306 citations · 1.3k across the 118 of their papers we have counts for
19 papers · 1 filter
Evaluating Psychological Safety of Large Language Models
Xingxuan Li, Yutong Li, Lin Qiu +2
In this work, we designed unbiased prompts to systematically evaluate the psychological safety of large language models (LLMs). First, we tested five different LLMs by using two pe…
Is GPT-3 a Good Data Annotator?
Bosheng Ding, Chengwei Qin, Linlin Liu +4
Data annotation is the process of labeling data that could be used to train machine learning models. Having high-quality annotation is crucial, as it allows the model to learn the…
From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Model to Pre-trained Machine Reader
Weiwen Xu, Xin Li, Wenxuan Zhang +4
We present Pre-trained Machine Reader (PMR), a novel method for retrofitting pre-trained masked language models (MLMs) to pre-trained machine reading comprehension (MRC) models wit…
On the Effectiveness of Parameter-Efficient Fine-Tuning
Zihao Fu, Haoran Yang, Anthony Man-Cho So +3
Fine-tuning pre-trained models has been ubiquitously proven to be effective in a wide range of NLP tasks. However, fine-tuning the whole model is parameter inefficient as it always…
A Dataset for Hyper-Relational Extraction and a Cube-Filling Approach
Yew Ken Chia, Lidong Bing, Sharifah Mahani Aljunied +2
Relation extraction has the potential for large-scale knowledge graph construction, but current methods do not consider the qualifier attributes for each relation triplet, such as…
ConNER: Consistency Training for Cross-lingual Named Entity Recognition
Ran Zhou, Xin Li, Lidong Bing +3
Cross-lingual named entity recognition (NER) suffers from data scarcity in the target languages, especially under zero-shot settings. Existing translate-train or knowledge distilla…
Towards Robust Low-Resource Fine-Tuning with Multi-View Compressed Representations
Linlin Liu, Xingxuan Li, Megh Thakkar +4
Due to the huge amount of parameters, fine-tuning of pretrained language models (PLMs) is prone to overfitting in the low resource scenarios. In this work, we present a novel metho…
Adaptive Contrastive Learning on Multimodal Transformer for Review Helpfulness Predictions
Thong Nguyen, Xiaobao Wu, Anh-Tuan Luu +3
Modern Review Helpfulness Prediction systems are dependent upon multiple modalities, typically texts and images. Unfortunately, those contemporary approaches pay scarce attention t…
Retrofitting Multilingual Sentence Embeddings with Abstract Meaning Representation
Deng Cai, Xin Li, Jackie Chun-Sing Ho +2
We introduce a new method to improve existing multilingual sentence embeddings with Abstract Meaning Representation (AMR). Compared with the original textual input, AMR is a struct…
SANCL: Multimodal Review Helpfulness Prediction with Selective Attention and Natural Contrastive Learning
Wei Han, Hui Chen, Zhen Hai +2
With the boom of e-commerce, Multimodal Review Helpfulness Prediction (MRHP), which aims to sort product reviews according to the predicted helpfulness scores has become a research…
SentBS: Sentence-level Beam Search for Controllable Summarization
Chenhui Shen, Liying Cheng, Lidong Bing +2
A wide range of control perspectives have been explored in controllable text generation. Structure-controlled summarization is recently proposed as a useful and interesting researc…
PeerDA: Data Augmentation via Modeling Peer Relation for Span Identification Tasks
Weiwen Xu, Xin Li, Yang Deng +2
Span identification aims at identifying specific text spans from text input and classifying them into pre-defined categories. Different from previous works that merely leverage the…
Informative Text Generation from Knowledge Triples
Zihao Fu, Yijiang River Dong, Lidong Bing +1
As the development of the encoder-decoder architecture, researchers are able to study the text generation tasks with broader types of data. Among them, KB-to-text aims at convertin…
Revisiting DocRED -- Addressing the False Negative Problem in Relation Extraction
Qingyu Tan, Lu Xu, Lidong Bing +2
The DocRED dataset is one of the most popular and widely used benchmarks for document-level relation extraction (RE). It adopts a recommend-revise annotation scheme so as to have a…
Document-Level Relation Extraction with Adaptive Focal Loss and Knowledge Distillation
Qingyu Tan, Ruidan He, Lidong Bing +1
Document-level Relation Extraction (DocRE) is a more challenging task compared to its sentence-level counterpart. It aims to extract relations from multiple sentences at once. In t…
RelationPrompt: Leveraging Prompts to Generate Synthetic Data for Zero-Shot Relation Triplet Extraction
Yew Ken Chia, Lidong Bing, Soujanya Poria +1
Despite the importance of relation extraction in building and representing knowledge, less research is focused on generalizing to unseen relations types. We introduce the task sett…
IAM: A Comprehensive and Large-Scale Dataset for Integrated Argument Mining Tasks
Liying Cheng, Lidong Bing, Ruidan He +3
Traditionally, a debate usually requires a manual preparation process, including reading plenty of articles, selecting the claims, identifying the stances of the claims, seeking th…
A Survey on Aspect-Based Sentiment Analysis: Tasks, Methods, and Challenges
Wenxuan Zhang, Xin Li, Yang Deng +2
As an important fine-grained sentiment analysis problem, aspect-based sentiment analysis (ABSA), aiming to analyze and understand people's opinions at the aspect level, has been at…
Enhancing Cross-lingual Prompting with Dual Prompt Augmentation
Meng Zhou, Xin Li, Yue Jiang +1
Prompting shows promising results in few-shot scenarios. However, its strength for multilingual/cross-lingual problems has not been fully exploited. Zhao and Schütze (2021) made in…