Mitesh M. Khapra

Also published as: Mitesh Khapra


2021

pdf bib
A Tutorial on Evaluation Metrics used in Natural Language Generation
Mitesh M. Khapra | Ananya B. Sai
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Tutorials

The advent of Deep Learning and the availability of large scale datasets has accelerated research on Natural Language Generation with a focus on newer tasks and better models. With such rapid progress, it is vital to assess the extent of scientific progress made and identify the areas / components that need improvement. To accomplish this in an automatic and reliable manner, the NLP community has actively pursued the development of automatic evaluation metrics. Especially in the last few years, there has been an increasing focus on evaluation metrics, with several criticisms of existing metrics and proposals for several new metrics. This tutorial presents the evolution of automatic evaluation metrics to their current state along with the emerging trends in this field by specifically addressing the following questions : (i) What makes NLG evaluation challenging? (ii) Why do we need automatic evaluation metrics? (iii) What are the existing automatic evaluation metrics and how can they be organised in a coherent taxonomy? (iv) What are the criticisms and shortcomings of existing metrics? (v) What are the possible future directions of research?

2020

pdf bib
Towards Interpreting BERT for Reading Comprehension Based QABERT for Reading Comprehension Based QA
Sahana Ramnath | Preksha Nema | Deep Sahni | Mitesh M. Khapra
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)

BERT and its variants have achieved state-of-the-art performance in various NLP tasks. Since then, various works have been proposed to analyze the linguistic information being captured in BERT. However, the current works do not provide an insight into how BERT is able to achieve near human-level performance on the task of Reading Comprehension based Question Answering. In this work, we attempt to interpret BERT for RCQA. Since BERT layers do not have predefined roles, we define a layer’s role or functionality using Integrated Gradients. Based on the defined roles, we perform a preliminary analysis across all layers. We observed that the initial layers focus on query-passage interaction, whereas later layers focus more on contextual understanding and enhancing the answer prediction. Specifically for quantifier questions (how much / how many), we notice that BERT focuses on confusing words (i.e., on other numerical quantities in the passage) in the later layers, but still manages to predict the answer correctly. The fine-tuning and analysis scripts will be publicly available at https://github.com/iitmnlp/BERT-Analysis-RCQA.

pdf bib
Towards Transparent and Explainable Attention Models
Akash Kumar Mohankumar | Preksha Nema | Sharan Narasimhan | Mitesh M. Khapra | Balaji Vasan Srinivasan | Balaraman Ravindran
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Recent studies on interpretability of attention distributions have led to notions of faithful and plausible explanations for a model’s predictions. Attention distributions can be considered a faithful explanation if a higher attention weight implies a greater impact on the model’s prediction. They can be considered a plausible explanation if they provide a human-understandable justification for the model’s predictions. In this work, we first explain why current attention mechanisms in LSTM based encoders can neither provide a faithful nor a plausible explanation of the model’s predictions. We observe that in LSTM based encoders the hidden representations at different time-steps are very similar to each other (high conicity) and attention weights in these situations do not carry much meaning because even a random permutation of the attention weights does not affect the model’s predictions. Based on experiments on a wide variety of tasks and datasets, we observe attention distributions often attribute the model’s predictions to unimportant words such as punctuation and fail to offer a plausible explanation for the predictions. To make attention mechanisms more faithful and plausible, we propose a modified LSTM cell with a diversity-driven training objective that ensures that the hidden representations learned at different time steps are diverse. We show that the resulting attention distributions offer more transparency as they (i) provide a more precise importance ranking of the hidden states (ii) are better indicative of words important for the model’s predictions (iii) correlate better with gradient-based attribution methods. Human evaluations indicate that the attention distributions learned by our model offer a plausible explanation of the model’s predictions.

pdf bib
IndicNLPSuite : Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian LanguagesIndicNLPSuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages
Divyanshu Kakwani | Anoop Kunchukuttan | Satish Golla | Gokul N.C. | Avik Bhattacharyya | Mitesh M. Khapra | Pratyush Kumar
Findings of the Association for Computational Linguistics: EMNLP 2020

