Search Results for author:
Found 129 papers, 37 papers with code
Creation of Corpus and Analysis in Code-Mixed Kannada-English Social Media Data for POS Tagging
There has been work done on code-mixed social media corpus but not on POS tagging of Kannada-English code-mixed data.
“Kanglish alli names!” Named Entity Recognition for Kannada-English Code-Mixed Social Media Data
Code-mixing (CM) is a frequently observed phenomenon on social media platforms in multilingual societies such as India.
LTRC @MuP 2022: Multi-Perspective Scientific Document Summarization Using Pre-trained Generation Models
The MuP-2022 shared task focuses on multiperspective scientific document summarization.
Improving Passage Re-Ranking with Word N-Gram Aware Coattention Encoder
In this paper, we propose two improvements to coattention mechanism in the context of passage ranking (re-ranking).
The Effect of Pretraining on Extractive Summarization for Scientific Documents
Large pretrained models have seen enormous success in extractive summarization tasks.
Enhancing Aspect Extraction for Hindi
We provide rigorous guidelines and a replicable methodology for this task.
Incorporating Sub-Word Level Information in Language Invariant Neural Event Detection
We compare the performance of our language invariant model to the current state-of-the-art in English, Spanish, Italian and French.
Event Centric Entity Linking for Hindi News Articles: A Knowledge Graph Based Approach
We describe the development of a knowledge graph from an event annotated corpus by presenting a pipeline that identifies and extracts the relations between entities and events from Hindi news articles.
Kunji : A Resource Management System for Higher Productivity in Computer Aided Translation Tools
Similarly, translators working on Computer Aided Translation workbenches, also require help from various kinds of resources - glossaries, terminologies, concordances and translation memory in the workbenches in order to increase their productivity.
The WEAVE Corpus: Annotating Synthetic Chemical Procedures in Patents with Chemical Named Entities
Such a design process calls for analyzing many existing synthetic chemical reactions and planning the synthesis of novel chemicals.
Topic Shift Detection for Mixed Initiative Response
In this paper, we present a model which uses a fine-tuned XLNet-base to classify the utterances pertaining to the major topic of conversation and those which are not, with a precision of 84%.
HashSet - A Dataset For Hashtag Segmentation
HashSet dataset is sampled from a different set of tweets when compared to existing datasets and provides an alternate distribution of hashtags to build and validate hashtag segmentation models.
TeSum: Human-Generated Abstractive Summarization Corpus for Telugu
But with this work, we show that even with a crowd sourced summary generation approach, quality can be controlled by aggressive expert informed filtering and sampling-based human evaluation.
Towards Fine-grained Classification of Climate Change related Social Media Text
We benchmark both the datasets for climate change stance detection and fine-grained classification using state-of-the-art methods in text classification.
SyMCoM - Syntactic Measure of Code Mixing A Study Of English-Hindi Code-Mixing
Code mixing is the linguistic phenomenon where bilingual speakers tend to switch between two or more languages in conversations.
A3-108 Machine Translation System for Similar Language Translation Shared Task 2020
In this paper, we describe our submissions for Similar Language Translation Shared Task 2020.
CoMeT: Towards Code-Mixed Translation Using Parallel Monolingual Sentences
Code-mixed languages are very popular in multilingual societies around the world, yet the resources lag behind to enable robust systems on such languages.
Translate and Classify: Improving Sequence Level Classification for English-Hindi Code-Mixed Data
To translate English-Hindi code-mixed data to English, we use mBART, a pre-trained multilingual sequence-to-sequence model that has shown competitive performance on various low-resource machine translation pairs and has also shown performance gains in languages that were not in its pre-training corpus.
SimpleNER Sentence Simplification System for GEM 2021
This paper describes SimpleNER, a model developed for the sentence simplification task at GEM-2021.
A3-108 Machine Translation System for LoResMT Shared Task @MT Summit 2021 Conference
Also, we reorder English to match Marathi syntax to further train another set of baseline and data augmented models using various tokenization schemes.
