arXiv subjects

Rahul Goel

Publications and source records attributed to Rahul Goel.

43 records · Page 3Linked to original sources

arXiv2018

Detecting Offensive Content in Open-domain Conversations using Two Stage Semi-supervision

As open-ended human-chatbot interaction becomes commonplace, sensitive content detection gains importance. In this work, we propose a two stage semi-supervised approach to bootstrap large-scale data for automatic sensitive language detection from publicly available web resources. We explore various data selection methods including 1) using a blacklist to rank online discussion forums by the level of their sensitiveness followed by randomly sampling utterances and 2) training a weakly supervised model in conjunction with the blacklist for scoring sentences from online discussion forums to curate a dataset. Our data collection strategy is flexible and allows the models to detect implicit sensitive content for which manual annotations may be difficult. We train models using publicly available annotated datasets as well as using the proposed large-scale semi-supervised datasets. We evaluate the performance of all the models on Twitter and Toxic Wikipedia comments testsets as well as on a manually annotated spoken language dataset collected during a large scale chatbot competition. Results show that a model trained on this collected data outperforms the baseline models by a large margin on both in-domain and out-of-domain testsets, achieving an F1 score of 95.5% on an out-of-domain testset compared to a score of 75% for models trained on public datasets. We also showcase that large scale two stage semi-supervision generalizes well across multiple classes of sensitivities such as hate speech, racism, sexual and pornographic content, etc. without even providing explicit labels for these classes, leading to an average recall of 95.5% versus the models trained using annotated public datasets which achieve an average recall of 73.2% across seven sensitive classes on out-of-domain testsets.

cs.CL↗

arXiv2018

Online Embedding Compression for Text Classification using Low Rank Matrix Factorization

Deep learning models have become state of the art for natural language processing (NLP) tasks, however deploying these models in production system poses significant memory constraints. Existing compression methods are either lossy or introduce significant latency. We propose a compression method that leverages low rank matrix factorization during training,to compress the word embedding layer which represents the size bottleneck for most NLP models. Our models are trained, compressed and then further re-trained on the downstream task to recover accuracy while maintaining the reduced size. Empirically, we show that the proposed method can achieve 90% compression with minimal impact in accuracy for sentence classification tasks, and outperforms alternative methods like fixed-point quantization or offline word embedding compression. We also analyze the inference time and storage space for our method through FLOP calculations, showing that we can compress DNN models by a configurable ratio and regain accuracy loss without introducing additional latency compared to fixed point quantization. Finally, we introduce a novel learning rate schedule, the Cyclically Annealed Learning Rate (CALR), which we empirically demonstrate to outperform other popular adaptive learning rate algorithms on a sentence classification benchmark.

cs.LG↗

arXiv2018

Parsing Coordination for Spoken Language Understanding

Typical spoken language understanding systems provide narrow semantic parses using a domain-specific ontology. The parses contain intents and slots that are directly consumed by downstream domain applications. In this work we discuss expanding such systems to handle compound entities and intents by introducing a domain-agnostic shallow parser that handles linguistic coordination. We show that our model for parsing coordination learns domain-independent and slot-independent features and is able to segment conjunct boundaries of many different phrasal categories. We also show that using adversarial training can be effective for improving generalization across different slot types for coordination parsing.

cs.CL↗

arXiv2018

Contextual Topic Modeling For Dialog Systems

Accurate prediction of conversation topics can be a valuable signal for creating coherent and engaging dialog systems. In this work, we focus on context-aware topic classification methods for identifying topics in free-form human-chatbot dialogs. We extend previous work on neural topic classification and unsupervised topic keyword detection by incorporating conversational context and dialog act features. On annotated data, we show that incorporating context and dialog acts leads to relative gains in topic classification accuracy by 35% and on unsupervised keyword detection recall by 11% for conversational interactions where topics frequently span multiple utterances. We show that topical metrics such as topical depth is highly correlated with dialog evaluation metrics such as coherence and engagement implying that conversational topic models can predict user satisfaction. Our work for detecting conversation topics and keywords can be used to guide chatbots towards coherent dialog.

cs.CL↗

arXiv2018

Modelling Competitive marketing strategies in Social Networks

In a competitive marketing, there are a large number of players which produce the same product. Each firm aims to diffuse its product information widely so that it's product will become popular among potential buyers. The more popular is a product of a firm, the higher is the revenue for the firm. A model is developed in which two players compete to spread information in the large network. Players choose their initial seed nodes simultaneously and the information is diffused according to Independent Cascade model (ICM). The main aim of the player is to choose the seed nodes such that they will spread its information to as many nodes as possible in a social network. The rate of spreading of information also plays a very important role in information diffusion process. Any node in a social network will get influenced by none or one or more than one information. We also analyzed how much fraction of nodes in different compartment changes by changing the rate of spreading of information. Finally, a game theory model is developed to obtain the Nash equilibrium based on best response function of the players. This model is based on Hotelling's model of electoral competition.

cs.SI↗

arXiv2018

Estimating city-level travel patterns using street imagery: a case study of using Google Street View in Britain

Street imagery is a promising big data source providing current and historical images in more than 100 countries. Previous studies used this data to audit built environment features. Here we explore a novel application, using Google Street View (GSV) to predict travel patterns at the city level. We sampled 34 cities in Great Britain. In each city, we accessed GSV images from 1000 random locations from years overlapping with the 2011 Census and the 2011-2013 Active People Survey (APS). We manually annotated images into seven categories of road users. We developed regression models with the counts of images of road users as predictors. Outcomes included Census-reported commute shares of four modes (walking plus public transport, cycling, motorcycle, and car), and APS-reported past-month participation in walking and cycling. In bivariate analyses, we found high correlations between GSV counts of cyclists (GSV-cyclists) and cycle commute mode share (r=0.92) and past-month cycling (r=0.90). Likewise, GSV-pedestrians was moderately correlated with past-month walking for transport (r=0.46), GSV-motorcycles was moderately correlated with commute share of motorcycles (r=0.44), and GSV-buses was highly correlated with commute share of walking plus public transport (r=0.81). GSV-car was not correlated with car commute mode share (r=-0.12). However, in multivariable regression models, all mode shares were predicted well. Cross-validation analyses showed good prediction performance for all the outcomes except past-month walking. Street imagery is a promising new big data source to predict urban mobility patterns. Further testing across multiple settings is warranted both for cross-sectional and longitudinal assessments.

cs.CY↗

arXiv2016

The Social Dynamics of Language Change in Online Networks

Language change is a complex social phenomenon, revealing pathways of communication and sociocultural influence. But, while language change has long been a topic of study in sociolinguistics, traditional linguistic research methods rely on circumstantial evidence, estimating the direction of change from differences between older and younger speakers. In this paper, we use a data set of several million Twitter users to track language changes in progress. First, we show that language change can be viewed as a form of social influence: we observe complex contagion for phonetic spellings and "netspeak" abbreviations (e.g., lol), but not for older dialect markers from spoken language. Next, we test whether specific types of social network connections are more influential than others, using a parametric Hawkes process model. We find that tie strength plays an important role: densely embedded social ties are significantly better conduits of linguistic influence. Geographic locality appears to play a more limited role: we find relatively little evidence to support the hypothesis that individuals are more influenced by geographically local social ties, even in their usage of geographical dialect markers.

cs.CL↗