Ferhan Türe

Also published as: Ferhan Ture


2023

pdf bib
What the DAAM: Interpreting Stable Diffusion Using Cross Attention
Raphael Tang | Linqing Liu | Akshat Pandey | Zhiying Jiang | Gefei Yang | Karun Kumar | Pontus Stenetorp | Jimmy Lin | Ferhan Ture
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Diffusion models are a milestone in text-to-image generation, but they remain poorly understood, lacking interpretability analyses. In this paper, we perform a text-image attribution analysis on Stable Diffusion, a recently open-sourced model. To produce attribution maps, we upscale and aggregate cross-attention maps in the denoising module, naming our method DAAM. We validate it by testing its segmentation ability on nouns, as well as its generalized attribution quality on all parts of speech, rated by humans. On two generated datasets, we attain a competitive 58.8-64.8 mIoU on noun segmentation and fair to good mean opinion scores (3.4-4.2) on generalized attribution. Then, we apply DAAM to study the role of syntax in the pixel space across head–dependent heat map interaction patterns for ten common dependency relations. We show that, for some relations, the head map consistently subsumes the dependent, while the opposite is true for others. Finally, we study several semantic phenomena, focusing on feature entanglement; we find that the presence of cohyponyms worsens generation quality by 9%, and descriptive adjectives attend too broadly. We are the first to interpret large diffusion models from a visuolinguistic perspective, which enables future research. Our code is at https://github.com/castorini/daam.

2022

pdf bib
SpeechNet: Weakly Supervised, End-to-End Speech Recognition at Industrial Scale
Raphael Tang | Karun Kumar | Gefei Yang | Akshat Pandey | Yajie Mao | Vladislav Belyaev | Madhuri Emmadi | Craig Murray | Ferhan Ture | Jimmy Lin
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track

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, as well as heavyweight computation for inference. Of course, this impedes commercialization since most companies lack vast human and computational resources. In this paper, we explore training and deploying an ASR system in the label-scarce, compute-limited setting. To reduce human labor, we use a third-party ASR system as a weak supervision source, supplemented with labeling functions derived from implicit user feedback. To accelerate inference, we propose to route production-time queries across a pool of CUDA graphs of varying input lengths, the distribution of which best matches the traffic’s. Compared to our third-party ASR, we achieve a relative improvement in word-error rate of 8% and a speedup of 600%. Our system, called SpeechNet, currently serves 12 million queries per day on our voice-enabled smart television. To our knowledge, this is the first time a large-scale, Wav2vec-based deployment has been described in the academic literature.

2018

pdf bib
SyntaViz: Visualizing Voice Queries through a Syntax-Driven Hierarchical Ontology
Md Iftekhar Tanveer | Ferhan Ture
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing: System Demonstrations

This paper describes SyntaViz, a visualization interface specifically designed for analyzing natural-language queries that were created by users of a voice-enabled product. SyntaViz provides a platform for browsing the ontology of user queries from a syntax-driven perspective, providing quick access to high-impact failure points of the existing intent understanding system and evidence for data-driven decisions in the development cycle. A case study on Xfinity X1 (a voice-enabled entertainment platform from Comcast) reveals that SyntaViz helps developers identify multiple action items in a short amount of time without any special training. SyntaViz has been open-sourced for the benefit of the community.

2017

pdf bib
No Need to Pay Attention: Simple Recurrent Neural Networks Work!
Ferhan Ture | Oliver Jojic
Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

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 challenging task, many recent attempts that apply either complex linguistic reasoning or deep neural networks achieve 65%–76% accuracy on benchmark sets. Our approach formulates the task as two machine learning problems: detecting the entities in the question, and classifying the question as one of the relation types in the KB. We train a recurrent neural network to solve each problem. On the SimpleQuestions dataset, our approach yields substantial improvements over previously published results — even neural networks based on much more complex architectures. The simplicity of our approach also has practical advantages, such as efficiency and modularity, that are valuable especially in an industry setting. In fact, we present a preliminary analysis of the performance of our model on real queries from Comcast’s X1 entertainment platform with millions of users every day.

2016

pdf bib
Learning to Translate for Multilingual Question Answering
Ferhan Ture | Elizabeth Boschee
Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing

2014

pdf bib
Learning to Translate: A Query-Specific Combination Approach for Cross-Lingual Information Retrieval
Ferhan Ture | Elizabeth Boschee
Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP)

2013

pdf bib
Towards Efficient Large-Scale Feature-Rich Statistical Machine Translation
Vladimir Eidelman | Ke Wu | Ferhan Ture | Philip Resnik | Jimmy Lin
Proceedings of the Eighth Workshop on Statistical Machine Translation

pdf bib
Mr. MIRA: Open-Source Large-Margin Structured Learning on MapReduce
Vladimir Eidelman | Ke Wu | Ferhan Ture | Philip Resnik | Jimmy Lin
Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics: System Demonstrations

2012

pdf bib
Encouraging Consistent Translation Choices
Ferhan Ture | Douglas W. Oard | Philip Resnik
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Why Not Grab a Free Lunch? Mining Large Corpora for Parallel Sentences to Improve Translation Modeling
Ferhan Ture | Jimmy Lin
Proceedings of the 2012 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

pdf bib
Combining Statistical Translation Techniques for Cross-Language Information Retrieval
Ferhan Ture | Jimmy Lin | Douglas Oard
Proceedings of COLING 2012

2010

pdf bib
cdec: A Decoder, Alignment, and Learning Framework for Finite-State and Context-Free Translation Models
Chris Dyer | Adam Lopez | Juri Ganitkevitch | Jonathan Weese | Ferhan Ture | Phil Blunsom | Hendra Setiawan | Vladimir Eidelman | Philip Resnik
Proceedings of the ACL 2010 System Demonstrations

2006

pdf bib
Learning Morphological Disambiguation Rules for Turkish
Deniz Yuret | Ferhan Türe
Proceedings of the Human Language Technology Conference of the NAACL, Main Conference