Bilingual Tabular Inference: A Case Study on Indic Languages
Existing research on Tabular Natural Language Inference (TNLI) exclusively examines the task in a monolingual setting where the tabular premise and hypothesis are in the same language.
Tesla at SemEval-2022 Task 4: Patronizing and Condescending Language Detection using Transformer-based Models with Data Augmentation
This paper describes our system for Task 4 of SemEval 2022: Patronizing and Condescending Language (PCL) Detection.
A3-108 Machine Translation System for Similar Language Translation Shared Task 2021
In this paper, we describe our submissions for the Similar Language Translation Shared Task 2021.
Analyzing (In)Abilities of SAEs via Formal Languages
Autoencoders have been used for finding interpretable and disentangled features underlying neural network representations in both image and text domains.
Knowledge-Aware Reasoning over Multimodal Semi-structured Tables
With the evolution of AI models capable of multimodal reasoning, it is pertinent to assess their efficacy in handling such structured data.
Mast Kalandar at SemEval-2024 Task 8: On the Trail of Textual Origins: RoBERTa-BiLSTM Approach to Detect AI-Generated Text
SemEval 2024 introduces the task of Multigenerator, Multidomain, and Multilingual Black-Box Machine-Generated Text Detection, aiming to develop automated systems for identifying machine-generated text and detecting potential misuse.
Benchmarks Underestimate the Readiness of Multi-lingual Dialogue Agents
However, after manual evaluation of the validation set, we find that by correcting gold label errors and improving dataset annotation schema, GPT-4 with our prompts can achieve (1) 89. 6%-96. 8% accuracy in DST, and (2) more than 99% correct response generation across different languages.
DaVinci at SemEval-2024 Task 9: Few-shot prompting GPT-3.5 for Unconventional Reasoning
While significant work has been done in the field of NLP on vertical thinking, which involves primarily logical thinking, little work has been done towards lateral thinking, which involves looking at problems from an unconventional perspective and defying existing conceptions and notions.
From Human Judgements to Predictive Models: Unravelling Acceptability in Code-Mixed Sentences
To this end, we construct Cline - a dataset containing human acceptability judgements for English-Hindi (en-hi) code-mixed text.
TeClass: A Human-Annotated Relevance-based Headline Classification and Generation Dataset for Telugu
We further demonstrate the impact of this work by fine-tuning various headline generation models using TeClass dataset.
LastResort at SemEval-2024 Task 3: Exploring Multimodal Emotion Cause Pair Extraction as Sequence Labelling Task
Conversation is the most natural form of human communication, where each utterance can range over a variety of possible emotions.
A Survey of using Large Language Models for Generating Infrastructure as Code
Automation of IaC is a necessity in the present conditions of the Industry and in this survey, we study the feasibility of applying Large Language Models (LLM) to address this problem.
SemEval-2024 Task 1: Semantic Textual Relatedness for African and Asian Languages
We present the first shared task on Semantic Textual Relatedness (STR).
Zero-Shot Multi-task Hallucination Detection
In recent studies, the extensive utilization of large language models has underscored the importance of robust evaluation methodologies for assessing text generation quality and relevance to specific tasks.
Can LLMs Compute with Reasons?
Large language models (LLMs) often struggle with complex mathematical tasks, prone to "hallucinating" incorrect answers due to their reliance on statistical patterns.
SemRel2024: A Collection of Semantic Textual Relatedness Datasets for 13 Languages
Exploring and quantifying semantic relatedness is central to representing language and holds significant implications across various NLP tasks.
Fine-grained Contract NER using instruction based model
In this paper, we transform the NER task into a text-generation task that can be readily adapted by LLMs.
Unsupervised Approach to Evaluate Sentence-Level Fluency: Do We Really Need Reference?
Our code and human-annotated benchmark test-set for fluency is available at https://github. com/AnanyaCoder/TextFluencyForIndicLanaguges.
