Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End

• URL: http://arxiv.org/abs/2212.10522v2
• Date: Tue, 26 Dec 2023 18:05:42 GMT
• Title: Transformers Go for the LOLs: Generating (Humourous) Titles from Scientific Abstracts End-to-End
• Authors: Yanran Chen and Steffen Eger
• Abstract summary: We consider the end-to-end abstract-to-title generation problem, exploring seven recent transformer based models. We also consider the harder problem of generating humorous paper titles. For the latter, we compile the first large-scale humor annotated dataset for scientific papers in the NLP/ML domains.
• Score: 26.53850343633923
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We consider the end-to-end abstract-to-title generation problem, exploring seven recent transformer based models (including ChatGPT) fine-tuned on more than 30k abstract-title pairs from NLP and machine learning (ML) venues. As an extension, we also consider the harder problem of generating humorous paper titles. For the latter, we compile the first large-scale humor annotated dataset for scientific papers in the NLP/ML domains, comprising almost ~2.6k titles. We evaluate all models using human and automatic metrics. Our human evaluation suggests that our best end-to-end system performs similarly to human authors (but arguably slightly worse). Generating funny titles is more difficult, however, and our automatic systems clearly underperform relative to humans and often learn dataset artefacts of humor. Finally, ChatGPT, without any fine-tuning, performs on the level of our best fine-tuned system.

Related papers

• Integrating Planning into Single-Turn Long-Form Text Generation [66.08871753377055]
  We propose to use planning to generate long form content. Our main novelty lies in a single auxiliary task that does not require multiple rounds of prompting or planning. Our experiments demonstrate on two datasets from different domains, that LLMs fine-tuned with the auxiliary task generate higher quality documents.
  arXiv  Detail & Related papers  (2024-10-08T17:02:40Z)
• Can pre-trained language models generate titles for research papers? [3.3489486000815765]
  In this paper, we fine-tune pre-trained language models to generate titles of papers from their abstracts. We also use GPT-3.5-turbo in a zero-shot setting to generate paper titles. Our observations suggest that AI-generated paper titles are generally accurate and appropriate.
  arXiv  Detail & Related papers  (2024-09-22T21:34:49Z)
• LitLLM: A Toolkit for Scientific Literature Review [15.080020634480272]
  Toolkit operates on Retrieval Augmented Generation (RAG) principles. System first initiates a web search to retrieve relevant papers. Second, the system re-ranks the retrieved papers based on the user-provided abstract. Third, the related work section is generated based on the re-ranked results and the abstract.
  arXiv  Detail & Related papers  (2024-02-02T02:41:28Z)
• BERT Goes Off-Topic: Investigating the Domain Transfer Challenge using Genre Classification [0.27195102129095]
  We show that classification tasks still suffer from a performance gap when the underlying distribution of topics changes. We quantify this phenomenon empirically with a large corpus and a large set of topics. We suggest and successfully test a possible remedy: after augmenting the training dataset with topically-controlled synthetic texts, the F1 score improves by up to 50% for some topics.
  arXiv  Detail & Related papers  (2023-11-27T18:53:31Z)
• TransHuman: A Transformer-based Human Representation for Generalizable Neural Human Rendering [52.59454369653773]
  We focus on the task of generalizable neural rendering human which trains conditional Radiance Fields (NeRF) from multi-view videos of different characters. Previous methods have primarily used a SparseConvNet (SPC)-based human representation to process the painted SMPL. We present a brand-new framework named TransHuman, which learns the painted SMPL under the canonical space and captures the global relationships between human parts.
  arXiv  Detail & Related papers  (2023-07-23T10:59:51Z)
• Unsupervised Sentiment Analysis of Plastic Surgery Social Media Posts [91.3755431537592]
  The massive collection of user posts across social media platforms is primarily untapped for artificial intelligence (AI) use cases. Natural language processing (NLP) is a subfield of AI that leverages bodies of documents, known as corpora, to train computers in human-like language understanding. This study demonstrates that the applied results of unsupervised analysis allow a computer to predict either negative, positive, or neutral user sentiment towards plastic surgery.
  arXiv  Detail & Related papers  (2023-07-05T20:16:20Z)
• Shall We Pretrain Autoregressive Language Models with Retrieval? A Comprehensive Study [115.96080028033904]
  We study a scalable pre-trained retrieval-augmented LM (i.e., RETRO) compared with standard GPT and retrieval-augmented GPT. Our findings highlight the promising direction of pretraining autoregressive LMs with retrieval as future foundation models.
  arXiv  Detail & Related papers  (2023-04-13T18:04:19Z)
• Summarization with Graphical Elements [55.5913491389047]
  We propose a new task: summarization with graphical elements. We collect a high quality human labeled dataset to support research into the task.
  arXiv  Detail & Related papers  (2022-04-15T17:16:41Z)
• Paperswithtopic: Topic Identification from Paper Title Only [5.025654873456756]
  We present a dataset of papers paired by title and sub-field from the field of artificial intelligence (AI) We also present results on how to predict a paper's AI sub-field from a given paper title only. For the transformer models, we also present gradient-based, attention visualizations to further explain the model's classification process.
  arXiv  Detail & Related papers  (2021-10-09T06:32:09Z)
• Domain Controlled Title Generation with Human Evaluation [2.5505887482902287]
  A good title allows you to get the attention that your research deserves. For domain-controlled titles, we used the pre-trained text-to-text transformer model and the additional token technique. Title tokens are sampled from a local distribution (which is a subset of global vocabulary) of the domain-specific vocabulary and not global vocabulary.
  arXiv  Detail & Related papers  (2021-03-08T20:55:55Z)
• Progressive Generation of Long Text with Pretrained Language Models [83.62523163717448]
  Large-scale language models (LMs) pretrained on massive corpora of text, such as GPT-2, are powerful open-domain text generators. It is still challenging for such models to generate coherent long passages of text, especially when the models are fine-tuned to the target domain on a small corpus. We propose a simple but effective method of generating text in a progressive manner, inspired by generating images from low to high resolution.
  arXiv  Detail & Related papers  (2020-06-28T21:23:05Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.