Related papers: Retrieval Enhanced Model for Commonsense Generatio…
Generative commonsense reasoning requires machines to generate sentences describing an everyday scenario given several concepts, which has attracted much attention recently. However, existing models cannot perform as well as humans, since…
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…
Story generation, namely generating a reasonable story from a leading context, is an important but challenging task. In spite of the success in modeling fluency and local coherence, existing neural language generation models (e.g., GPT-2)…
Since commonsense information has been recorded significantly less frequently than its existence, language models pre-trained by text generation have difficulty to learn sufficient commonsense knowledge. Several studies have leveraged text…
Commonsense generation aims to generate a realistic sentence describing a daily scene under the given concepts, which is very challenging, since it requires models to have relational reasoning and compositional generalization capabilities.…
Sequence generation models for dialogue are known to have several problems: they tend to produce short, generic sentences that are uninformative and unengaging. Retrieval models on the other hand can surface interesting responses, but are…
Recent advances in large-scale pre-training such as GPT-3 allow seemingly high quality text to be generated from a given prompt. However, such generation systems often suffer from problems of hallucinated facts, and are not inherently…
While commonsense knowledge acquisition and reasoning has traditionally been a core research topic in the knowledge representation and reasoning community, recent years have seen a surge of interest in the natural language processing…
Generative commonsense reasoning is the capability of a language model to generate a sentence with a given concept-set that is based on commonsense knowledge. However, generative language models still struggle to provide outputs, and the…
Recently, large-scale pre-trained language models have demonstrated impressive performance on several commonsense-reasoning benchmark datasets. However, building machines with commonsense to compose realistically plausible sentences remains…
Large language models augmented with task-relevant documents have demonstrated impressive performance on knowledge-intensive tasks. However, regarding how to obtain effective documents, the existing methods are mainly divided into two…
This paper studies constrained text generation, which is to generate sentences under certain pre-conditions. We focus on CommonGen, the task of generating text based on a set of concepts, as a representative task of constrained text…
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…
Conditional text generation has been a challenging task that is yet to see human-level performance from state-of-the-art models. In this work, we specifically focus on the Commongen benchmark, wherein the aim is to generate a plausible…
Question generation (QG) is to generate natural and grammatical questions that can be answered by a specific answer for a given context. Previous sequence-to-sequence models suffer from a problem that asking high-quality questions requires…
Standard language models generate text by selecting tokens from a fixed, finite, and standalone vocabulary. We introduce a novel method that selects context-aware phrases from a collection of supporting documents. One of the most…
Stories generated with neural language models have shown promise in grammatical and stylistic consistency. However, the generated stories are still lacking in common sense reasoning, e.g., they often contain sentences deprived of world…
Generative Commonsense Reasoning (GCR) requires a model to reason about a situation using commonsense knowledge, while generating coherent sentences. Although the quality of the generated sentences is crucial, the diversity of the…
Retrieval augmented generation mitigates limitations of large language models in factual consistency and knowledge updating by introducing external knowledge. However, practical applications still suffer from semantic misalignment between…
Inferring commonsense knowledge is a key challenge in natural language processing, but due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on…