Mukhyansh: A Headline Generation Dataset for Indic Languages
The task of headline generation within the realm of Natural Language Processing (NLP) holds immense significance, as it strives to distill the true essence of textual content into concise and attention-grabbing summaries.
X-RiSAWOZ: High-Quality End-to-End Multilingual Dialogue Datasets and Few-shot Agents
We create a new multilingual benchmark, X-RiSAWOZ, by translating the Chinese RiSAWOZ to 4 languages: English, French, Hindi, Korean; and a code-mixed English-Hindi language.
PMIndiaSum: Multilingual and Cross-lingual Headline Summarization for Languages in India
This paper introduces PMIndiaSum, a multilingual and massively parallel summarization corpus focused on languages in India.
Attention at SemEval-2023 Task 10: Explainable Detection of Online Sexism (EDOS)
In this paper, we have worked on interpretability, trust, and understanding of the decisions made by models in the form of classification tasks.
Indian Language Summarization using Pretrained Sequence-to-Sequence Models
This paper also extensively analyzes the impact of k-fold cross-validation while experimenting with limited data size, and we also perform various experiments with a combination of the original and a filtered version of the data to determine the efficacy of the pretrained models.
Generalised Spherical Text Embedding
The proposed modelling and the novel similarity metric exploits the matrix structure of embeddings.
Diverse Multi-Answer Retrieval with Determinantal Point Processes
Often questions provided to open-domain question answering systems are ambiguous.
Leveraging Data Recasting to Enhance Tabular Reasoning
Creating challenging tabular inference data is essential for learning complex reasoning.
PreCogIIITH at HinglishEval : Leveraging Code-Mixing Metrics & Language Model Embeddings To Estimate Code-Mix Quality
Code-Mixing is a phenomenon of mixing two or more languages in a speech event and is prevalent in multilingual societies.
HashSet -- A Dataset For Hashtag Segmentation
HashSet dataset is sampled from a different set of tweets when compared to existing datasets and provides an alternate distribution of hashtags to build and validate hashtag segmentation models.
Battling Hateful Content in Indic Languages HASOC '21
We adopt a multilingual transformer based approach and describe our architecture for all 6 subtasks as part of the challenge.
A Dynamic Head Importance Computation Mechanism for Neural Machine Translation
In multi-head attention mechanism, different heads attend to different parts of the input.
Is My Model Using The Right Evidence? Systematic Probes for Examining Evidence-Based Tabular Reasoning
Our experiments demonstrate that a RoBERTa-based model, representative of the current state-of-the-art, fails at reasoning on the following counts: it (a) ignores relevant parts of the evidence, (b) is over-sensitive to annotation artifacts, and (c) relies on the knowledge encoded in the pre-trained language model rather than the evidence presented in its tabular inputs.
Volta at SemEval-2021 Task 9: Statement Verification and Evidence Finding with Tables using TAPAS and Transfer Learning
We fine-tune TAPAS (a model which extends BERT's architecture to capture tabular structure) for both the subtasks as it has shown state-of-the-art performance in various table understanding tasks.
"Subverting the Jewtocracy": Online Antisemitism Detection Using Multimodal Deep Learning
Hence, we collect and label two datasets with 3, 102 and 3, 509 social media posts from Twitter and Gab respectively.
Creation of Corpus and analysis in Code-Mixed Kannada-English Twitter data for Emotion Prediction
Emotion prediction is a critical task in the field of Natural Language Processing (NLP).
SIS@IIITH at SemEval-2020 Task 8: An Overview of Simple Text Classification Methods for Meme Analysis
We chose to participate only in Task A which dealt with Sentiment Classification, which we formulated as a text classification problem.
Finding The Right One and Resolving it
One-anaphora has figured prominently in theoretical linguistic literature, but computational linguistics research on the phenomenon is sparse.
AbuseAnalyzer: Abuse Detection, Severity and Target Prediction for Gab Posts
While extensive popularity of online social media platforms has made information dissemination faster, it has also resulted in widespread online abuse of different types like hate speech, offensive language, sexist and racist opinions, etc.
