相关论文: Knowledge-Augmented Language Models for Cause-Effe…

Implicit knowledge, such as common sense, is key to fluid human conversations. Current neural response generation (RG) models are trained to generate responses directly, omitting unstated implicit knowledge. In this paper, we present…

Recent works show that pre-trained language models (PTLMs), such as BERT, possess certain commonsense and factual knowledge. They suggest that it is promising to use PTLMs as "neural knowledge bases" via predicting masked words.…

When people reason about cause and effect, they often consider many competing "what if" scenarios before deciding which explanation fits best. Analogously, advanced language models capable of causal inference can consider multiple…

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on understanding of the…

Current pre-trained language models have enabled remarkable improvements in downstream tasks, but it remains difficult to distinguish effects of statistical correlation from more systematic logical reasoning grounded on the understanding of…

Prior work has shown that the ordering in which concepts are shown to a commonsense generator plays an important role, affecting the quality of the generated sentence. However, it remains a challenge to determine the optimal ordering of a…

A fundamental ability of humans is to utilize commonsense knowledge in language understanding and question answering. In recent years, many knowledge-enhanced Commonsense Question Answering (CQA) approaches have been proposed. However, it…

Event commonsense reasoning requires the ability to reason about the relationship between events, as well as infer implicit context underlying that relationship. However, data scarcity makes it challenging for language models to learn to…

Large pre-trained language models have been shown to encode large amounts of world and commonsense knowledge in their parameters, leading to substantial interest in methods for extracting that knowledge. In past work, knowledge was…

Recent approaches to empathetic response generation try to incorporate commonsense knowledge or reasoning about the causes of emotions to better understand the user's experiences and feelings. However, these approaches mainly focus on…

Open-domain dialogue systems need to grasp social commonsense to understand and respond effectively to human users. Commonsense-augmented dialogue models have been proposed that aim to infer commonsense knowledge from dialogue contexts in…

Commonsense reasoning (CR) has been studied in many pieces of domain and has achieved great progress with the aid of large datasets. Unfortunately, most existing CR datasets are built in English, so most previous work focus on English.…

When provided with sufficient explanatory context, smaller Language Models have been shown to exhibit strong reasoning ability on challenging short-answer question-answering tasks where the questions are unseen in training. We evaluate two…

A common thread of retrieval-augmented methods in the existing literature focuses on retrieving encyclopedic knowledge, such as Wikipedia, which facilitates well-defined entity and relation spaces that can be modeled. However, applying such…

Commonsense reasoning has long been considered as one of the holy grails of artificial intelligence. Most of the recent progress in the field has been achieved by novel machine learning algorithms for natural language processing. However,…

Despite large-scale pre-trained language models have achieved striking results for text classificaion, recent work has raised concerns about the challenge of shortcut learning. In general, a keyword is regarded as a shortcut if it creates a…

Memorizing and utilizing speakers' personas is a common practice for response generation in long-term conversations. Yet, human-authored datasets often provide uninformative persona sentences that hinder response quality. This paper…

Causal knowledge extraction is the task of extracting relevant causes and effects from text by detecting the causal relation. Although this task is important for language understanding and knowledge discovery, recent works in this domain…

Acquiring commonsense knowledge and reasoning is recognized as an important frontier in achieving general Artificial Intelligence (AI). Recent research in the Natural Language Processing (NLP) community has demonstrated significant progress…

Pre-trained language models (PLMs) have been prevailing in state-of-the-art methods for natural language processing, and knowledge-enhanced PLMs are further proposed to promote model performance in knowledge-intensive tasks. However,…