arXiv subjects

Karthik Raman

Publications and source records attributed to Karthik Raman.

26 records · Page 2Linked to original sources

arXiv2020

DICT-MLM: Improved Multilingual Pre-Training using Bilingual Dictionaries

Pre-trained multilingual language models such as mBERT have shown immense gains for several natural language processing (NLP) tasks, especially in the zero-shot cross-lingual setting. Most, if not all, of these pre-trained models rely on the masked-language modeling (MLM) objective as the key language learning objective. The principle behind these approaches is that predicting the masked words with the help of the surrounding text helps learn potent contextualized representations. Despite the strong representation learning capability enabled by MLM, we demonstrate an inherent limitation of MLM for multilingual representation learning. In particular, by requiring the model to predict the language-specific token, the MLM objective disincentivizes learning a language-agnostic representation -- which is a key goal of multilingual pre-training. Therefore to encourage better cross-lingual representation learning we propose the DICT-MLM method. DICT-MLM works by incentivizing the model to be able to predict not just the original masked word, but potentially any of its cross-lingual synonyms as well. Our empirical analysis on multiple downstream tasks spanning 30+ languages, demonstrates the efficacy of the proposed approach and its ability to learn better multilingual representations.

cs.CL↗

arXiv2020

DiPair: Fast and Accurate Distillation for Trillion-Scale Text Matching and Pair Modeling

Pre-trained models like BERT (Devlin et al., 2018) have dominated NLP / IR applications such as single sentence classification, text pair classification, and question answering. However, deploying these models in real systems is highly non-trivial due to their exorbitant computational costs. A common remedy to this is knowledge distillation (Hinton et al., 2015), leading to faster inference. However -- as we show here -- existing works are not optimized for dealing with pairs (or tuples) of texts. Consequently, they are either not scalable or demonstrate subpar performance. In this work, we propose DiPair -- a novel framework for distilling fast and accurate models on text pair tasks. Coupled with an end-to-end training strategy, DiPair is both highly scalable and offers improved quality-speed tradeoffs. Empirical studies conducted on both academic and real-world e-commerce benchmarks demonstrate the efficacy of the proposed approach with speedups of over 350x and minimal quality drop relative to the cross-attention teacher BERT model.

cs.CL↗

arXiv2020

Google COVID-19 Search Trends Symptoms Dataset: Anonymization Process Description (version 1.0)

This report describes the aggregation and anonymization process applied to the initial version of COVID-19 Search Trends symptoms dataset (published at https://goo.gle/covid19symptomdataset on September 2, 2020), a publicly available dataset that shows aggregated, anonymized trends in Google searches for symptoms (and some related topics). The anonymization process is designed to protect the daily symptom search activity of every user with $\varepsilon$-differential privacy for $\varepsilon$ = 1.68.

cs.CR↗

arXiv2019

Evaluating the Cross-Lingual Effectiveness of Massively Multilingual Neural Machine Translation

The recently proposed massively multilingual neural machine translation (NMT) system has been shown to be capable of translating over 100 languages to and from English within a single model. Its improved translation performance on low resource languages hints at potential cross-lingual transfer capability for downstream tasks. In this paper, we evaluate the cross-lingual effectiveness of representations from the encoder of a massively multilingual NMT model on 5 downstream classification and sequence labeling tasks covering a diverse set of over 50 languages. We compare against a strong baseline, multilingual BERT (mBERT), in different cross-lingual transfer learning scenarios and show gains in zero-shot transfer in 4 out of these 5 tasks.

cs.CL↗

arXiv2019

Learning Multilingual Word Embeddings Using Image-Text Data

There has been significant interest recently in learning multilingual word embeddings -- in which semantically similar words across languages have similar embeddings. State-of-the-art approaches have relied on expensive labeled data, which is unavailable for low-resource languages, or have involved post-hoc unification of monolingual embeddings. In the present paper, we investigate the efficacy of multilingual embeddings learned from weakly-supervised image-text data. In particular, we propose methods for learning multilingual embeddings using image-text data, by enforcing similarity between the representations of the image and that of the text. Our experiments reveal that even without using any expensive labeled data, a bag-of-words-based embedding model trained on image-text data achieves performance comparable to the state-of-the-art on crosslingual semantic similarity tasks.