In this paper, we introduce NLP resources for 11 major Indian languages from two major language families. These resources include : (a) large-scale sentence-level monolingual corpora, (b) pre-trained word embeddings, (c) pre-trained language models, and (d) multiple NLU evaluation datasets (IndicGLUE benchmark). The monolingual corpora contains a total of 8.8 billion tokens across all 11 languages and Indian English, primarily sourced from news crawls. The word embeddings are based on FastText, hence suitable for handling morphological complexity of Indian languages. The pre-trained language models are based on the compact ALBERT model. Lastly, we compile the (IndicGLUE benchmark for Indian language NLU. To this end, we create datasets for the following tasks : Article Genre Classification, Headline Prediction, Wikipedia Section-Title Prediction, Cloze-style Multiple choice QA, Winograd NLI and COPA. We also include publicly available datasets for some Indic languages for tasks like Named Entity Recognition, Cross-lingual Sentence Retrieval, Paraphrase detection, etc. Our embeddings are competitive or better than existing pre-trained embeddings on multiple tasks. We hope that the availability of the dataset will accelerate Indic NLP research which has the potential to impact more than a billion people. It can also help the community in evaluating advances in NLP over a more diverse pool of languages. The data and models are available at.IndicGLUE benchmark). The monolingual corpora contains a total of 8.8 billion tokens across all 11 languages and Indian English, primarily sourced from news crawls. The word embeddings are based on FastText, hence suitable for handling morphological complexity of Indian languages. The pre-trained language models are based on the compact ALBERT model. Lastly, we compile the (IndicGLUE benchmark for Indian language NLU. To this end, we create datasets for the following tasks: Article Genre Classification, Headline Prediction, Wikipedia Section-Title Prediction, Cloze-style Multiple choice QA, Winograd NLI and COPA. We also include publicly available datasets for some Indic languages for tasks like Named Entity Recognition, Cross-lingual Sentence Retrieval, Paraphrase detection, etc. Our embeddings are competitive or better than existing pre-trained embeddings on multiple tasks. We hope that the availability of the dataset will accelerate Indic NLP research which has the potential to impact more than a billion people. It can also help the community in evaluating advances in NLP over a more diverse pool of languages. The data and models are available at https://indicnlp.ai4bharat.org.

2019

pdf bib
Let’s Ask Again : Refine Network for Automatic Question Generation
Preksha Nema | Akash Kumar Mohankumar | Mitesh M. Khapra | Balaji Vasan Srinivasan | Balaraman Ravindran
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

In this work, we focus on the task of Automatic Question Generation (AQG) where given a passage and an answer the task is to generate the corresponding question. It is desired that the generated question should be (i) grammatically correct (ii) answerable from the passage and (iii) specific to the given answer. An analysis of existing AQG models shows that they produce questions which do not adhere to one or more of the above-mentioned qualities. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. To alleviate this shortcoming, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, viz., SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16 % on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training.the above-mentioned qualities. In particular, the generated questions look like an incomplete draft of the desired question with a clear scope for refinement. To alleviate this shortcoming, we propose a method which tries to mimic the human process of generating questions by first creating an initial draft and then refining it. More specifically, we propose Refine Network (RefNet) which contains two decoders. The second decoder uses a dual attention network which pays attention to both (i) the original passage and (ii) the question (initial draft) generated by the first decoder. In effect, it refines the question generated by the first decoder, thereby making it more correct and complete. We evaluate RefNet on three datasets, viz., SQuAD, HOTPOT-QA, and DROP, and show that it outperforms existing state-of-the-art methods by 7-16% on all of these datasets. Lastly, we show that we can improve the quality of the second decoder on specific metrics, such as, fluency and answerability by explicitly rewarding revisions that improve on the corresponding metric during training. The code has been made publicly available .

pdf bib
On Knowledge distillation from complex networks for response prediction
Siddhartha Arora | Mitesh M. Khapra | Harish G. Ramaswamy
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)

Recent advances in Question Answering have lead to the development of very complex models which compute rich representations for query and documents by capturing all pairwise interactions between query and document words. This makes these models expensive in space and time, and in practice one has to restrict the length of the documents that can be fed to these models. Such models have also been recently employed for the task of predicting dialog responses from available background documents (e.g., Holl-E dataset). However, here the documents are longer, thereby rendering these complex models infeasible except in select restricted settings. In order to overcome this, we use standard simple models which do not capture all pairwise interactions, but learn to emulate certain characteristics of a complex teacher network. Specifically, we first investigate the conicity of representations learned by a complex model and observe that it is significantly lower than that of simpler models. Based on this insight, we modify the simple architecture to mimic this characteristic. We go further by using knowledge distillation approaches, where the simple model acts as a student and learns to match the output from the complex teacher network. We experiment with the Holl-E dialog data set and show that by mimicking characteristics and matching outputs from a teacher, even a simple network can give improved performance.

