no code implementations • EAMT 2022 • Nishant Kambhatla, Logan Born, Anoop Sarkar
We propose a novel technique that combines alternative subword tokenizations of a single source-target language pair that allows us to leverage multilingual neural translation training methods.
no code implementations • EMNLP 2020 • Ashkan Alinejad, Anoop Sarkar
Directly translating from speech to text using an end-to-end approach is still challenging for many language pairs due to insufficient data.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +4
1 code implementation • EMNLP 2021 • Ashkan Alinejad, Hassan S. Shavarani, Anoop Sarkar
In simultaneous machine translation, finding an agent with the optimal action sequence of reads and writes that maintain a high level of translation quality while minimizing the average lag in producing target tokens remains an extremely challenging problem.
1 code implementation • 17 Apr 2024 • Nicolas Ong, Hassan Shavarani, Anoop Sarkar
Despite remarkable strides made in the development of entity linking systems in recent years, a comprehensive comparative analysis of these systems using a unified framework is notably absent.
1 code implementation • 23 Oct 2023 • Hassan S. Shavarani, Anoop Sarkar
Entity linking is a prominent thread of research focused on structured data creation by linking spans of text to an ontology or knowledge source.
Ranked #1 on Entity Linking on AIDA/testc (using extra training data)
1 code implementation • ACL 2022 • Nishant Kambhatla, Logan Born, Anoop Sarkar
We propose a novel data-augmentation technique for neural machine translation based on ROT-$k$ ciphertexts.
Ranked #9 on Machine Translation on IWSLT2014 German-English
1 code implementation • EACL 2021 • Hassan S. Shavarani, Anoop Sarkar
Adding linguistic information (syntax or semantics) to neural machine translation (NMT) has mostly focused on using point estimates from pre-trained models.
no code implementations • EACL 2021 • Pooya Moradi, Nishant Kambhatla, Anoop Sarkar
While the attention heatmaps produced by neural machine translation (NMT) models seem insightful, there is little evidence that they reflect a model{'}s true internal reasoning.
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Pooya Moradi, Nishant Kambhatla, Anoop Sarkar
Can we trust that the attention heatmaps produced by a neural machine translation (NMT) model reflect its true internal reasoning?
no code implementations • CONLL 2019 • Zhenqi Zhu, Anoop Sarkar
Supertagging is a sequence prediction task where each word is assigned a piece of complex syntactic structure called a supertag.
1 code implementation • WS 2019 • Pooya Moradi, Nishant Kambhatla, Anoop Sarkar
Attention models have become a crucial component in neural machine translation (NMT).
1 code implementation • 17 Sep 2019 • Jetic Gū, Hassan S. Shavarani, Anoop Sarkar
Neural machine translation (NMT) systems require large amounts of high quality in-domain parallel corpora for training.
1 code implementation • WS 2019 • Logan Born, Kate Kelley, Nishant Kambhatla, Carolyn Chen, Anoop Sarkar
We describe a first attempt at using techniques from computational linguistics to analyze the undeciphered proto-Elamite script.
no code implementations • EMNLP 2018 • Ashkan Alinejad, Maryam Siahbani, Anoop Sarkar
Simultaneous speech translation aims to maintain translation quality while minimizing the delay between reading input and incrementally producing the output.
no code implementations • WS 2018 • Zhelun Wu, Nishant Kambhatla, Anoop Sarkar
Automated filters are commonly used by online services to stop users from sending age-inappropriate, bullying messages, or asking others to expose personal information.
no code implementations • WS 2018 • Golnar Sheikhshabbafghi, Inanc Birol, Anoop Sarkar
Here we report on a pipeline built on Embeddings from Language Models (ELMo) and a deep learning package for natural language processing (AllenNLP).
no code implementations • EMNLP 2018 • Jetic Gū, Hassan S. Shavarani, Anoop Sarkar
The addition of syntax-aware decoding in Neural Machine Translation (NMT) systems requires an effective tree-structured neural network, a syntax-aware attention model and a language generation model that is sensitive to sentence structure.
no code implementations • ACL 2018 • Logan Born, Anoop Sarkar
We show that an epsilon-free, chain-free synchronous context-free grammar (SCFG) can be converted into a weakly equivalent synchronous tree-adjoining grammar (STAG) which is prefix lexicalized.
no code implementations • EACL 2017 • Maryam Siahbani, Anoop Sarkar
Phrase-based and hierarchical phrase-based (Hiero) translation models differ radically in the way reordering is modeled.
no code implementations • 16 Apr 2015 • Mark Schmidt, Reza Babanezhad, Mohamed Osama Ahmed, Aaron Defazio, Ann Clifton, Anoop Sarkar
We apply stochastic average gradient (SAG) algorithms for training conditional random fields (CRFs).