NLAS-multi: A multilingual corpus of automatically generated Natural Language Argumentation Schemes. [PDF]
Some of the major limitations identified in the areas of argument mining, argument generation, and natural language argument analysis are related to the complexity of annotating argumentatively rich data, the limited size of these corpora, and the constraints that represent the different languages and domains in which these data is annotated.
Ruiz-Dolz R+3 more
europepmc +2 more sources
Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [PDF]
This article surveys and organizes research works in a new paradigm in natural language processing, which we dub “prompt-based learning.” Unlike traditional supervised learning, which trains a model to take in an input x and predict an output y as P(y|x),
Pengfei Liu+5 more
semanticscholar +1 more source
Survey of Hallucination in Natural Language Generation [PDF]
Natural Language Generation (NLG) has improved exponentially in recent years thanks to the development of sequence-to-sequence deep learning technologies such as Transformer-based language models. This advancement has led to more fluent and coherent NLG,
Ziwei Ji+11 more
semanticscholar +1 more source
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation [PDF]
We introduce a method to measure uncertainty in large language models. For tasks like question answering, it is essential to know when we can trust the natural language outputs of foundation models.
Lorenz Kuhn, Y. Gal, Sebastian Farquhar
semanticscholar +1 more source
Organizing an in-class hackathon to correct PDF-to-text conversion errors of 1.0 [PDF]
This paper describes a community effort to improve earlier versions of the full-text corpus of Genomics & Informatics by semi-automatically detecting and correcting PDF-to-text conversion errors and optical character recognition errors during the first ...
Sunho Kim+44 more
doaj +1 more source
Is ChatGPT a General-Purpose Natural Language Processing Task Solver? [PDF]
Spurred by advancements in scale, large language models (LLMs) have demonstrated the ability to perform a variety of natural language processing (NLP) tasks zero-shot -- i.e., without adaptation on downstream data.
Chengwei Qin+5 more
semanticscholar +1 more source
Can Language Models Solve Graph Problems in Natural Language? [PDF]
Large language models (LLMs) are increasingly adopted for a variety of tasks with implicit graphical structures, such as planning in robotics, multi-hop question answering or knowledge probing, structured commonsense reasoning, and more.
Heng Wang+5 more
semanticscholar +1 more source
Text2Motion: from natural language instructions to feasible plans [PDF]
We propose Text2Motion, a language-based planning framework enabling robots to solve sequential manipulation tasks that require long-horizon reasoning. Given a natural language instruction, our framework constructs both a task- and motion-level plan that
Kevin Lin+4 more
semanticscholar +1 more source
Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models [PDF]
To recognize and mitigate harms from large language models (LLMs), we need to understand the prevalence and nuances of stereotypes in LLM outputs. Toward this end, we present Marked Personas, a prompt-based method to measure stereotypes in LLMs for ...
Myra Cheng, Esin Durmus, Dan Jurafsky
semanticscholar +1 more source
Text-to-SQL is the problem of converting a user question into an SQL query, when the question and database are given. In this article, we present a neural network approach called RYANSQL (Recursively Yielding Annotation Network for SQL) to solve complex ...
DongHyun Choi+3 more
doaj +1 more source