Author name cluster

Mitesh M. Khapra

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

AAAI Conference 2023 Conference Paper

IndicSUPERB: A Speech Processing Universal Performance Benchmark for Indian Languages

Tahir Javed
Kaushal Bhogale
Abhigyan Raman
Pratyush Kumar
Anoop Kunchukuttan
Mitesh M. Khapra

A cornerstone in AI research has been the creation and adoption of standardized training and test datasets to earmark the progress of state-of-the-art models. A particularly successful example is the GLUE dataset for training and evaluating Natural Language Understanding (NLU) models for English. The large body of research around self-supervised BERT-based language models revolved around performance improvements on NLU tasks in GLUE. To evaluate language models in other languages, several language-specific GLUE datasets were created. The area of speech language understanding (SLU) has followed a similar trajectory. The success of large self-supervised models such as wav2vec2 enable creation of speech models with relatively easy to access unlabelled data. These models can then be evaluated on SLU tasks, such as the SUPERB benchmark. In this work, we extend this to Indic languages by releasing the IndicSUPERB benchmark. Specifically, we make the following three contributions. (i) We collect Kathbath containing 1,684 hours of labelled speech data across 12 Indian languages from 1,218 contributors located in 203 districts in India. (ii) Using Kathbath, we create benchmarks across 6 speech tasks: Automatic Speech Recognition, Speaker Verification, Speaker Identification (mono/multi), Language Identification, Query By Example, and Keyword Spotting for 12 languages. (iii) On the released benchmarks, we train and evaluate different self-supervised models alongside the a commonly used baseline FBANK. We show that language-specific fine-tuned models are more accurate than baseline on most of the tasks, including a large gap of 76% for Language Identification task. However, for speaker identification, self-supervised models trained on large datasets demonstrate an advantage. We hope IndicSUPERB contributes to the progress of developing speech language understanding models for Indian languages.

PDF Details DOI

AAAI Conference 2022 Conference Paper

Towards Building ASR Systems for the Next Billion Users

Tahir Javed
Sumanth Doddapaneni
Abhigyan Raman
Kaushal Santosh Bhogale
Gowtham Ramesh
Anoop Kunchukuttan
Pratyush Kumar
Mitesh M. Khapra

Recent methods in speech and language technology pretrain very large models which are fine-tuned for specific tasks. However, the benefits of such large models are often limited to a few resource rich languages of the world. In this work, we make multiple contributions towards building ASR systems for low resource languages from the Indian subcontinent. First, we curate 17, 000 hours of raw speech data for 40 Indian languages from a wide variety of domains including education, news, technology, and finance. Second, using this raw speech data we pretrain several variants of wav2vec style models for 40 Indian languages. Third, we analyze the pretrained models to find key features: codebook vectors of similar sounding phonemes are shared across languages, representations across layers are discriminative of the language family, and attention heads often pay attention within small local windows. Fourth, we fine-tune this model for downstream ASR for 9 languages and obtain state-of-the-art results on 3 public datasets, including on very low-resource languages such as Sinhala and Nepali. Our work establishes that multilingual pretraining is an effective strategy for building ASR systems for the linguistically diverse speakers of the Indian subcontinent.

PDF Details

AAAI Conference 2021 Conference Paper

A Systematic Evaluation of Object Detection Networks for Scientific Plots

Pritha Ganguly
Nitesh S Methani
Mitesh M. Khapra
Pratyush Kumar

Are existing object detection methods adequate for detecting text and visual elements in scientific plots which are arguably different than the objects found in natural images? To answer this question, we train and compare the accuracy of Fast/Faster R-CNN, SSD, YOLO and RetinaNet on the PlotQA dataset with over 220, 000 scientific plots. At the standard IOU setting of 0. 5, most networks perform well with mAP scores greater than 80% in detecting the relatively simple objects in plots. However, the performance drops drastically when evaluated at a stricter IOU of 0. 9 with the best model giving a mAP of 35. 70%. Note that such a stricter evaluation is essential when dealing with scientific plots where even minor localisation errors can lead to large errors in downstream numerical inferences. Given this poor performance, we propose minor modifications to existing models by combining ideas from different object detection networks. While this significantly improves the performance, there are still two main issues: (i) performance on text objects which are essential for reasoning is very poor, and (ii) inference time is unacceptably large considering the simplicity of plots. To solve this open problem, we make a series of contributions: (a) an efficient region proposal method based on Laplacian edge detectors, (b) a feature representation of region proposals that includes neighbouring information, (c) a linking component to join multiple region proposals for detecting longer textual objects, and (d) a custom loss function that combines a smooth `1-loss with an IOU-based loss. Combining these ideas, our final model is very accurate at extreme IOU values achieving a mAP of 93. 44%@0. 9 IOU. Simultaneously, our model is very efficient with an inference time 16x lesser than the current models, including one-stage detectors. Our model also achieves a high accuracy on an extrinsic plot-to-table conversion task with an F1 score of 0. 77. With these contributions, we make a definitive progress in object detection for plots and enable further exploration on automated reasoning of plots.

