Results 1 to 10 of about 7,007,067 (368)

NLAS-multi: A multilingual corpus of automatically generated Natural Language Argumentation Schemes. [PDF]

Data Brief
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, Taverner J, Lawrence J, Reed C.   +3 more
europepmc   +2 more sources

Pre-train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing [PDF]

ACM Computing Surveys, 2021
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, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, Graham Neubig   +5 more
semanticscholar   +1 more source

Survey of Hallucination in Natural Language Generation [PDF]

ACM Computing Surveys, 2022
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, Nayeon Lee, Rita Frieske, Tiezheng Yu, D. Su, Yan Xu, Etsuko Ishii, Yejin Bang, Delong Chen, Wenliang Dai, Andrea Madotto, Pascale Fung   +11 more
semanticscholar   +1 more source

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation [PDF]

International Conference on Learning Representations, 2023
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]

Genomics & Informatics, 2020
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, Royoung Kim, Hee-Jo Nam, Ryeo-Gyeong Kim, Enjin Ko, Han-Su Kim, Jihye Shin, Daeun Cho, Yurhee Jin, Soyeon Bae, Ye Won Jo, San Ah Jeong, Yena Kim, Seoyeon Ahn, Bomi Jang, Jiheyon Seong, Yujin Lee, Si Eun Seo, Yujin Kim, Ha-Jeong Kim, Hyeji Kim, Hye-Lynn Sung, Hyoyoung Lho, Jaywon Koo, Jion Chu, Juwon Lim, Youngju Kim, Kyungyeon Lee, Yuri Lim, Meongeun Kim, Seonjeong Hwang, Shinhye Han, Sohyeun Bae, Sua Kim, Suhyeon Yoo, Yeonjeong Seo, Yerim Shin, Yonsoo Kim, You-Jung Ko, Jihee Baek, Hyejin Hyun, Hyemin Choi, Ji-Hye Oh, Da-Young Kim, Hyun-Seok Park   +44 more
doaj   +1 more source

Is ChatGPT a General-Purpose Natural Language Processing Task Solver? [PDF]

Conference on Empirical Methods in Natural Language Processing, 2023
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, Aston Zhang, Zhuosheng Zhang, Jiaao Chen, Michihiro Yasunaga, Diyi Yang   +5 more
semanticscholar   +1 more source

Can Language Models Solve Graph Problems in Natural Language? [PDF]

Neural Information Processing Systems, 2023
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, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov   +5 more
semanticscholar   +1 more source

Text2Motion: from natural language instructions to feasible plans [PDF]

Autonomous Robots, 2023
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, Christopher Agia, Toki Migimatsu, M. Pavone, Jeannette Bohg   +4 more
semanticscholar   +1 more source

Marked Personas: Using Natural Language Prompts to Measure Stereotypes in Language Models [PDF]

Annual Meeting of the Association for Computational Linguistics, 2023
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

RYANSQL: Recursively Applying Sketch-based Slot Fillings for Complex Text-to-SQL in Cross-Domain Databases

Computational Linguistics, 2021
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, Myeong Cheol Shin, EungGyun Kim, Dong Ryeol Shin   +3 more
doaj   +1 more source