Ensure the presence of a word/token/noun in Encoder-Decoder text generation deep learning models

Question

I am stuck with a problem where in I want to ensure that specific tokens/words are produced while decoding and generating abstractive-style sentences.

I am working with deep learning models like LSTM and transformer model for generating short sentences(100-200 characters). I want that some words like places or nouns(like brand names) be present in the generated texts.

I am not sure if there has been any research on this, I couldn't really find a paper after an extensive search on it.

TIA, any leads or suggestions are appreciated. :)

Right now, its the basic seq2seq encoder-decoder model. LSTM to encode input, and another LSTM to decode output. — Divish Dayal, Aug 18 '18 at 08:14

score 0 · Answer 1 · answered Jan 08 '19 at 17:15

0

I am not sure but you can try to condition your output based on those specific words. Your trainer can be like a seq2seq decoder but instead of attending to the encoder outputs it can attend to those specific words.

answered Jan 08 '19 at 17:15

Suvam Dubey

21
1
4

Ensure the presence of a word/token/noun in Encoder-Decoder text generation deep learning models

1 Answers1