PDF Details

AAAI Conference 2021 Conference Paper

The Heads Hypothesis: A Unifying Statistical Approach Towards Understanding Multi-Headed Attention in BERT

Madhura Pande
Aakriti Budhraja
Preksha Nema
Pratyush Kumar
Mitesh M. Khapra

Multi-headed attention heads are a mainstay in transformerbased models. Different methods have been proposed to classify the role of each attention head based on the relations between tokens which have high pair-wise attention. These roles include syntactic (tokens with some syntactic relation), local (nearby tokens), block (tokens in the same sentence) and delimiter (the special [CLS], [SEP] tokens). There are two main challenges with existing methods for classification: (a) there are no standard scores across studies or across functional roles, and (b) these scores are often average quantities measured across sentences without capturing statistical significance. In this work, we formalize a simple yet effective score that generalizes to all the roles of attention heads and employs hypothesis testing on this score for robust inference. This provides us the right lens to systematically analyze attention heads and confidently comment on many commonly posed questions on analyzing the BERT model. In particular, we comment on the co-location of multiple functional roles in the same attention head, the distribution of attention heads across layers, and effect of fine-tuning for specific NLP tasks on these functional roles. Code is made publicly available at https: //github. com/iitmnlp/heads-hypothesis

PDF Details

AAAI Conference 2019 Conference Paper

Re-Evaluating ADEM: A Deeper Look at Scoring Dialogue Responses

Ananya B. Sai
Mithun Das Gupta
Mitesh M. Khapra
Mukundhan Srinivasan

Automatically evaluating the quality of dialogue responses for unstructured domains is a challenging problem. ADEM (Lowe et al. 2017) formulated the automatic evaluation of dialogue systems as a learning problem and showed that such a model was able to predict responses which correlate significantly with human judgements, both at utterance and system level. Their system was shown to have beaten word-overlap metrics such as BLEU with large margins. We start with the question of whether an adversary can game the ADEM model. We design a battery of targeted attacks at the neural network based ADEM evaluation system and show that automatic evaluation of dialogue systems still has a long way to go. ADEM can get confused with a variation as simple as reversing the word order in the text! We report experiments on several such adversarial scenarios that draw out counterintuitive scores on the dialogue responses. We take a systematic look at the scoring function proposed by ADEM and connect it to linear system theory to predict the shortcomings evident in the system. We also devise an attack that can fool such a system to rate a response generation system as favorable. Finally, we allude to future research directions of using the adversarial attacks to design a truly automated dialogue evaluation system.

PDF Details

RLDM Conference 2017 Conference Abstract

Attend, Adapt and Transfer: Attentive Deep Architecture for Adaptive Transfer from multiple sources in the same domain

Aravind Srinivas Lakshminarayanan
Janarthanan Rajendran
Mitesh M. Khapra
Prasanna Parthasarathi
Balaraman Ravindran

Transferring knowledge from prior source tasks in solving a new target task can be useful in several learning applications. The application of transfer poses two serious challenges which have not been adequately addressed. First, the agent should be able to avoid negative transfer, which happens when the transfer hampers or slows down the learning instead of helping it. Second, the agent should be able to selectively transfer, which is the ability to select and transfer from different and multiple source tasks for different parts of the state space of the target task. We propose A2T (Attend, Adapt and Transfer), an attentive deep architecture which adapts and transfers from these source tasks. Our model is generic enough to effect transfer of either policies or value functions. Empirical evaluations on different learning algorithms show that A2T is an effective architecture for transfer by being able to avoid negative transfer while transferring selectively from multiple source tasks in the same domain.

PDF Details