Dinesh Raghu


pdf bib
Disentangling Language and Knowledge in Task-Oriented Dialogs
Dinesh Raghu | Nikhil Gupta | Mausam
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

The Knowledge Base (KB) used for real-world applications, such as booking a movie or restaurant reservation, keeps changing over time. End-to-end neural networks trained for these task-oriented dialogs are expected to be immune to any changes in the KB. However, existing approaches breakdown when asked to handle such changes. We propose an encoder-decoder architecture (BoSsNet) with a novel Bag-of-Sequences (BoSs) memory, which facilitates the disentangled learning of the response’s language model and its knowledge incorporation. Consequently, the KB can be modified with new knowledge without a drop in interpretability. We find that BoSsNeT outperforms state-of-the-art models, with considerable improvements (>10%) on bAbI OOV test sets and other human-human datasets. We also systematically modify existing datasets to measure disentanglement and show BoSsNeT to be robust to KB modifications.

pdf bib
Multi-Level Memory for Task Oriented Dialogs
Revanth Gangi Reddy | Danish Contractor | Dinesh Raghu | Sachindra Joshi
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Recent end-to-end task oriented dialog systems use memory architectures to incorporate external knowledge in their dialogs. Current work makes simplifying assumptions about the structure of the knowledge base, such as the use of triples to represent knowledge, and combines dialog utterances (context) as well as knowledge base (KB) results as part of the same memory. This causes an explosion in the memory size, and makes the reasoning over memory harder. In addition, such a memory design forces hierarchical properties of the data to be fit into a triple structure of memory. This requires the memory reader to infer relationships across otherwise connected attributes. In this paper we relax the strong assumptions made by existing architectures and separate memories used for modeling dialog context and KB results. Instead of using triples to store KB results, we introduce a novel multi-level memory architecture consisting of cells for each query and their corresponding results. The multi-level memory first addresses queries, followed by results and finally each key-value pair within a result. We conduct detailed experiments on three publicly available task oriented dialog data sets and we find that our method conclusively outperforms current state-of-the-art models. We report a 15-25% increase in both entity F1 and BLEU scores.


pdf bib
Generating Natural Language Question-Answer Pairs from a Knowledge Graph Using a RNN Based Question Generation Model
Sathish Reddy | Dinesh Raghu | Mitesh M. Khapra | Sachindra Joshi
Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers

In recent years, knowledge graphs such as Freebase that capture facts about entities and relationships between them have been used actively for answering factoid questions. In this paper, we explore the problem of automatically generating question answer pairs from a given knowledge graph. The generated question answer (QA) pairs can be used in several downstream applications. For example, they could be used for training better QA systems. To generate such QA pairs, we first extract a set of keywords from entities and relationships expressed in a triple stored in the knowledge graph. From each such set, we use a subset of keywords to generate a natural language question that has a unique answer. We treat this subset of keywords as a sequence and propose a sequence to sequence model using RNN to generate a natural language question from it. Our RNN based model generates QA pairs with an accuracy of 33.61 percent and performs 110.47 percent (relative) better than a state-of-the-art template based method for generating natural language question from keywords. We also do an extrinsic evaluation by using the generated QA pairs to train a QA system and observe that the F1-score of the QA system improves by 5.5 percent (relative) when using automatically generated QA pairs in addition to manually generated QA pairs available for training.


pdf bib
A statistical approach for Non-Sentential Utterance Resolution for Interactive QA System
Dinesh Raghu | Sathish Indurthi | Jitendra Ajmera | Sachindra Joshi
Proceedings of the 16th Annual Meeting of the Special Interest Group on Discourse and Dialogue


pdf bib
Semi-Supervised Answer Extraction from Discussion Forums
Rose Catherine | Rashmi Gangadharaiah | Karthik Visweswariah | Dinesh Raghu
Proceedings of the Sixth International Joint Conference on Natural Language Processing


pdf bib
Does Similarity Matter? The Case of Answer Extraction from Technical Discussion Forums
Rose Catherine | Amit Singh | Rashmi Gangadharaiah | Dinesh Raghu | Karthik Visweswariah
Proceedings of COLING 2012: Posters