IIT (BHU) Varanasi at MSR-SRST 2018: A Language Model Based Approach for Natural Language Generation
This work addresses natural language generation for shallow surface realization, presenting an incremental improvement by combining existing methods for a specific shared task.
The paper tackled the problem of converting unordered, lemmatized Universal Dependencies structures into correct sentences by dividing it into word reinflection and word order prediction, using an LSTM encoder-decoder for reinflection and a language model for ordering, achieving competitive results in the SRST'18 shared task.
This paper describes our submission system for the Shallow Track of Surface Realization Shared Task 2018 (SRST'18). The task was to convert genuine UD structures, from which word order information had been removed and the tokens had been lemmatized, into their correct sentential form. We divide the problem statement into two parts, word reinflection and correct word order prediction. For the first sub-problem, we use a Long Short Term Memory based Encoder-Decoder approach. For the second sub-problem, we present a Language Model (LM) based approach. We apply two different sub-approaches in the LM Based approach and the combined result of these two approaches is considered as the final output of the system.