Tag2Risk: Harnessing Social Music Tags for Characterizing Depression Risk
Studies have shown musical engagement to be an indirect representation of internal states including internalized symptomatology and depression.
Word Embeddings as Tuples of Feature Probabilities
In this paper, we provide an alternate perspective on word representations, by reinterpreting the dimensions of the vector space of a word embedding as a collection of features.
A Simple and Effective Dependency Parser for Telugu
We present a simple and effective dependency parser for Telugu, a morphologically rich, free word order language.
ConfNet2Seq: Full Length Answer Generation from Spoken Questions
This is the first attempt towards generating full-length natural answers from a graph input(confusion network) to the best of our knowledge.
Detection and Annotation of Events in Kannada
In this paper, we provide the basic guidelines towards the detection and linguistic analysis of events in Kannada.
A Multi-Dimensional View of Aggression when voicing Opinion
The advent of social media has immensely proliferated the amount of opinions and arguments voiced on the internet.
NoEl: An Annotated Corpus for Noun Ellipsis in English
Ellipsis resolution has been identified as an important step to improve the accuracy of mainstream Natural Language Processing (NLP) tasks such as information retrieval, event extraction, dialog systems, etc.
Hindi TimeBank: An ISO-TimeML Annotated Reference Corpus
In this paper, we present the Hindi TimeBank, an ISO-TimeML annotated reference corpus for the detection and classification of events, states and time expressions, and the links between them.
A Fully Expanded Dependency Treebank for Telugu
The available Paninian dependency treebank(s) for Telugu is annotated only with inter-chunk dependency relations and not all words of a sentence are part of the parse tree.
Modeling ASR Ambiguity for Dialogue State Tracking Using Word Confusion Networks
Spoken dialogue systems typically use a list of top-N ASR hypotheses for inferring the semantic meaning and tracking the state of the dialogue.
Transition-Based Deep Input Linearization
Traditional methods for deep NLG adopt pipeline approaches comprising stages such as constructing syntactic input, predicting function words, linearizing the syntactic input and generating the surface forms.
Ranked #1 on
Data-to-Text Generation
on SR11Deep
Answering Naturally: Factoid to Full length Answer Generation
A reading comprehension system extracts a span of text, comprising of named entities, dates, small phrases, etc., which serve as the answer to a given question.
Using Syntax to Resolve NPE in English
We get an F1-score of 76. 47{\%} for detection and 70. 27{\%} for NPE resolution on the testset.
De-Mixing Sentiment from Code-Mixed Text
The Collective Encoder captures the overall sentiment of the sentence, while the Specific Encoder utilizes an attention mechanism in order to focus on individual sentiment-bearing sub-words.
Corpus Creation and Analysis for Named Entity Recognition in Telugu-English Code-Mixed Social Media Data
We present a Telugu-English code-mixed corpus with the corresponding named entity tags.
Curriculum Learning Strategies for Hindi-English Codemixed Sentiment Analysis
Sentiment Analysis and other semantic tasks are commonly used for social media textual analysis to gauge public opinion and make sense from the noise on social media.
Fermi at SemEval-2019 Task 8: An elementary but effective approach to Question Discernment in Community QA Forums
This information is highly useful in segregating factual questions from non-factual ones which highly helps in organizing the questions into useful categories and trims down the problem space for the next task in the pipeline for fact evaluation among the available answers.
FERMI at SemEval-2019 Task 5: Using Sentence embeddings to Identify Hate Speech Against Immigrants and Women in Twitter
This paper describes our system (Fermi) for Task 5 of SemEval-2019: HatEval: Multilingual Detection of Hate Speech Against Immigrants and Women on Twitter.
A Pregroup Representation of Word Order Alternation Using Hindi Syntax
Pregroup calculus has been used for the representation of free word order languages (Sanskrit and Hungarian), using a construction called precyclicity.
Fermi at SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media using Sentence Embeddings
This paper describes our system (Fermi) for Task 6: OffensEval: Identifying and Categorizing Offensive Language in Social Media of SemEval-2019.
