# Dialog Context Language Modeling with Recurrent Neural Networks

## TL;DR

This paper introduces RNN-based dialog context language models that incorporate speaker interactions, improving perplexity performance over traditional models by 3.3% on the Switchboard corpus.

## Contribution

It presents a novel RNN-based approach that explicitly models speaker interactions in dialog, advancing contextual language modeling techniques.

## Key findings

- Outperforms single turn RNN models by 3.3% in perplexity
- Demonstrates superior performance over other contextual models
- Effective modeling of dialog interactions improves language modeling

## Abstract

In this work, we propose contextual language models that incorporate dialog level discourse information into language modeling. Previous works on contextual language model treat preceding utterances as a sequence of inputs, without considering dialog interactions. We design recurrent neural network (RNN) based contextual language models that specially track the interactions between speakers in a dialog. Experiment results on Switchboard Dialog Act Corpus show that the proposed model outperforms conventional single turn based RNN language model by 3.3% on perplexity. The proposed models also demonstrate advantageous performance over other competitive contextual language models.