Related papers: Refined Commonsense Knowledge from Large-Scale Web…
The rapid increase in hate speech on social media has exposed an unprecedented impact on society, making automated methods for detecting such content important. Unlike prior black-box models, we propose a novel transparent method for…
Recently several datasets have been proposed to encourage research in Question Answering domains where commonsense knowledge is expected to play an important role. Recent language models such as ROBERTA, BERT and GPT that have been…
Commonsense generation is a challenging task of generating a plausible sentence describing an everyday scenario using provided concepts. Its requirement of reasoning over commonsense knowledge and compositional generalization ability even…
Commonsense knowledge about object properties, human behavior and general concepts is crucial for robust AI applications. However, automatic acquisition of this knowledge is challenging because of sparseness and bias in online sources. This…
Concepts embody the knowledge of the world and facilitate the cognitive processes of human beings. Mining concepts from web documents and constructing the corresponding taxonomy are core research problems in text understanding and support…
Composing knowledge from multiple pieces of texts is a key challenge in multi-hop question answering. We present a multi-hop reasoning dataset, Question Answering via Sentence Composition(QASC), that requires retrieving facts from a large…
Large language models (LLMs) have recently emerged as powerful training-free recommenders. However, their knowledge of individual items is inevitably uneven due to imbalanced information exposure during pretraining, a phenomenon we refer to…
In order to facilitate natural language understanding, the key is to engage commonsense or background knowledge. However, how to engage commonsense effectively in question answering systems is still under exploration in both research…
Recent efforts have aimed to utilize multilingual pretrained language models (mPLMs) to extend semantic parsing (SP) across multiple languages without requiring extensive annotations. However, achieving zero-shot cross-lingual transfer for…
With the constantly growing number of reviews and other sentiment-bearing texts on the Web, the demand for automatic sentiment analysis algorithms continues to expand. Aspect-based sentiment classification (ABSC) allows for the automatic…
Spoken conversational question answering (SCQA) requires machines to model complex dialogue flow given the speech utterances and text corpora. Different from traditional text question answering (QA) tasks, SCQA involves audio signal…
Data augmentation has been proved effective in training deep models. Existing data augmentation methods tackle the fine-grained problem by blending image pairs and fusing corresponding labels according to the statistics of mixed pixels,…
Researchers have investigated the potential of leveraging pre-trained language models, such as CodeBERT, to enhance source code-related tasks. Previous methodologies have relied on CodeBERT's '[CLS]' token as the embedding representation of…
Knowledge extrapolation is the process of inferring novel information by combining and extending existing knowledge that is explicitly available. It is essential for solving complex questions in specialized domains where retrieving…
We study how to enhance text representation via textual commonsense. We point out that commonsense has the nature of domain discrepancy. Namely, commonsense has different data formats and is domain-independent from the downstream task. This…
The field of artificial intelligence has witnessed significant advancements in natural language processing, largely attributed to the capabilities of Large Language Models (LLMs). These models form the backbone of Agents designed to address…
In aspect-level sentiment classification (ASC), it is prevalent to equip dominant neural models with attention mechanisms, for the sake of acquiring the importance of each context word on the given aspect. However, such a mechanism tends to…
Commonsense generation aims at generating plausible everyday scenario description based on a set of provided concepts. Digging the relationship of concepts from scratch is non-trivial, therefore, we retrieve prototypes from external…
Plausibility Estimation (PE) plays a crucial role for enabling language models to objectively comprehend the real world. While large language models (LLMs) demonstrate remarkable capabilities in PE tasks but sometimes produce trivial…
Knowledge Editing (KE) aims to adjust a Large Language Model's (LLM) internal representations and parameters to correct inaccuracies and improve output consistency without incurring the computational expense of re-training the entire model.…