21 citations · 120 across the 24 of their papers we have counts for
24 papers
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
Chang Gao, Haiyun Jiang, Deng Cai +2
Most existing prompting methods suffer from the issues of generalizability and consistency, as they often rely on instance-specific solutions that may not be applicable to other in…
A Benchmark for Text Expansion: Datasets, Metrics, and Baselines
Yi Chen, Haiyun Jiang, Wei Bi +4
This work presents a new task of Text Expansion (TE), which aims to insert fine-grained modifiers into proper locations of the plain text to concretize or vivify human writings. Di…
Towards Visual Taxonomy Expansion
Tinghui Zhu, Jingping Liu, Jiaqing Liang +5
Taxonomy expansion task is essential in organizing the ever-increasing volume of new concepts into existing taxonomies. Most existing methods focus exclusively on using textual sem…
DoG-Instruct: Towards Premium Instruction-Tuning Data via Text-Grounded Instruction Wrapping
Yongrui Chen, Haiyun Jiang, Xinting Huang +2
The improvement of LLMs' instruction-following capabilities relies heavily on the availability of high-quality instruction-response pairs. Unfortunately, the current methods used t…
Disco-Bench: A Discourse-Aware Evaluation Benchmark for Language Modelling
Longyue Wang, Zefeng Du, Donghuai Liu +7
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP). However, existing…
Sen2Pro: A Probabilistic Perspective to Sentence Embedding from Pre-trained Language Model
Lingfeng Shen, Haiyun Jiang, Lemao Liu +1
Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks. The recent breakthrough in sentence embedding i…
Frequency-aware Dimension Selection for Static Word Embedding by Mixed Product Distance
Lingfeng Shen, Haiyun Jiang, Lemao Liu +1
Static word embedding is still useful, particularly for context-unavailable tasks, because in the case of no context available, pre-trained language models often perform worse than…
A Simple and Plug-and-play Method for Unsupervised Sentence Representation Enhancement
Lingfeng Shen, Haiyun Jiang, Lemao Liu +1
Generating proper embedding of sentences through an unsupervised way is beneficial to semantic matching and retrieval problems in real-world scenarios. This paper presents Represen…
Exploring the Use of Large Language Models for Reference-Free Text Quality Evaluation: An Empirical Study
Yi Chen, Rui Wang, Haiyun Jiang +2
Evaluating the quality of generated text is a challenging task in NLP, due to the inherent complexity and diversity of text. Recently, large language models (LLMs) have garnered si…
Is ChatGPT A Good Keyphrase Generator? A Preliminary Study
Mingyang Song, Haiyun Jiang, Shuming Shi +5
The emergence of ChatGPT has recently garnered significant attention from the computational linguistics community. To demonstrate its capabilities as a keyphrase generator, we cond…
TextShield: Beyond Successfully Detecting Adversarial Sentences in Text Classification
Lingfeng Shen, Ze Zhang, Haiyun Jiang +1
Adversarial attack serves as a major challenge for neural network models in NLP, which precludes the model's deployment in safety-critical applications. A recent line of work, dete…
Zero-Shot Rumor Detection with Propagation Structure via Prompt Learning
Hongzhan Lin, Pengyao Yi, Jing Ma +4
The spread of rumors along with breaking events seriously hinders the truth in the era of social media. Previous studies reveal that due to the lack of annotated resources, rumors…
Large Language Models Meet Harry Potter: A Bilingual Dataset for Aligning Dialogue Agents with Characters
Nuo Chen, Yan Wang, Haiyun Jiang +5
In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, alig…
Effidit: Your AI Writing Assistant
Shuming Shi, Enbo Zhao, Duyu Tang +10
In this technical report, we introduce Effidit (Efficient and Intelligent Editing), a digital writing assistant that facilitates users to write higher-quality text more efficiently…
FL-Tuning: Layer Tuning for Feed-Forward Network in Transformer
Jingping Liu, Yuqiu Song, Kui Xue +6
Prompt tuning is an emerging way of adapting pre-trained language models to downstream tasks. However, the existing studies are mainly to add prompts to the input sequence. This wa…
Context Enhanced Short Text Matching using Clickthrough Data
Mao Yan Chen, Haiyun Jiang, Yujiu Yang
The short text matching task employs a model to determine whether two short texts have the same semantic meaning or intent. Existing short text matching models usually rely on the…
Rethink the Evaluation for Attack Strength of Backdoor Attacks in Natural Language Processing
Lingfeng Shen, Haiyun Jiang, Lemao Liu +1
It has been shown that natural language processing (NLP) models are vulnerable to a kind of security threat called the Backdoor Attack, which utilizes a `backdoor trigger' paradigm…
On the Evaluation Metrics for Paraphrase Generation
Lingfeng Shen, Lemao Liu, Haiyun Jiang +1
In this paper we revisit automatic metrics for paraphrase evaluation and obtain two findings that disobey conventional wisdom: (1) Reference-free metrics achieve better performance…
A Question-answering Based Framework for Relation Extraction Validation
Jiayang Cheng, Haiyun Jiang, Deqing Yang +1
Relation extraction is an important task in knowledge acquisition and text understanding. Existing works mainly focus on improving relation extraction by extracting effective featu…
TexSmart: A Text Understanding System for Fine-Grained NER and Enhanced Semantic Analysis
Haisong Zhang, Lemao Liu, Haiyun Jiang +14
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities. Com…
InSRL: A Multi-view Learning Framework Fusing Multiple Information Sources for Distantly-supervised Relation Extraction
Zhendong Chu, Haiyun Jiang, Yanghua Xiao +1
Distant supervision makes it possible to automatically label bags of sentences for relation extraction by leveraging knowledge bases, but suffers from the sparse and noisy bag issu…
Complex Relation Extraction: Challenges and Opportunities
Haiyun Jiang, Qiaoben Bao, Qiao Cheng +3
Relation extraction aims to identify the target relations of entities in texts. Relation extraction is very important for knowledge base construction and text understanding. Tradit…
Ensuring Readability and Data-fidelity using Head-modifier Templates in Deep Type Description Generation
Jiangjie Chen, Ao Wang, Haiyun Jiang +3
A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity. Entities in most knowledge…
Deep Short Text Classification with Knowledge Powered Attention
Jindong Chen, Yizhou Hu, Jingping Liu +2
Short text classification is one of important tasks in Natural Language Processing (NLP). Unlike paragraphs or documents, short texts are more ambiguous since they have not enough…