Search Results for author:
Found 30 papers, 11 papers with code
HanTrans: An Empirical Study on Cross-Era Transferability of Chinese Pre-trained Language Model
Most of all, the ancient Chinese corpus is still disappearance in the pre-training stage.
Converting the Sinica Treebank of Mandarin Chinese to Universal Dependencies
This paper describes the conversion of the Sinica Treebank, one of the major Mandarin Chinese treebanks, to Universal Dependencies.
Semantic Guidance of Dialogue Generation with Reinforcement Learning
To address this, in this paper, we propose semantic guidance using reinforcement learning to ensure that the generated responses indeed include the given or predicted semantics and that these semantics do not appear repeatedly in the response.
Not All LLM-Generated Data Are Equal: Rethinking Data Weighting in Text Classification
Synthetic data augmentation via large language models (LLMs) allows researchers to leverage additional training data, thus enhancing the performance of downstream tasks, especially when real-world data is scarce.
Generating Attractive and Authentic Copywriting from Customer Reviews
The goal of product copywriting is to capture the interest of potential buyers by emphasizing the features of products through text descriptions.
Extending the Pre-Training of BLOOM for Improved Support of Traditional Chinese: Models, Methods and Results
In this paper we present the multilingual language model BLOOM-zh that features enhanced support for Traditional Chinese.
Roof-Transformer: Divided and Joined Understanding with Knowledge Enhancement
Recent work on enhancing BERT-based language representation models with knowledge graphs (KGs) and knowledge bases (KBs) has yielded promising results on multiple NLP tasks.
DCT: Dynamic Compressive Transformer for Modeling Unbounded Sequence
In this paper, we propose Dynamic Compressive Transformer (DCT), a transformer-based framework for modeling the unbounded sequence.
H-FND: Hierarchical False-Negative Denoising for Distant Supervision Relation Extraction
Experiments on SemEval-2010 and TACRED were conducted with controlled FN ratios that randomly turn the relations of training and validation instances into negatives to generate FN instances.
Predict and Use Latent Patterns for Short-Text Conversation
Many neural network models nowadays have achieved promising performances in Chit-chat settings.
Headword-Oriented Entity Linking: A Special Entity Linking Task with Dataset and Baseline
In this paper, we design headword-oriented entity linking (HEL), a specialized entity linking problem in which only the headwords of the entities are to be linked to knowledge bases; mention scopes of the entities do not need to be identified in the problem setting.
Why Attention? Analyzing and Remedying BiLSTM Deficiency in Modeling Cross-Context for NER
State-of-the-art approaches of NER have used sequence-labeling BiLSTM as a core module.
Why Attention? Analyze BiLSTM Deficiency and Its Remedies in the Case of NER
We test the practical impacts of the deficiency on real-world NER datasets, OntoNotes 5. 0 and WNUT 2017, with clear and consistent improvements over the baseline, up to 8. 7% on some of the multi-token entity mentions.
Ranked #20 on
Named Entity Recognition (NER)
on WNUT 2017
CA-EHN: Commonsense Analogy from E-HowNet
We present CA-EHN, the first commonsense word analogy dataset containing 90, 505 analogies covering 5, 656 words and 763 relations.
GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction
In contrast to previous baselines, we consider the interaction between named entities and relations via a 2nd-phase relation-weighted GCN to better extract relations.
iComposer: An Automatic Songwriting System for Chinese Popular Music
In this paper, we introduce iComposer, an interactive web-based songwriting system designed to assist human creators by greatly simplifying music production.
Speed Reading: Learning to Read ForBackward via Shuttle
We present LSTM-Shuttle, which applies human speed reading techniques to natural language processing tasks for accurate and efficient comprehension.
CKIP at IJCNLP-2017 Task 2: Neural Valence-Arousal Prediction for Phrases
In addition, the CKIP phrase Valence-Arousal (VA) predictor depends on knowledge of modifier words and head words.
Guess What: A Question Answering Game via On-demand Knowledge Validation
In this paper, we propose an idea of ondemand knowledge validation and fulfill the idea through an interactive Question-Answering (QA) game system, which is named Guess What.
Leveraging Linguistic Structures for Named Entity Recognition with Bidirectional Recursive Neural Networks
Motivated by the observation that named entities are highly related to linguistic constituents, we propose a constituent-based BRNN-CNN for named entity recognition.
Integrating Semantic Knowledge into Lexical Embeddings Based on Information Content Measurement
Distributional word representations are widely used in NLP tasks.
