no code implementations • 15 Apr 2024 • Zelin Wu, Gan Song, Christopher Li, Pat Rondon, Zhong Meng, Xavier Velez, Weiran Wang, Diamantino Caseiro, Golan Pundak, Tsendsuren Munkhdalai, Angad Chandorkar, Rohit Prabhavalkar
Contextual biasing enables speech recognizers to transcribe important phrases in the speaker's context, such as contact names, even if they are rare in, or absent from, the training data.
2 code implementations • 10 Apr 2024 • Tsendsuren Munkhdalai, Manaal Faruqui, Siddharth Gopal
This work introduces an efficient method to scale Transformer-based Large Language Models (LLMs) to infinitely long inputs with bounded memory and computation.
no code implementations • 25 Mar 2024 • Tsendsuren Munkhdalai, Youzheng Chen, Khe Chai Sim, Fadi Biadsy, Tara Sainath, Pedro Moreno Mengibar
However, their per-task parameter overhead is considered still high when the number of downstream tasks to adapt for is large.
no code implementations • 29 Sep 2023 • Weiran Wang, Zelin Wu, Diamantino Caseiro, Tsendsuren Munkhdalai, Khe Chai Sim, Pat Rondon, Golan Pundak, Gan Song, Rohit Prabhavalkar, Zhong Meng, Ding Zhao, Tara Sainath, Pedro Moreno Mengibar
Contextual biasing refers to the problem of biasing the automatic speech recognition (ASR) systems towards rare entities that are relevant to the specific user or application scenarios.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 16 Sep 2023 • Shefali Garg, Zhouyuan Huo, Khe Chai Sim, Suzan Schwartz, Mason Chua, Alëna Aksënova, Tsendsuren Munkhdalai, Levi King, Darryl Wright, Zion Mengesha, Dongseong Hwang, Tara Sainath, Françoise Beaufays, Pedro Moreno Mengibar
By combining the classifier output with coarse geographic information, we can select a subset of utterances from a large corpus of untranscribed short-form queries for semi-supervised learning at scale.
no code implementations • EMNLP 2021 • Trapit Bansal, Karthick Gunasekaran, Tong Wang, Tsendsuren Munkhdalai, Andrew McCallum
Meta-learning considers the problem of learning an efficient learning process that can leverage its past experience to accurately solve new tasks.
no code implementations • 5 Oct 2021 • Tsendsuren Munkhdalai, Khe Chai Sim, Angad Chandorkar, Fan Gao, Mason Chua, Trevor Strohman, Françoise Beaufays
Fast contextual adaptation has shown to be effective in improving Automatic Speech Recognition (ASR) of rare words and when combined with an on-device personalized training, it can yield an even better recognition result.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +2
1 code implementation • ICLR 2021 • Imanol Schlag, Tsendsuren Munkhdalai, Jürgen Schmidhuber
Humans can quickly associate stimuli to solve problems in novel contexts.
Ranked #1 on Question Answering on catbAbI LM-mode
1 code implementation • EMNLP 2020 • Trapit Bansal, Rishikesh Jha, Tsendsuren Munkhdalai, Andrew McCallum
We meta-train a transformer model on this distribution of tasks using a recent meta-learning framework.
no code implementations • 3 Sep 2020 • Tsendsuren Munkhdalai
We augment a deep neural network with a layer-specific fast-weight memory.
1 code implementation • 7 May 2020 • Lkhagvadorj Munkhdalai, Tsendsuren Munkhdalai, Keun Ho Ryu
Therefore, LoAIR is a step towards bridging the gap between econometrics, statistics, and machine learning by improving the predictive ability of linear regression without depreciating its interpretability.
1 code implementation • EMNLP 2020 • Tu Vu, Tong Wang, Tsendsuren Munkhdalai, Alessandro Sordoni, Adam Trischler, Andrew Mattarella-Micke, Subhransu Maji, Mohit Iyyer
We also develop task embeddings that can be used to predict the most transferable source tasks for a given target task, and we validate their effectiveness in experiments controlled for source and target data size.
1 code implementation • NeurIPS 2019 • Tsendsuren Munkhdalai, Alessandro Sordoni, Tong Wang, Adam Trischler
We augment recurrent neural networks with an external memory mechanism that builds upon recent progress in metalearning.
no code implementations • ICLR 2019 • Rajarshi Das, Tsendsuren Munkhdalai, Xingdi Yuan, Adam Trischler, Andrew McCallum
We harness and extend a recently proposed machine reading comprehension (MRC) model to query for entity states, since these states are generally communicated in spans of text and MRC models perform well in extracting entity-centric spans.
Ranked #3 on Procedural Text Understanding on ProPara
no code implementations • 12 Jul 2018 • Tsendsuren Munkhdalai, Adam Trischler
We unify recent neural approaches to one-shot learning with older ideas of associative memory in a model for metalearning.
no code implementations • NAACL 2018 • Tu Vu, Baotian Hu, Tsendsuren Munkhdalai, Hong Yu
Sentence simplification aims to simplify the content and structure of complex sentences, and thus make them easier to interpret for human readers, and easier to process for downstream NLP applications.
Ranked #1 on Text Simplification on PWKP / WikiSmall
no code implementations • ICML 2018 • Tsendsuren Munkhdalai, Xingdi Yuan, Soroush Mehri, Adam Trischler
We describe a mechanism by which artificial neural networks can learn rapid adaptation - the ability to adapt on the fly, with little data, to new tasks - that we call conditionally shifted neurons.
1 code implementation • ICML 2017 • Tsendsuren Munkhdalai, Hong Yu
Neural networks have been successfully applied in applications with a large amount of labeled data.
no code implementations • EMNLP 2018 • John P. Lalor, Hao Wu, Tsendsuren Munkhdalai, Hong Yu
We examine the impact of a test set question's difficulty to determine if there is a relationship between difficulty and performance.
no code implementations • 20 Oct 2016 • Tsendsuren Munkhdalai, Hong Yu
Hypothesis testing is an important cognitive process that supports human reasoning.
1 code implementation • EACL 2017 • Tsendsuren Munkhdalai, Hong Yu
NTI constructs a full n-ary tree by processing the input text with its node function in a bottom-up fashion.
Ranked #46 on Natural Language Inference on SNLI
3 code implementations • EACL 2017 • Tsendsuren Munkhdalai, Hong Yu
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders.
Ranked #18 on Question Answering on WikiQA