PRPushpendre Rastogi

Pushpendre Rastogi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Pushpendre Rastogi has a total of 9 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Scaling Multi-Domain Dialogue State Tracking via Query Reformulation

    by Pushpendre Rastogi, Arpit Gupta, Tongfei Chen, Lambert Mathias

    We present a novel approach to dialogue state tracking and referring expression resolution tasks. Successful contextual understanding of multi-turn spoken dialogues requires resolving referring expressions across turns and tracking the entities relevant to the conversation across turns. Tracking conversational state is particularly challenging in a multi-domain scenario when there exist multiple spoken language understanding (SLU) sub-systems, and each SLU sub-system operates on its domain-specific meaning representation. While previous approaches have addressed the disparate schema issue by learning candidate transformations of the meaning representation, in this paper, we instead model the reference resolution as a dialogue context-aware user query reformulation task -- the dialog state is serialized to a sequence of natural language tokens representing the conversation. We develop our model for query reformulation using a pointer-generator network and a novel multi-task learning setup. In our experiments, we show a significant improvement in absolute F1 on an internal as well as a, soon to be released, public benchmark respectively.

  • Neural variational entity set expansion for automatically populated knowledge graphs

    by Pushpendre Rastogi, Adam Poliak, Vince Lyzinski, Benjamin Van Durme


  • Open Access

    Problems With Evaluation of Word Embeddings Using Word Similarity Tasks

    by Manaal Faruqui, Yulia Tsvetkov, Pushpendre Rastogi, Chris Dyer

    Lacking standardized extrinsic evaluation methods for vector representations of words, the NLP community has relied heavily on word similarity tasks as a proxy for intrinsic evaluation of word vectors. Word similarity evaluation, which correlates the distance between vectors and human judgments of semantic similarity is attractive, because it is computationally inexpensive and fast. In this paper we present several problems associated with the evaluation of word vectors on word similarity datasets, and summarize existing solutions. Our study suggests that the use of word similarity tasks for evaluation of word vectors is not sustainable and calls for further research on evaluation methods.


  • Open Access

    A Critical Examination of RESCAL for Completion of Knowledge Bases with Transitive Relations

    by Pushpendre Rastogi, Benjamin Van Durme

    Link prediction in large knowledge graphs has received a lot of attention recently because of its importance for inferring missing relations and for completing and improving noisily extracted knowledge graphs. Over the years a number of machine learning researchers have presented various models for predicting the presence of missing relations in a knowledge base. Although all the previous methods are presented with empirical results that show high performance on select datasets, there is almost no previous work on understanding the connection between properties of a knowledge base and the performance of a model. In this paper we analyze the RESCAL method and prove that it can not encode asymmetric transitive relations in knowledge bases.