Papers by Anoop Sarkar

16 papers
Compositionality of Complex Graphemes in the Undeciphered Proto-Elamite Script using Image and Text Embedding Models (2021.findings-acl)

Copied to clipboard

Challenge: a language model over sign images produces more interpretable results than a model over text . a new language model is developed to abstract from human annotators .
Approach: They propose a language modeling architecture which operates over sequences of images or over multimodal sequences with associated labels.
Outcome: The proposed language model can interpret signs in the undeciphered proto-Elamite script . it also provides a novel way to abstract away from biases introduced by human annotators.
Prefix Lexicalization of Synchronous CFGs using Synchronous TAG (P18-1)

Copied to clipboard

Challenge: epsilon-free, chain-free synchronous context-free grammars can be converted into weakly equivalent synchronous tree-adjoining grammars (STAGs) this transformation doubles the grammar’s rank and cubes its size, but in practice the size increase is only quadratic.
Approach: They extend Greibach normal form from CFGs to SCFGs and prove new formal properties about SCFG, a formalism with many applications in natural language processing.
Outcome: The proposed grammars achieve asymptotic and empirical speed improvements on a machine translation task.
Unified Examination of Entity Linking in Absence of Candidate Sets (2024.naacl-short)

Copied to clipboard

Challenge: Entity linking systems depend on candidate sets for their performance, but a comprehensive comparative analysis of these systems is lacking.
Approach: They propose a black-box benchmark and a method to evaluate all state-of-the-art entity linking methods.
Outcome: The proposed approach reduces the inference time and memory footprint of some models.
CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation (2022.acl-long)

Copied to clipboard

Challenge: a novel data-augmentation technique for neural machine translation is based on a letter substitution cipher . a bijective ciphered text is in effect invisible to modern NLP techniques because of its invariant distributional features .
Approach: They propose a data-augmentation technique for neural machine translation based on ROT-k ciphertexts.
Outcome: The proposed method outperforms existing methods on several datasets by a significant margin.
Training with Adversaries to Improve Faithfulness of Attention in Neural Machine Translation (2020.aacl-srw)

Copied to clipboard

Challenge: Existing approaches to measure faithfulness of neural machine translation models are based on stress tests and a novel objective that rewards faithful behaviour by the model through probability divergence.
Approach: They propose a measure of faithfulness for neural machine translation models based on stress tests and measuring faithfulness based upon how often the model output changes.
Outcome: The proposed objective increases faithfulness without reducing translation quality and can even improve translation quality in some cases.
Decipherment of Substitution Ciphers with Neural Language Models (D18-1)

Copied to clipboard

Challenge: Existing methods for deciphering homophonic substitution ciphers use pre-trained neural LMs.
Approach: They propose a beam search algorithm that scores the entire candidate plaintext at each step of the decipherment using a neural language model.
Outcome: The proposed beam search algorithm improves on challenging ciphers with smaller beam sizes and better error rates than state-of-the-art methods.
Interrogating the Explanatory Power of Attention in Neural Machine Translation (D19-56)

Copied to clipboard

Challenge: Attention models are often used to justify the model’s decision in generating a token but it has not been rigorously established to what extent attention is a reliable source of information in NMT.
Approach: They propose to use attention models to modify crucial aspects of the trained attention model to produce function and content words in the translation process.
Outcome: The proposed models preserve function and content words in the translation process compared to state-of-the-art models.
Sequence Models for Document Structure Identification in an Undeciphered Script (2022.emnlp-main)

Copied to clipboard

Challenge: a systematic analysis of “header” signs in proto-Elamite provides new evidence for their existence . experts have hypothesized that headers are a sign which qualifies transactions .
Approach: They provide unsupervised neural and statistical sequence modeling techniques to identify “header” signs in proto-Elamite, an undeciphered script from 3100-2900 BCE.
Outcome: The authors provide new evidence for the existence of "header" signs in proto-Elamite . they examine which features predict their presence and identify correlations between features and other document properties .
Decipherment as Regression: Solving Historical Substitution Ciphers by Learning Symbol Recurrence Relations (2023.findings-eacl)

Copied to clipboard

Challenge: Existing methods for solving substitution ciphers use character-level language models to find key . a Transformer-based causal language model can be used to learn recurrences between characters in a ciphered text .
Approach: They propose a Transformer-based causal language model for decipherment that learns recurrences between characters in a ciphertext.
Outcome: The proposed method achieves strong results on synthetic 1:1 and homophonic ciphers . it learns recurrence relations between cipheries and recovers keys in its self-attention .
Measuring and Improving Faithfulness of Attention in Neural Machine Translation (2021.eacl-main)

Copied to clipboard

Challenge: Existing evidence for faithfulness of neural machine translation models is lacking.
Approach: They propose a novel objective that rewards faithful behaviour by the model through probability divergence and a differentiable objective that can increase faithfulness without reducing the translation quality.
Outcome: The proposed objective increases faithfulness without reducing translation quality and can even improve translation quality in some cases.
Effectively pretraining a speech translation decoder with Machine Translation data (2020.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to improve the performance of AST systems are based on pretraining the encoder parameters using an ASR model, but using a pretrained MT decoder is not beneficial or improves the results.
Approach: They propose to use an adversarial regularizer to bring the encoder representations of the ASR and NMT tasks closer even though they are in different modalities.
Outcome: The proposed model can be pre-trained using the Automatic Speech Recognition (ASR) task even in different languages and improves in low resource settings.
SpEL: Structured Prediction for Entity Linking (2023.emnlp-main)

Copied to clipboard

Challenge: Entity linking is a key component of structured data creation by linking spans of text to an ontology or knowledge source.
Approach: They propose to use structured prediction for entity linking to classify each input token as an entity and aggregate the token predictions.
Outcome: The proposed system outperforms the state-of-the-art on the commonly used AIDA benchmark dataset for entity linking to Wikipedia.
Top-down Tree Structured Decoding with Syntactic Connections for Neural Machine Translation and Parsing (D18-1)

Copied to clipboard

Challenge: Neural machine translation (NMT) models are based on sequential decoding or serialisation of structured data into sequence.
Approach: They propose a model that combines sequential encoder with tree-structured decoding augmented with a syntax-aware attention model.
Outcome: The proposed model produces fluent translations with better reordering than previous models.
Prediction Improves Simultaneous Neural Machine Translation (D18-1)

Copied to clipboard

Challenge: Current systems for simultaneous machine translation use an AGENT to control an incremental encoder-decoder model.
Approach: They propose a general-purpose prediction action which predicts future words in the input stream.
Outcome: The proposed agent with prediction has better translation quality and less delay compared to an agent-based system without prediction.
Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation (2021.emnlp-main)

Copied to clipboard

Challenge: Existing approaches to train simultaneous machine translation agents have been used to find the optimal action sequences for translation quality and lag.
Approach: They propose a supervised learning approach that detects minimum reads required for generating target tokens by comparing simultaneous translations against full-sentence translations.
Outcome: The proposed method produces much higher quality translations while minimizing the average lag in simultaneous translation.
Better Neural Machine Translation by Extracting Linguistic Information from BERT (2021.eacl-main)

Copied to clipboard

Challenge: Experimental results show that incorporating linguistic information into neural machine translation models is no more difficult to train than conventional Transformer-based NMT.
Approach: They propose to extract linguistic information from contextual word embeddings instead of point estimates to augment NMT models.
Outcome: The proposed method generalizes better in a variety of training contexts and is no more difficult to train than conventional Transformer-based NMT.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations