingual Representation for Low Resource Speech Recognition
In this paper, we propose a weakly supervised multilingual representation learning framework, called cross-lingual self-training (XLST).
From Target Tracking to Targeting Track: A Data-Driven Yet Analytical Approach to Joint Target Detection and Tracking
This paper addresses the problem of real-time detection and tracking of a non-cooperative target in the challenging scenario with almost no a-priori information about target birth, death, dynamics and detection probability.
Understanding the Spread of COVID-19 Epidemic: A Spatio-Temporal Point Process View
In this paper, we model the propagation of the COVID-19 as spatio-temporal point processes and propose a generative and intensity-free model to track the spread of the disease.
Learning to Cluster via Same-Cluster Queries
We study the problem of learning to cluster data points using an oracle which can answer same-cluster queries.
Improving Arabic Diacritization with Regularized Decoding and Adversarial Training
Arabic diacritization is a fundamental task for Arabic language processing.
Meet Changes with Constancy: Learning Invariance in Multi-Source Translation
Multi-source neural machine translation aims to translate from parallel sources of information (e. g. languages, images, etc.)
Relation Extraction with Word Graphs from N-grams
Most recent studies for relation extraction (RE) leverage the dependency tree of the input sentence to incorporate syntax-driven contextual information to improve model performance, with little attention paid to the limitation where high-quality dependency parsers in most cases unavailable, especially for in-domain scenarios.
Improving Federated Learning for Aspect-based Sentiment Analysis via Topic Memories
Aspect-based sentiment analysis (ABSA) predicts the sentiment polarity towards a particular aspect term in a sentence, which is an important task in real-world applications.
Aspect-Based Sentiment Analysis
Aspect-Based Sentiment Analysis (ABSA)
+2
Exploring Word Segmentation and Medical Concept Recognition for Chinese Medical Texts
Chinese word segmentation (CWS) and medical concept recognition are two fundamental tasks to process Chinese electronic medical records (EMRs) and play important roles in downstream tasks for understanding Chinese EMRs.
DOMAIN ADAPTATION VIA DISTRIBUTION AND REPRESENTATION MATCHING: A CASE STUDY ON TRAINING DATA SELECTION VIA REINFORCEMENT LEARNING
Following the TDS methodology, in this paper, we propose a general data selection framework with representation learning and distribution matching simultaneously for domain adaptation on neural models.
Expansion-Squeeze-Excitation Fusion Network for Elderly Activity Recognition
This work focuses on the task of elderly activity recognition, which is a challenging task due to the existence of individual actions and human-object interactions in elderly activities.
Reinforced Cross-modal Alignment for Radiology Report Generation
In detail, a shared memory is used to record the mappings between visual and textual information, and the proposed reinforced algorithm is performed to learn the signal from the reports to guide the cross-modal alignment even though such reports are not directly related to how images and texts are mapped.
Turning to a Teacher for Timestamp Supervised Temporal Action Segmentation
To obtain more information to optimize the model, the existing method generated pseudo frame-wise labels iteratively based on the output of a segmentation model and the timestamp annotations.
Chinese Couplet Generation with Syntactic Information
Chinese couplet generation aims to generate a pair of clauses (usually generating a subsequent clause given an antecedent one) with certain rules (e. g., morphological and syntactical symmetry) adhered and has long been a challenging task with cultural background.
Neural Episodic Control with State Abstraction
Generally, episodic control-based approaches are solutions that leverage highly-rewarded past experiences to improve sample efficiency of DRL algorithms.
Unsupervised Neural Aspect Extraction with Sememes
Aspect extraction relies on identifying aspects by discovering coherence among words, which is challenging when word meanings are diversified and processing on short texts.
Aspect Extraction
Aspect Term Extraction and Sentiment Classification
+1
AST-SED: An Effective Sound Event Detection Method Based on Audio Spectrogram Transformer
In this paper, we propose an effective sound event detection (SED) method based on the audio spectrogram transformer (AST) model, pretrained on the large-scale AudioSet for audio tagging (AT) task, termed AST-SED.
Towards Solving Fuzzy Tasks with Human Feedback: A Retrospective of the MineRL BASALT 2022 Competition
To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022.
Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection
In this paper, we propose a joint generative and contrastive representation learning method (GeCo) for anomalous sound detection (ASD).
Hierarchical Audio-Visual Information Fusion with Multi-label Joint Decoding for MER 2023
Three different structures based on attention-guided feature gathering (AFG) are designed for deep feature fusion.
Ziya-Visual: Bilingual Large Vision-Language Model via Multi-Task Instruction Tuning
Recent advancements enlarge the capabilities of large language models (LLMs) in zero-shot image-to-text generation and understanding by integrating multi-modal inputs.
Ask more, know better: Reinforce-Learned Prompt Questions for Decision Making with Large Language Models
To that purpose, we offer a new leader-follower bilevel framework that is capable of learning to ask relevant questions (prompts) and subsequently undertaking reasoning to guide the learning of actions.
Ziya2: Data-centric Learning is All LLMs Need
Although many such issues are addressed along the line of research on LLMs, an important yet practical limitation is that many studies overly pursue enlarging model sizes without comprehensively analyzing and optimizing the use of pre-training data in their learning process, as well as appropriate organization and leveraging of such data in training LLMs under cost-effective settings.
Improving Image Captioning via Predicting Structured Concepts
Having the difficulty of solving the semantic gap between images and texts for the image captioning task, conventional studies in this area paid some attention to treating semantic concepts as a bridge between the two modalities and improved captioning performance accordingly.
iDesigner: A High-Resolution and Complex-Prompt Following Text-to-Image Diffusion Model for Interior Design
However, there are few specialized models in certain domains, such as interior design, which is attributed to the complex textual descriptions and detailed visual elements inherent in design, alongside the necessity for adaptable resolution.
Taiyi-Diffusion-XL: Advancing Bilingual Text-to-Image Generation with Large Vision-Language Model Support
Recent advancements in text-to-image models have significantly enhanced image generation capabilities, yet a notable gap of open-source models persists in bilingual or Chinese language support.
Learning Macroeconomic Policies based on Microfoundations: A Stackelberg Mean Field Game Approach
Effective macroeconomic policies play a crucial role in promoting economic growth and social stability.
