Taming Repetition in Dialogue Generation
- URL: http://arxiv.org/abs/2112.08657v1
- Date: Thu, 16 Dec 2021 06:25:46 GMT
- Title: Taming Repetition in Dialogue Generation
- Authors: Yadong Xi, Jiashu Pu, Xiaoxi Mao
- Abstract summary: Inappropriate repetition of words can significantly degrade the quality of the generated texts.
We design a context-aware classifier to explicitly decide when to allow repetition and when to employ penalized sampling.
Our method can generate higher quality and more authentic dialogues.
- Score: 1.851321027703742
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: The wave of pre-training language models has been continuously improving the
quality of the machine-generated conversations, however, some of the generated
responses still suffer from excessive repetition, sometimes repeating words
from utterance, sometimes repeating words within self-generated responses, or
both. Inappropriate repetition of words can significantly degrade the quality
of the generated texts. Penalized sampling is one popular solution, reducing
the sampling probability of existing words during inference, however, it is
highly vulnerable to the inappropriate setting of the static weight. Setting it
too high can yield strange and unrealistic sentences while setting it too low
makes the task of suppressing repetition trivial. To remedy the shortcomings of
the above methods, we design a context-aware classifier to explicitly decide
when to allow repetition and when to employ penalized sampling. Such a
classifier can be easily integrated with existing decoding methods, reducing
repetitions where appropriate while preserving the diversity of the text.
Experimental results demonstrate that our method can generate higher quality
and more authentic dialogues.
Related papers
- Detecting, Explaining, and Mitigating Memorization in Diffusion Models [49.438362005962375]
We introduce a straightforward yet effective method for detecting memorized prompts by inspecting the magnitude of text-conditional predictions.
Our proposed method seamlessly integrates without disrupting sampling algorithms, and delivers high accuracy even at the first generation step.
Building on our detection strategy, we unveil an explainable approach that shows the contribution of individual words or tokens to memorization.
arXiv Detail & Related papers (2024-07-31T16:13:29Z) - Mitigating the Learning Bias towards Repetition by Self-Contrastive
Training for Open-Ended Generation [92.42032403795879]
We show that pretrained language models (LMs) such as GPT2 still tend to generate repetitive texts.
We attribute their overestimation of token-level repetition probabilities to the learning bias.
We find that LMs use longer-range dependencies to predict repetitive tokens than non-repetitive ones, which may be the cause of sentence-level repetition loops.
arXiv Detail & Related papers (2023-07-04T07:53:55Z) - Learning with Rejection for Abstractive Text Summarization [42.15551472507393]
We propose a training objective for abstractive summarization based on rejection learning.
We show that our method considerably improves the factuality of generated summaries in automatic and human evaluations.
arXiv Detail & Related papers (2023-02-16T19:07:08Z) - Generating Repetitions with Appropriate Repeated Words [30.10429353715689]
Repetitions are essential in communication to build trust with others.
To the best of our knowledge, this is the first neural approach to address repetition generation.
We propose Weighted Label Smoothing, a smoothing method for explicitly learning which words to repeat during fine-tuning, and a repetition scoring method that can output more appropriate repetitions during decoding.
arXiv Detail & Related papers (2022-07-03T01:21:49Z) - Learning to Break the Loop: Analyzing and Mitigating Repetitions for
Neural Text Generation [41.3948101212288]
We study the relationship between the probabilities of the repetitive tokens and their previous repetitions in the context.
We propose a training method where the model learns to penalize probabilities of sentence-level repetitions from pseudo repetitive data.
arXiv Detail & Related papers (2022-06-06T05:51:12Z) - Towards Robust Online Dialogue Response Generation [62.99904593650087]
We argue that this can be caused by a discrepancy between training and real-world testing.
We propose a hierarchical sampling-based method consisting of both utterance-level sampling and semi-utterance-level sampling.
arXiv Detail & Related papers (2022-03-07T06:51:41Z) - Speaker Embedding-aware Neural Diarization for Flexible Number of
Speakers with Textual Information [55.75018546938499]
We propose the speaker embedding-aware neural diarization (SEND) method, which predicts the power set encoded labels.
Our method achieves lower diarization error rate than the target-speaker voice activity detection.
arXiv Detail & Related papers (2021-11-28T12:51:04Z) - Self-Normalized Importance Sampling for Neural Language Modeling [97.96857871187052]
In this work, we propose self-normalized importance sampling. Compared to our previous work, the criteria considered in this work are self-normalized and there is no need to further conduct a correction step.
We show that our proposed self-normalized importance sampling is competitive in both research-oriented and production-oriented automatic speech recognition tasks.
arXiv Detail & Related papers (2021-11-11T16:57:53Z) - Rewriting Meaningful Sentences via Conditional BERT Sampling and an
application on fooling text classifiers [11.49508308643065]
adversarial attack methods that are designed to deceive a text classifier change the text classifier's prediction by modifying a few words or characters.
Few try to attack classifiers by rewriting a whole sentence, due to the difficulties inherent in sentence-level rephrasing as well as the problem of setting the criteria for legitimate rewriting.
In this paper, we explore the problem of creating adversarial examples with sentence-level rewriting.
We propose a new criteria for modification, called a sentence-level threaten model. This criteria allows for both word- and sentence-level changes, and can be adjusted independently in two dimensions: semantic similarity and
arXiv Detail & Related papers (2020-10-22T17:03:13Z) - 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)
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.