Auxiliary information from multiple sources has been demonstrated to be effective in zero-shot fine-grained entity typing (ZFET).
In this paper, we firstly empirically find that existing models struggle to handle hard mentions due to their insufficient contexts, which consequently limits their overall typing performance.
Existing work on Fine-grained Entity Typing (FET) typically trains automatic models on the datasets obtained by using Knowledge Bases (KB) as distant supervision.
Most existing chain-of-thought (CoT) 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 cases and lack task-level consistency in their reasoning steps.
In-context learning (ICL) ability has emerged with the increasing scale of large language models (LLMs), enabling them to learn input-label mappings from demonstrations and perform well on downstream tasks.
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.
Specifically, on the Chinese taxonomy dataset, our method significantly improves accuracy by 8. 75 %.
Modeling discourse -- the linguistic phenomena that go beyond individual sentences, is a fundamental yet challenging aspect of natural language processing (NLP).
Sentence embedding is one of the most fundamental tasks in Natural Language Processing and plays an important role in various tasks.
Generating proper embedding of sentences through an unsupervised way is beneficial to semantic matching and retrieval problems in real-world scenarios.
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 static word embeddings.
Evaluating the quality of generated text is a challenging task in NLP, due to the inherent complexity and diversity of text.
Based on our findings, we conclude that ChatGPT has great potential for keyphrase generation.
A recent line of work, detection-based defense, aims to distinguish adversarial sentences from benign ones.
The spread of rumors along with breaking events seriously hinders the truth in the era of social media.
In this paper, we introduce the Harry Potter Dialogue (HPD) dataset, designed to advance the study of dialogue agents and character alignment.
In Effidit, we significantly expand the capacities of a writing assistant by providing functions in five categories: text completion, error checking, text polishing, keywords to sentences (K2S), and cloud input methods (cloud IME).
Specifically, we focus on layer tuning for feed-forward network in the Transformer, namely FL-tuning.
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 than their reference-based counterparts.
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 to mislead the models.
no code implementations • • Lemao Liu, Haisong Zhang, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Dick Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This paper introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
However, few works have focused on how to validate and correct the results generated by the existing relation extraction models.
no code implementations • 31 Dec 2020 • Haisong Zhang, Lemao Liu, Haiyun Jiang, Yangming Li, Enbo Zhao, Kun Xu, Linfeng Song, Suncong Zheng, Botong Zhou, Jianchen Zhu, Xiao Feng, Tao Chen, Tao Yang, Dong Yu, Feng Zhang, Zhanhui Kang, Shuming Shi
This technique report introduces TexSmart, a text understanding system that supports fine-grained named entity recognition (NER) and enhanced semantic analysis functionalities.
We see information sources as multiple views and fusing them to construct an intact space with sufficient information.
In recent years, many complex relation extraction tasks, i. e., the variants of simple binary relation extraction, are proposed to meet the complex applications in practice.
A type description is a succinct noun compound which helps human and machines to quickly grasp the informative and distinctive information of an entity.
For the purpose of measuring the importance of knowledge, we introduce attention mechanisms and propose deep Short Text Classification with Knowledge powered Attention (STCKA).