Generating Coherent and Diverse Slogans with Sequence-to-Sequence Transformer

• URL: http://arxiv.org/abs/2102.05924v1
• Date: Thu, 11 Feb 2021 10:25:08 GMT
• Title: Generating Coherent and Diverse Slogans with Sequence-to-Sequence Transformer
• Abstract summary: We propose a sequence-to-sequence transformer model to generate slogans from a brief company description. A naive sequence-to-sequence model fine-tuned for slogan generation is prone to introducing false information. We use delexicalisation to address this problem and improve the generated slogans' quality by a large margin.
• Score: 0.1835211348413763
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Previous work in slogan generation focused on generating novel slogans by utilising templates mined from real slogans. While some such slogans can be catchy, they are often not coherent with the company's focus or style across their marketing communications because the templates are mined from other companies' slogans. We propose a sequence-to-sequence transformer model to generate slogans from a brief company description. A naive sequence-to-sequence model fine-tuned for slogan generation is prone to introducing false information, especially unrelated company names appearing in the training data. We use delexicalisation to address this problem and improve the generated slogans' quality by a large margin. Furthermore, we apply two simple but effective approaches to generate more diverse slogans. Firstly, we train a slogan generator conditioned on the industry. During inference time, by changing the industry, we can obtain different "flavours" of slogans. Secondly, instead of using only the company description as the input sequence, we sample random paragraphs from the company's website. Surprisingly, the model can generate meaningful slogans, even if the input sequence does not resemble a company description. We validate the effectiveness of the proposed method with both quantitative evaluation and qualitative evaluation. Our best model achieved a ROUGE-1/-2/-L F1 score of 53.13/33.30/46.49. Besides, human evaluators assigned the generated slogans an average score of 3.39 on a scale of 1-5, indicating the system can generate plausible slogans with a quality close to human-written ones (average score 3.55).

Related papers

• Recontextualizing Famous Quotes for Brand Slogan Generation [9.48100252812595]
  We argue that effective slogans should balance novelty with familiarity.<n>We propose a new paradigm that recontextualizes persona-related famous quotes for slogan generation.
  arXiv  Detail & Related papers  (2026-01-12T04:56:48Z)
• BOOST: Harnessing Black-Box Control to Boost Commonsense in LMs' Generation [60.77990074569754]
  We present a computation-efficient framework that steers a frozen Pre-Trained Language Model towards more commonsensical generation. Specifically, we first construct a reference-free evaluator that assigns a sentence with a commonsensical score. We then use the scorer as the oracle for commonsense knowledge, and extend the controllable generation method called NADO to train an auxiliary head.
  arXiv  Detail & Related papers  (2023-10-25T23:32:12Z)
• Effective Slogan Generation with Noise Perturbation [2.80888070977859]
  We introduce a novel apporach that leverages pre-trained transformer T5 model with noise metrics on newly proposed 1:N matching pair dataset. We evaluate generated slogans based on ROUGE1, ROUGEL and Cosine Similarity and also assess them with human subjects in terms of slogan's distinctiveness, coherence, and fluency.
  arXiv  Detail & Related papers  (2023-10-06T04:48:48Z)
• A Unified Framework for Pun Generation with Humor Principles [31.70470387786539]
  We propose a unified framework to generate both homophonic and homographic puns. We incorporate three linguistic attributes of puns to the language models: ambiguity, distinctiveness, and surprise.
  arXiv  Detail & Related papers  (2022-10-24T09:20:45Z)
• Pruned Graph Neural Network for Short Story Ordering [0.7087237546722617]
  Organizing sentences into an order that maximizes coherence is known as sentence ordering. We propose a new method for constructing sentence-entity graphs of short stories to create the edges between sentences. We also observe that replacing pronouns with their referring entities effectively encodes sentences in sentence-entity graphs.
  arXiv  Detail & Related papers  (2022-03-13T22:25:17Z)
• Attend and Select: A Segment Attention based Selection Mechanism for Microblog Hashtag Generation [69.73215951112452]
  A hashtag is formed by tokens or phrases that may originate from various fragmentary segments of the original text. We propose an end-to-end Transformer-based generation model which consists of three phases: encoding, segments-selection, and decoding. We introduce two large-scale hashtag generation datasets, which are newly collected from Chinese Weibo and English Twitter.
  arXiv  Detail & Related papers  (2021-06-06T15:13:58Z)
• Neural Syntactic Preordering for Controlled Paraphrase Generation [57.5316011554622]
  Our work uses syntactic transformations to softly "reorder'' the source sentence and guide our neural paraphrasing model. First, given an input sentence, we derive a set of feasible syntactic rearrangements using an encoder-decoder model. Next, we use each proposed rearrangement to produce a sequence of position embeddings, which encourages our final encoder-decoder paraphrase model to attend to the source words in a particular order.
  arXiv  Detail & Related papers  (2020-05-05T09:02:25Z)
• Diverse, Controllable, and Keyphrase-Aware: A Corpus and Method for News Multi-Headline Generation [98.98411895250774]
  We propose generating multiple headlines with keyphrases of user interests. The proposed method achieves state-of-the-art results in terms of quality and diversity.
  arXiv  Detail & Related papers  (2020-04-08T08:30:05Z)
• Hooks in the Headline: Learning to Generate Headlines with Controlled Styles [69.30101340243375]
  We propose a new task, Stylistic Headline Generation (SHG), to enrich the headlines with three style options. TitleStylist generates style-specific headlines by combining the summarization and reconstruction tasks into a multitasking framework. The attraction score of our model generated headlines surpasses that of the state-of-the-art summarization model by 9.68%, and even outperforms human-written references.
  arXiv  Detail & Related papers  (2020-04-04T17:24:47Z)
• AvgOut: A Simple Output-Probability Measure to Eliminate Dull Responses [97.50616524350123]
  We build dialogue models that are dynamically aware of what utterances or tokens are dull without any feature-engineering. The first model, MinAvgOut, directly maximizes the diversity score through the output distributions of each batch. The second model, Label Fine-Tuning (LFT), prepends to the source sequence a label continuously scaled by the diversity score to control the diversity level. The third model, RL, adopts Reinforcement Learning and treats the diversity score as a reward signal.
  arXiv  Detail & Related papers  (2020-01-15T18:32:06Z)

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.