2018

pdf bib
Towards Exploiting Background Knowledge for Building Conversation Systems
Nikita Moghe | Siddhartha Arora | Suman Banerjee | Mitesh M. Khapra
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

Existing dialog datasets contain a sequence of utterances and responses without any explicit background knowledge associated with them. This has resulted in the development of models which treat conversation as a sequence-to-sequence generation task (i.e., given a sequence of utterances generate the response sequence). This is not only an overly simplistic view of conversation but it is also emphatically different from the way humans converse by heavily relying on their background knowledge about the topic (as opposed to simply relying on the previous sequence of utterances). For example, it is common for humans to (involuntarily) produce utterances which are copied or suitably modified from background articles they have read about the topic. To facilitate the development of such natural conversation models which mimic the human process of conversing, we create a new dataset containing movie chats wherein each response is explicitly generated by copying and/or modifying sentences from unstructured background knowledge such as plots, comments and reviews about the movie. We establish baseline results on this dataset (90 K utterances from 9 K conversations) using three different models : (i) pure generation based models which ignore the background knowledge (ii) generation based models which learn to copy information from the background knowledge when required and (iii) span prediction based models which predict the appropriate response span in the background knowledge.

pdf bib
Towards a Better Metric for Evaluating Question Generation Systems
Preksha Nema | Mitesh M. Khapra
Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing

There has always been criticism for using n-gram based similarity metrics, such as BLEU, NIST, etc, for evaluating the performance of NLG systems. However, these metrics continue to remain popular and are recently being used for evaluating the performance of systems which automatically generate questions from documents, knowledge graphs, images, etc. Given the rising interest in such automatic question generation (AQG) systems, it is important to objectively examine whether these metrics are suitable for this task. In particular, it is important to verify whether such metrics used for evaluating AQG systems focus on answerability of the generated question by preferring questions which contain all relevant information such as question type (Wh-types), entities, relations, etc. In this work, we show that current automatic evaluation metrics based on n-gram similarity do not always correlate well with human judgments about answerability of a question. To alleviate this problem and as a first step towards better evaluation metrics for AQG, we introduce a scoring function to capture answerability and show that when this scoring function is integrated with existing metrics, they correlate significantly better with human judgments. The scripts and data developed as a part of this work are made publicly available.n-gram based similarity metrics, such as BLEU, NIST, etc, for evaluating the performance of NLG systems. However, these metrics continue to remain popular and are recently being used for evaluating the performance of systems which automatically generate questions from documents, knowledge graphs, images, etc. Given the rising interest in such automatic question generation (AQG) systems, it is important to objectively examine whether these metrics are suitable for this task. In particular, it is important to verify whether such metrics used for evaluating AQG systems focus on answerability of the generated question by preferring questions which contain all relevant information such as question type (Wh-types), entities, relations, etc. In this work, we show that current automatic evaluation metrics based on n-gram similarity do not always correlate well with human judgments about answerability of a question. To alleviate this problem and as a first step towards better evaluation metrics for AQG, we introduce a scoring function to capture answerability and show that when this scoring function is integrated with existing metrics, they correlate significantly better with human judgments. The scripts and data developed as a part of this work are made publicly available.

pdf bib
Leveraging Orthographic Similarity for Multilingual Neural Transliteration
Anoop Kunchukuttan | Mitesh Khapra | Gurneet Singh | Pushpak Bhattacharyya
Transactions of the Association for Computational Linguistics, Volume 6

We address the task of joint training of transliteration models for multiple language pairs (multilingual transliteration). This is an instance of multitask learning, where individual tasks (language pairs) benefit from sharing knowledge with related tasks. We focus on transliteration involving related tasks i.e., languages sharing writing systems and phonetic properties (orthographically similar languages). We propose a modified neural encoder-decoder model that maximizes parameter sharing across language pairs in order to effectively leverage orthographic similarity. We show that multilingual transliteration significantly outperforms bilingual transliteration in different scenarios (average increase of 58 % across a variety of languages we experimented with). We also show that multilingual transliteration models can generalize well to languages / language pairs not encountered during training and hence perform well on the zeroshot transliteration task. We show that further improvements can be achieved by using phonetic feature input.

pdf bib
Generating Descriptions from Structured Data Using a Bifocal Attention Mechanism and Gated Orthogonalization
Preksha Nema | Shreyas Shetty | Parag Jain | Anirban Laha | Karthik Sankaranarayanan | Mitesh M. Khapra
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)