Predicting Algorithm Classes for Programming Word Problems
We present four new datasets for this task, two multiclass datasets with 550 and 1159 problems each and two multilabel datasets having 3737 and 3960 problems each.
Retrieve and Re-rank: A Simple and Effective IR Approach to Simple Question Answering over Knowledge Graphs
SimpleQuestions is a commonly used benchmark for single-factoid question answering (QA) over Knowledge Graphs (KG).
Aggression Detection on Social Media Text Using Deep Neural Networks
In this paper, we introduce a deep learning based classification system for Facebook posts and comments of Hindi-English Code-Mixed text to detect the aggressive behaviour of/towards users.
NUTS: Network for Unsupervised Telegraphic Summarization
Extractive summarization methods operate by ranking and selecting the sentences which best encapsulate the theme of a given document.
SWDE : A Sub-Word And Document Embedding Based Engine for Clickbait Detection
We generate sub-word level embeddings of the title using Convolutional Neural Networks and use them to train a bidirectional LSTM architecture.
Twitter corpus of Resource-Scarce Languages for Sentiment Analysis and Multilingual Emoji Prediction
In this paper, we leverage social media platforms such as twitter for developing corpus across multiple languages.
Enabling Code-Mixed Translation: Parallel Corpus Creation and MT Augmentation Approach
With the help of the created parallel corpus, we analyzed the structure of English-Hindi code-mixed data and present a technique to augment run-of-the-mill machine translation (MT) approaches that can help achieve superior translations without the need for specially designed translation systems.
Gold Corpus for Telegraphic Summarization
Here, we don{'}t select whole sentences, rather pick short segments of text spread across sentences, as the summary.
Named Entity Recognition for Hindi-English Code-Mixed Social Media Text
Named Entity Recognition (NER) is a major task in the field of Natural Language Processing (NLP), and also is a sub-task of Information Extraction.
Automatic Question Generation using Relative Pronouns and Adverbs
This paper presents a system that automatically generates multiple, natural language questions using relative pronouns and relative adverbs from complex English sentences.
Transliteration Better than Translation? Answering Code-mixed Questions over a Knowledge Base
Our network is trained only on English questions provided in this dataset and noisy Hindi translations of these questions and can answer English-Hindi CM questions effectively without the need of translation into English.
Exploring Chunk Based Templates for Generating a subset of English Text
Natural Language Generation (NLG) is a research task which addresses the automatic generation of natural language text representative of an input non-linguistic collection of knowledge.
Humor Detection in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System
In this paper, we analyze the task of humor detection in texts and describe a freely available corpus containing English-Hindi code-mixed tweets annotated with humorous(H) or non-humorous(N) tags.
Gender Prediction in English-Hindi Code-Mixed Social Media Content : Corpus and Baseline System
In this paper, we analyze the task of author's gender prediction in code-mixed content and present a corpus of English-Hindi texts collected from Twitter which is annotated with author's gender.
Degree based Classification of Harmful Speech using Twitter Data
Harmful speech has various forms and it has been plaguing the social media in different ways.
Cross-Lingual Task-Specific Representation Learning for Text Classification in Resource Poor Languages
The model learns the representation of resource-poor and resource-rich sentences in a common space by using the similarity between their assigned annotation tags.
Corpus Creation and Emotion Prediction for Hindi-English Code-Mixed Social Media Text
Emotion Prediction is a Natural Language Processing (NLP) task dealing with detection and classification of emotions in various monolingual and bilingual texts.
A Dataset of Hindi-English Code-Mixed Social Media Text for Hate Speech Detection
Hate speech detection in social media texts is an important Natural language Processing task, which has several crucial applications like sentiment analysis, investigating cyberbullying and examining socio-political controversies.
A Corpus of English-Hindi Code-Mixed Tweets for Sarcasm Detection
Social media platforms like twitter and facebook have be- come two of the largest mediums used by people to express their views to- wards different topics.
