Papers by Kartikeya Upasani
Generate, Filter, and Rank: Grammaticality Classification for Production-Ready NLG Systems (N19-2)
Copied to clipboard
| Challenge: | Existing datasets for grammatical error correction don’t capture the distribution of errors that data-driven generators are likely to make. |
| Approach: | They propose a framework that allows candidates to be filtered and ranked to select the best response. |
| Outcome: | The proposed framework can be scaled with relatively low effort and achieve high precision with reasonable recall on a weather domain dataset. |
The OSU/Facebook Realizer for SRST 2019: Seq2Seq Inflection and Serialized Tree2Tree Linearization (D19-63)
Copied to clipboard
| Challenge: | Existing linearization methods for shallow surface realization tasks are not available for all languages. |
| Approach: | They propose a system that implements morphological inflection with a baseline linearizer for a shallow surface realization task. |
| Outcome: | The proposed system is competitive across languages, but poor on longer sentences. |
MuDoCo: Corpus for Multidomain Coreference Resolution and Referring Expression Generation (2020.lrec-1)
Copied to clipboard
| Challenge: | a new dataset, MuDoCo, is composed of authored dialogs between a fictional user and a system . the dialogs cross domains and users exhibit complex task switching behavior . |
| Approach: | They propose a new dataset, MuDoCo, composed of authored dialogs between a fictional user and a system . they propose two baseline models for the downstream tasks: coreference resolution and referring expression generation. |
| Outcome: | The proposed dataset contains 8,429 dialogs with an average of 5.36 turns per dialog . the users exhibit complex task switching behavior such as re-initiating a previous task . |
Constrained Decoding for Neural NLG from Compositional Representations in Task-Oriented Dialogue (P19-1)
Copied to clipboard
| Challenge: | Generating fluent natural language responses from structured semantic representations is a critical step in task-oriented conversational systems. |
| Approach: | They propose using tree-structured semantic representations for better discourse-level structuring and sentence-level planning and introduce a challenging dataset using this representation for the weather domain. |
| Outcome: | The proposed model improves discourse-level structuring and sentence-level planning on a weather domain and can be decoded to improve semantic correctness. |