相关论文: ERICA: Improving Entity and Relation Understanding…

Entity typing aims to assign types to the entity mentions in given texts. The traditional classification-based entity typing paradigm has two unignorable drawbacks: 1) it fails to assign an entity to the types beyond the predefined type…

Emotion Recognition in Conversation (ERC) plays an important role in driving the development of human-machine interaction. Emotions can exist in multiple modalities, and multimodal ERC mainly faces two problems: (1) the noise problem in the…

Pre-trained language models (PTLM) have achieved impressive results in a range of natural language understanding (NLU) and generation (NLG) tasks. However, current pre-training objectives such as masked token prediction (for BERT-style…

State-of-the-art natural language understanding classification models follow two-stages: pre-training a large language model on an auxiliary task, and then fine-tuning the model on a task-specific labeled dataset using cross-entropy loss.…

Named Entity Recognition (NER) aims to extract and classify entity mentions in the text into pre-defined types (e.g., organization or person name). Recently, many works have been proposed to shape the NER as a machine reading comprehension…

Despite pre-trained language models have proven useful for learning high-quality semantic representations, these models are still vulnerable to simple perturbations. Recent works aimed to improve the robustness of pre-trained models mainly…

Entity resolution has been an essential and well-studied task in data cleaning research for decades. Existing work has discussed the feasibility of utilizing pre-trained language models to perform entity resolution and achieved promising…

Expressing universal semantics common to all languages is helpful in understanding the meanings of complex and culture-specific sentences. The research theme underlying this scenario focuses on learning universal representations across…

Recently pre-training models have significantly improved the performance of various NLP tasks by leveraging large-scale text corpora to improve the contextual representation ability of the neural network. The large pre-training language…

Linking biomedical entities is an essential aspect in biomedical natural language processing tasks, such as text mining and question answering. However, a difficulty of linking the biomedical entities using current large language models…

Conversational recommender systems (CRS) utilize natural language interactions and dialogue history to infer user preferences and provide accurate recommendations. Due to the limited conversation context and background knowledge, existing…

Large Language Models (LLMs) have demonstrated impressive capabilities in language generation and general task performance. However, their application to spoken language understanding (SLU) remains challenging, particularly for token-level…

Relation extraction (RE), which has relied on structurally annotated corpora for model training, has been particularly challenging in low-resource scenarios and domains. Recent literature has tackled low-resource RE by self-supervised…

Entity Matching (EM) involves identifying different data representations referring to the same entity from multiple data sources and is typically formulated as a binary classification problem. It is a challenging problem in data integration…

For years, adversarial training has been extensively studied in natural language processing (NLP) settings. The main goal is to make models robust so that similar inputs derive in semantically similar outcomes, which is not a trivial…

Large-scale pre-trained models such as CodeBERT, GraphCodeBERT have earned widespread attention from both academia and industry. Attributed to the superior ability in code representation, they have been further applied in multiple…

Tracking entities in procedural language requires understanding the transformations arising from actions on entities as well as those entities' interactions. While self-attention-based pre-trained language encoders like GPT and BERT have…

Entity linking (EL) is the task of disambiguating mentions in text by associating them with entries in a predefined database of mentions (persons, organizations, etc). Most previous EL research has focused mainly on one language, English,…

Meta-learning enables learning systems to adapt quickly to new tasks, similar to humans. Different meta-learning approaches all work under/with the mini-batch episodic training framework. Such framework naturally gives the information about…

Humans use language to refer to entities in the external world. Motivated by this, in recent years several models that incorporate a bias towards learning entity representations have been proposed. Such entity-centric models have shown…