Follow the discussion in Section 3.1.2 In this section, we continue the discussion in Section 3.3 and obtain the form used in (25). The architecture of the discriminator is shown in Table 3. Exponential Linear Units [ One of the issue with BLEU is that in the case that a higher order n-gram precision of a sentence is 0, then the BLEU score will be 0, resulting in severely underestimation. This is due to the fact that BLEU is calculated by the geometric mean of precision. Sentences in the COCO dataset have a maximum length of 24 tokens and a vocabulary of 4.6k Training and validation data both consist of 10k sentences.

Modeling human personality is important for several AI challenges, from the engineering of artificial psychotherapists to the design of persona bots. However, the field of computational personality analysis heavily relies on labeled data, which may be expensive, difficult or impossible to get. This problem is amplified when dealing with rare personality types or disorders (e.g., the anti-social psychopathic personality disorder). In this context, we developed a text-based data augmentation approach for human personality (PEDANT). PEDANT doesn't rely on the common type of labeled data but on the generative pre-trained model (GPT) combined with domain expertise. Testing the methodology on three different datasets, provides results that support the quality of the generated data.

Text generation is a crucial task in NLP. Recently, several adversarial generative models have been proposed to improve the exposure bias problem in text generation. Though these models gain great success, they still suffer from the problems of reward sparsity and mode collapse. In order to address these two problems, in this paper, we employ inverse reinforcement learning (IRL) for text generation. Specifically, the IRL framework learns a reward function on training data, and then an optimal policy to maximum the expected total reward. Similar to the adversarial models, the reward and policy function in IRL are optimized alternately. Our method has two advantages: (1) the reward function can produce more dense reward signals. (2) the generation policy, trained by "entropy regularized" policy gradient, encourages to generate more diversified texts. Experiment results demonstrate that our proposed method can generate higher quality texts than the previous methods.

Automatically generating coherent and semantically meaningful text has many applications in machine translation, dialogue systems, image captioning, etc. Recently, by combining with policy gradient, Generative Adversarial Nets(GAN) that use a discriminative model to guide the training of the generative model as a reinforcement learning policy has shown promising results in text generation. However, the scalar guiding signal is only available after the entire text has been generated and lacks intermediate information about text structure during the generative process. As such, it limits its success when the length of the generated text samples is long (more than 20 words). In this paper, we propose a new framework, called LeakGAN, to address the problem for long text generation. We allow the discriminative net to leak its own high-level extracted features to the generative net to further help the guidance. The generator incorporates such informative signals into all generation steps through an additional MANAGER module, which takes the extracted features of current generated words and outputs a latent vector to guide the WORKER module for next-word generation.Our extensive experiments on synthetic data and various real-world tasks with Turing test demonstrate that LeakGAN is highly effective in long text generation and also improves the performance in short text generation scenarios. More importantly, without any supervision, LeakGAN would be able to implicitly learn sentence structures only through the interaction between MANAGER and WORKER.