Why Do Neural Dialog Systems Generate Short and Meaningless Replies? a Comparison between Dialog and Translation

Wei, Bolin; Lu, Shiqiang; Mou, Lili; Zhou, Hao; Poupart, Pascal; Li, Ge; Jin, Zhi

doi:10.1109/icassp.2019.8682634

Cited by 9 publications

(7 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 Overall architecture of the proposed model Fig. 2 A sample architecture for sequnce2sequence neural transliteration [9] This method has been widely used in different natural language processing tasks, such as machine translation [3,1], question answering [11,15], dialog systems [23], and speech recognition [4]. In machine translation, an input sentence, as a sequence of words, is given to the system, and a sentence, again as a sequence of words, is generated in the output.…”

Section: -1-transliteration With Deep Sequence2sequence Modelmentioning

confidence: 99%

Recognizing Transliterated English Words in Persian Texts

Hoseinmardy¹,

Momtazi²

2020

jist

View full text Add to dashboard Cite

One of the most important problems of text processing systems is the word mismatch problem. This results in limited access to the required information in information retrieval. This problem occurs in analyzing textual data such as news, or low accuracy in text classification and clustering. In this case, if the text-processing engine does not use similar/related words in the same sense, it may not be able to guide you to the appropriate result. Various statistical techniques have been proposed to bridge the vocabulary gap problem; e.g., if two words are used in similar contexts frequently, they have similar/related meanings. Synonym and similar words, however, are only one of the categories of related words that are expected to be captured by statistical approaches. Another category of related words is the pair of an original word in one language and its transliteration from another language. This kind of related words is common in non-English languages. In non-English texts, instead of using the original word from the target language, the writer may borrow the English word and only transliterate it to the target language. Since this kind of writing style is used in limited texts, the frequency of transliterated words is not as high as original words. As a result, available corpus-based techniques are not able to capture their concept. In this article, we propose two different approaches to overcome this problem: (1) using neural network-based transliteration, (2) using available tools that are used for machine translation/transliteration, such as Google Translate and Behnevis. Our experiments on a dataset, which is provided for this purpose, shows that the combination of the two approaches can detect English words with 89.39% accuracy.

show abstract

Section: -1-transliteration With Deep Sequence2sequence Modelmentioning

confidence: 99%

Recognizing Transliterated English Words in Persian Texts

Hoseinmardy¹,

Momtazi²

2020

jist

View full text Add to dashboard Cite

show abstract

“…However, they suffer from the problem of generic utterance generation, e.g., always generating "I don't know" (Serban et al, 2016;Li et al, 2016). One possible explanation (Wei et al, 2019) is the high uncertainty in dialog generation. A plausible response is analogous to a "mode" of a continuous distribution, and the response distribution is thus multimodal.…”

Section: Introductionmentioning

confidence: 99%

Adversarial Learning on the Latent Space for Diverse Dialog Generation

Khan

Sahu

Mou

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

Self Cite

View full text Add to dashboard Cite

Generating relevant responses in a dialog is challenging, and requires not only proper modeling of context in the conversation, but also being able to generate fluent sentences during inference. In this paper, we propose a two-step framework based on generative adversarial nets for generating conditioned responses. Our model first learns a meaningful representation of sentences by autoencoding, and then learns to map an input query to the response representation, which is in turn decoded as a response sentence. Both quantitative and qualitative evaluations show that our model generates more fluent, relevant, and diverse responses than existing state-of-the-art methods. 1

show abstract

“…A less well known issue is the template-like generation of neural NLG systems (Wei et al, 2019). Figure 1 highlights this issue; neural NLG systems (TGen and Slug2Slug) are far less diverse than the training data (E2E Dataset) in their usage of surface forms that express an attribute.…”

Section: Introductionmentioning

confidence: 99%

How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue

Elder¹,

O’Connor

Foster

2020

Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

View full text Add to dashboard Cite

Neural Natural Language Generation (NLG) systems are well known for their unreliability. To overcome this issue, we propose a data augmentation approach which allows us to restrict the output of a network and guarantee reliability. While this restriction means generation will be less diverse than if randomly sampled, we include experiments that demonstrate the tendency of existing neural generation approaches to produce dull and repetitive text, and we argue that reliability is more important than diversity for this task. The system trained using this approach scored 100% in semantic accuracy on the E2E NLG Challenge dataset, the same as a template system.

show abstract

Why Do Neural Dialog Systems Generate Short and Meaningless Replies? a Comparison between Dialog and Translation

Cited by 9 publications

References 12 publications

Recognizing Transliterated English Words in Persian Texts

Recognizing Transliterated English Words in Persian Texts

Adversarial Learning on the Latent Space for Diverse Dialog Generation

How to Make Neural Natural Language Generation as Reliable as Templates in Task-Oriented Dialogue

Contact Info

Product

Resources

About