An English-Hindi Code-Mixed Corpus: Stance Annotation and Baseline System
Social media has become one of the main channels for peo- ple to communicate and share their views with the society.
Universal Dependency Parsing for Hindi-English Code-switching
We present a treebank of Hindi-English code-switching tweets under Universal Dependencies scheme and propose a neural stacking model for parsing that efficiently leverages part-of-speech tag and syntactic tree annotations in the code-switching treebank and the preexisting Hindi and English treebanks.
Emotions are Universal: Learning Sentiment Based Representations of Resource-Poor Languages using Siamese Networks
Machine learning approaches in sentiment analysis principally rely on the abundance of resources.
Automatic Normalization of Word Variations in Code-Mixed Social Media Text
Social media platforms such as Twitter and Facebook are becoming popular in multilingual societies.
Contrastive Learning of Emoji-based Representations for Resource-Poor Languages
The model learns the representations of resource-poor and resource-rich language in a common emoji space by using a similarity metric based on the emojis present in sentences from both languages.
Sentiment Analysis of Code-Mixed Languages leveraging Resource Rich Languages
Code-mixed data is an important challenge of natural language processing because its characteristics completely vary from the traditional structures of standard languages.
Neural Network Architecture for Credibility Assessment of Textual Claims
CREDO consists of different modules for capturing various features responsible for the credibility of an article.
Beyond Word2Vec: Embedding Words and Phrases in Same Vector Space
Word embeddings are being used for several linguistic problems and NLP tasks.
An Unsupervised Approach for Mapping between Vector Spaces
Our model handles the problem of data scarcity which is faced by many languages in the world and yields improved word embeddings for words in the target language by relying on transformed embeddings of words of the source language.
Unsupervised Morphological Expansion of Small Datasets for Improving Word Embeddings
We evaluate our method using small sized training sets on eleven test sets for the word similarity task across seven languages.
Injecting Word Embeddings with Another Language's Resource : An Application of Bilingual Embeddings
Word embeddings learned from text corpus can be improved by injecting knowledge from external resources, while at the same time also specializing them for similarity or relatedness.
Deep Neural Network based system for solving Arithmetic Word problems
The worldstate and the query are processed separately in two different networks and finally, the networks are merged to predict the final operation.
Exploiting Morphological Regularities in Distributional Word Representations
We present an unsupervised, language agnostic approach for exploiting morphological regularities present in high dimensional vector spaces.
Word Similarity Datasets for Indian Languages: Annotation and Baseline Systems
With the advent of word representations, word similarity tasks are becoming increasing popular as an evaluation metric for the quality of the representations.
Joining Hands: Exploiting Monolingual Treebanks for Parsing of Code-mixing Data
In this paper, we propose efficient and less resource-intensive strategies for parsing of code-mixed data.
Hand in Glove: Deep Feature Fusion Network Architectures for Answer Quality Prediction in Community Question Answering
Given a question-answer pair along with its metadata, the DFFN architecture independently - a) learns features from the Deep Neural Network (DNN) and b) computes hand-crafted features using various external resources and then combines them using a fully connected neural network trained to predict the final answer quality.
Towards Sub-Word Level Compositions for Sentiment Analysis of Hindi-English Code Mixed Text
We introduce a Hindi-English (Hi-En) code-mixed dataset for sentiment analysis and perform empirical analysis comparing the suitability and performance of various state-of-the-art SA methods in social media.
Towards Deep Learning in Hindi NER: An approach to tackle the Labelled Data Scarcity
In this paper we describe an end to end Neural Model for Named Entity Recognition NER) which is based on Bi-Directional RNN-LSTM.
Deep Feature Fusion Network for Answer Quality Prediction in Community Question Answering
Current AQP systems either learn models using - a) various hand-crafted features (HCF) or b) use deep learning (DL) techniques which automatically learn the required feature representations.
A language model based approach towards large scale and lightweight language identification systems
Most of the existing LID systems rely on modeling the language discriminative information from low-level acoustic features.