cs.CL↗

arXiv2014

Fast-SL: An efficient algorithm to identify synthetic lethal reaction sets in metabolic networks

Synthetic lethal reaction/gene-sets are sets of reactions/genes where only the simultaneous removal of all reactions/genes in the set abolishes growth of an organism. In silico, synthetic lethal sets can be identified by simulating the effect of removal of gene sets from the reconstructed genome-scale metabolic network of an organism. Flux balance analysis (FBA), based on linear programming, has emerged as a powerful tool for the in silico analyses of metabolic networks. To identify all possible synthetic lethal reactions combinations, an exhaustive sampling of all possible combinations is computationally expensive. We surmount the computational complexity of exhaustive search by iteratively restricting the sample space of reaction combinations for search, resulting in a substantial reduction in the running time. We here propose an algorithm, Fast-SL, which provides an efficient way to analyse metabolic networks for higher order lethal reaction sets. Fast-SL offers a substantial speed-up through a massive reduction in the search space for synthetic lethals; in the case of E. coli, Fast-SL reduces the search space for synthetic lethal triplets by over 4000-fold. Fast-SL also compares favourably with SL Finder, an algorithm for identifying synthetic lethal sets, by Suthers et al (2009), which involves the solution of a bi-level Mixed Integer Linear Programming problem. We have implemented the Fast-SL algorithm in MATLAB, building upon COBRA toolbox v2.0.

q-bio.MN↗

arXiv2014

Methods for Ordinal Peer Grading

MOOCs have the potential to revolutionize higher education with their wide outreach and accessibility, but they require instructors to come up with scalable alternates to traditional student evaluation. Peer grading -- having students assess each other -- is a promising approach to tackling the problem of evaluation at scale, since the number of "graders" naturally scales with the number of students. However, students are not trained in grading, which means that one cannot expect the same level of grading skills as in traditional settings. Drawing on broad evidence that ordinal feedback is easier to provide and more reliable than cardinal feedback, it is therefore desirable to allow peer graders to make ordinal statements (e.g. "project X is better than project Y") and not require them to make cardinal statements (e.g. "project X is a B-"). Thus, in this paper we study the problem of automatically inferring student grades from ordinal peer feedback, as opposed to existing methods that require cardinal peer feedback. We formulate the ordinal peer grading problem as a type of rank aggregation problem, and explore several probabilistic models under which to estimate student grades and grader reliability. We study the applicability of these methods using peer grading data collected from a real class -- with instructor and TA grades as a baseline -- and demonstrate the efficacy of ordinal feedback techniques in comparison to existing cardinal peer grading methods. Finally, we compare these peer-grading techniques to traditional evaluation techniques.

cs.LG↗

arXiv2011

Structured Learning of Two-Level Dynamic Rankings

For ambiguous queries, conventional retrieval systems are bound by two conflicting goals. On the one hand, they should diversify and strive to present results for as many query intents as possible. On the other hand, they should provide depth for each intent by displaying more than a single result. Since both diversity and depth cannot be achieved simultaneously in the conventional static retrieval model, we propose a new dynamic ranking approach. Dynamic ranking models allow users to adapt the ranking through interaction, thus overcoming the constraints of presenting a one-size-fits-all static ranking. In particular, we propose a new two-level dynamic ranking model for presenting search results to the user. In this model, a user's interactions with the first-level ranking are used to infer this user's intent, so that second-level rankings can be inserted to provide more results relevant for this intent. Unlike for previous dynamic ranking models, we provide an algorithm to efficiently compute dynamic rankings with provable approximation guarantees for a large family of performance measures. We also propose the first principled algorithm for learning dynamic ranking functions from training data. In addition to the theoretical results, we provide empirical evidence demonstrating the gains in retrieval quality that our method achieves over conventional approaches.

cs.IR↗