In this work, we focus on the task of generating natural language descriptions from a structured table of facts containing fields (such as nationality, occupation, etc) and values (such as Indian, actor, director, etc). One simple choice is to treat the table as a sequence of fields and values and then use a standard seq2seq model for this task. However, such a model is too generic and does not exploit task specific characteristics. For example, while generating descriptions from a table, a human would attend to information at two levels : (i) the fields (macro level) and (ii) the values within the field (micro level). Further, a human would continue attending to a field for a few timesteps till all the information from that field has been rendered and then never return back to this field (because there is nothing left to say about it). To capture this behavior we use (i) a fused bifocal attention mechanism which exploits and combines this micro and macro level information and (ii) a gated orthogonalization mechanism which tries to ensure that a field is remembered for a few time steps and then forgotten. We experiment with a recently released dataset which contains fact tables about people and their corresponding one line biographical descriptions in English. In addition, we also introduce two similar datasets for French and German. Our experiments show that the proposed model gives 21 % relative improvement over a recently proposed state of the art method and 10 % relative improvement over basic seq2seq models.https://github.com/PrekshaNema25/StructuredData_To_Descriptions\n

pdf bib
A Mixed Hierarchical Attention Based Encoder-Decoder Approach for Standard Table Summarization
Parag Jain | Anirban Laha | Karthik Sankaranarayanan | Preksha Nema | Mitesh M. Khapra | Shreyas Shetty
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)

Structured data summarization involves generation of natural language summaries from structured input data. In this work, we consider summarizing structured data occurring in the form of tables as they are prevalent across a wide variety of domains. We formulate the standard table summarization problem, which deals with tables conforming to a single predefined schema. To this end, we propose a mixed hierarchical attention based encoder-decoder model which is able to leverage the structure in addition to the content of the tables. Our experiments on the publicly available weathergov dataset show around 18 BLEU (around 30 %) improvement over the current state-of-the-art.

pdf bib
DuoRC : Towards Complex Language Understanding with Paraphrased Reading ComprehensionDuoRC: Towards Complex Language Understanding with Paraphrased Reading Comprehension
Amrita Saha | Rahul Aralikatte | Mitesh M. Khapra | Karthik Sankaranarayanan
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

We propose DuoRC, a novel dataset for Reading Comprehension (RC) that motivates several new challenges for neural approaches in language understanding beyond those offered by existing RC datasets. DuoRC contains 186,089 unique question-answer pairs created from a collection of 7680 pairs of movie plots where each pair in the collection reflects two versions of the same movie-one from Wikipedia and the other from IMDb-written by two different authors. We asked crowdsourced workers to create questions from one version of the plot and a different set of workers to extract or synthesize answers from the other version. This unique characteristic of DuoRC where questions and answers are created from different versions of a document narrating the same underlying story, ensures by design, that there is very little lexical overlap between the questions created from one version and the segments containing the answer in the other version. Further, since the two versions have different levels of plot detail, narration style, vocabulary, etc., answering questions from the second version requires deeper language understanding and incorporating external background knowledge. Additionally, the narrative style of passages arising from movie plots (as opposed to typical descriptive passages in existing datasets) exhibits the need to perform complex reasoning over events across multiple sentences. Indeed, we observe that state-of-the-art neural RC models which have achieved near human performance on the SQuAD dataset, even when coupled with traditional NLP techniques to address the challenges presented in DuoRC exhibit very poor performance (F1 score of 37.42 % on DuoRC v / s 86 % on SQuAD dataset).

2017

pdf bib
Diversity driven attention model for query-based abstractive summarization
Preksha Nema | Mitesh M. Khapra | Anirban Laha | Balaraman Ravindran
Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Abstractive summarization aims to generate a shorter version of the document covering all the salient points in a compact and coherent fashion. On the other hand, query-based summarization highlights those points that are relevant in the context of a given query. The encode-attend-decode paradigm has achieved notable success in machine translation, extractive summarization, dialog systems, etc. But it suffers from the drawback of generation of repeated phrases. In this work we propose a model for the query-based summarization task based on the encode-attend-decode paradigm with two key additions (i) a query attention model (in addition to document attention model) which learns to focus on different portions of the query at different time steps (instead of using a static representation for the query) and (ii) a new diversity based attention model which aims to alleviate the problem of repeating phrases in the summary. In order to enable the testing of this model we introduce a new query-based summarization dataset building on debatepedia. Our experiments show that with these two additions the proposed model clearly outperforms vanilla encode-attend-decode models with a gain of 28 % (absolute) in ROUGE-L scores.