Search Results - "Ture, Ferhan"

Searching to translate and translating to search: When information retrieval meets machine translation by Ture, Ferhan

“…With the adoption of web services in daily life, people have access to tremendous amounts of information, beyond any human's reading and comprehension…”
Get full text

"Ask Me Anything": How Comcast Uses LLMs to Assist Agents in Real Time by Rome, Scott, Chen, Tianwen, Tang, Raphael, Zhou, Luwei, Ture, Ferhan

“…Customer service is how companies interface with their customers. It can contribute heavily towards the overall customer satisfaction. However, high-quality…”
Get full text

What Do Llamas Really Think? Revealing Preference Biases in Language Model Representations by Tang, Raphael, Zhang, Xinyu, Lin, Jimmy, Ture, Ferhan

“…Do large language models (LLMs) exhibit sociodemographic biases, even when they decline to respond? To bypass their refusal to "speak," we study this research…”
Get full text

Found in the Middle: Permutation Self-Consistency Improves Listwise Ranking in Large Language Models by Tang, Raphael, Zhang, Xinyu, Ma, Xueguang, Lin, Jimmy, Ture, Ferhan

“…Large language models (LLMs) exhibit positional bias in how they use context, which especially complicates listwise ranking. To address this, we propose…”
Get full text

LLM Stability: A detailed analysis with some surprises by Atil, Berk, Chittams, Alexa, Fu, Liseng, Ture, Ferhan, Xu, Lixinyu, Baldwin, Breck

“…LLM (large language model) practitioners commonly notice that outputs can vary for the same inputs, but we have been unable to find work that evaluates LLM…”
Get full text

Words Worth a Thousand Pictures: Measuring and Understanding Perceptual Variability in Text-to-Image Generation by Tang, Raphael, Zhang, Xinyu, Xu, Lixinyu, Lu, Yao, Li, Wenyan, Stenetorp, Pontus, Lin, Jimmy, Ture, Ferhan

“…Diffusion models are the state of the art in text-to-image generation, but their perceptual variability remains understudied. In this paper, we examine how…”
Get full text

Learning to Translate for Multilingual Question Answering by Ture, Ferhan, Boschee, Elizabeth

“…In multilingual question answering, either the question needs to be translated into the document language, or vice versa. In addition to direction, there are…”
Get full text

No Need to Pay Attention: Simple Recurrent Neural Networks Work! (for Answering "Simple" Questions) by Ture, Ferhan, Jojic, Oliver

“…First-order factoid question answering assumes that the question can be answered by a single fact in a knowledge base (KB). While this does not seem like a…”
Get full text

SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale by Tang, Raphael, Kumar, Karun, Yang, Gefei, Pandey, Akshat, Mao, Yajie, Belyaev, Vladislav, Emmadi, Madhuri, Murray, Craig, Ture, Ferhan, Lin, Jimmy

“…End-to-end automatic speech recognition systems represent the state of the art, but they rely on thousands of hours of manually annotated speech for training,…”
Get full text

What the DAAM: Interpreting Stable Diffusion Using Cross Attention by Tang, Raphael, Liu, Linqing, Pandey, Akshat, Jiang, Zhiying, Yang, Gefei, Kumar, Karun, Stenetorp, Pontus, Lin, Jimmy, Ture, Ferhan

“…Large-scale diffusion neural networks represent a substantial milestone in text-to-image generation, but they remain poorly understood, lacking…”
Get full text

Multi-Perspective Relevance Matching with Hierarchical ConvNets for Social Media Search by Rao, Jinfeng, Yang, Wei, Zhang, Yuhao, Ture, Ferhan, Lin, Jimmy

“…Despite substantial interest in applications of neural networks to information retrieval, neural ranking models have only been applied to standard ad hoc…”
Get full text

Talking to Your TV: Context-Aware Voice Search with Hierarchical Recurrent Neural Networks by Rao, Jinfeng, Ture, Ferhan, He, Hua, Jojic, Oliver, Lin, Jimmy

“…We tackle the novel problem of navigational voice queries posed against an entertainment system, where viewers interact with a voice-enabled remote controller…”
Get full text

Streaming Voice Query Recognition using Causal Convolutional Recurrent Neural Networks by Tang, Raphael, Yang, Gefei, Wei, Hong, Mao, Yajie, Ture, Ferhan, Lin, Jimmy

“…Voice-enabled commercial products are ubiquitous, typically enabled by lightweight on-device keyword spotting (KWS) and full automatic speech recognition (ASR)…”
Get full text

Integrating Lexical and Temporal Signals in Neural Ranking Models for Searching Social Media Streams by Rao, Jinfeng, He, Hua, Zhang, Haotian, Ture, Ferhan, Sequiera, Royal, Mohammed, Salman, Lin, Jimmy

“…Time is an important relevance signal when searching streams of social media posts. The distribution of document timestamps from the results of an initial…”
Get full text