Search Results for author: Avishek Anand

Found 29 papers, 5 papers with code

Fast Forward Indexes for Efficient Document Ranking

no code implementations12 Oct 2021 Jurek Leonhardt, Koustav Rudra, Megha Khosla, Abhijit Anand, Avishek Anand

In this paper, we propose the fast-forward index -- a simple vector forward index that facilitates ranking documents using interpolation-based ranking models.

Document Ranking Semantic Similarity +1

FaxPlainAC: A Fact-Checking Tool Based on EXPLAINable Models with HumAn Correction in the Loop

no code implementations12 Sep 2021 Zijian Zhang, Koustav Rudra, Avishek Anand

It is therefore important to conduct user studies to correct models' inference biases and improve the model in a life-long learning manner in the future according to the user feedback.

Fact Checking

Learnt Sparsification for Interpretable Graph Neural Networks

no code implementations23 Jun 2021 Mandeep Rathee, Zijian Zhang, Thorben Funke, Megha Khosla, Avishek Anand

However, GNNs remain hard to interpret as the interplay between node features and graph structure is only implicitly learned.

Learnt Sparsity for Effective and Interpretable Document Ranking

1 code implementation23 Jun 2021 Jurek Leonhardt, Koustav Rudra, Avishek Anand

We also show that our sentence selection approach can be used to provide explanations for models that operate on only parts of the document, such as BERT.

Document Ranking Language understanding

Towards Axiomatic Explanations for Neural Ranking Models

no code implementations15 Jun 2021 Michael Völske, Alexander Bondarenko, Maik Fröbe, Matthias Hagen, Benno Stein, Jaspreet Singh, Avishek Anand

We investigate whether one can explain the behavior of neural ranking models in terms of their congruence with well understood principles of document ranking by using established theories from axiomatic IR.

Document Ranking Information Retrieval

Exploiting Sentence-Level Representations for Passage Ranking

1 code implementation14 Jun 2021 Jurek Leonhardt, Fabian Beringer, Avishek Anand

Recently, pre-trained contextual models, such as BERT, have shown to perform well in language related tasks.

Fine-tuning Open-Domain Question Answering +2

BERTnesia: Investigating the capture and forgetting of knowledge in BERT

no code implementations EMNLP (BlackboxNLP) 2020 Jonas Wallat, Jaspreet Singh, Avishek Anand

We found that ranking models forget the least and retain more knowledge in their final layer compared to masked language modeling and question-answering.

Fine-tuning Knowledge Base Completion +4

Zorro: Valid, Sparse, and Stable Explanations in Graph Neural Networks

no code implementations18 May 2021 Thorben Funke, Megha Khosla, Avishek Anand

In this paper, we lay down some of the fundamental principles that an explanation method for GNNs should follow and introduce a metric fidelity as a measure of the explanation's effectiveness.

Towards Benchmarking the Utility of Explanations for Model Debugging

no code implementations NAACL (TrustNLP) 2021 Maximilian Idahl, Lijun Lyu, Ujwal Gadiraju, Avishek Anand

Post-hoc explanation methods are an important class of approaches that help understand the rationale underlying a trained model's decision.

An In-depth Analysis of Passage-Level Label Transfer for Contextual Document Ranking

no code implementations30 Mar 2021 Koustav Rudra, Zeon Trevor Fernando, Avishek Anand

Recently introduced pre-trained contextualized autoregressive models like BERT have shown improvements in document retrieval tasks.

Document Ranking

Revisiting the Auction Algorithm for Weighted Bipartite Perfect Matchings

no code implementations18 Jan 2021 Megha Khosla, Avishek Anand

We study the classical weighted perfect matchings problem for bipartite graphs or sometimes referred to as the assignment problem, i. e., given a weighted bipartite graph $G = (U\cup V, E)$ with weights $w : E \rightarrow \mathcal{R}$ we are interested to find the maximum matching in $G$ with the minimum/maximum weight.

Data Structures and Algorithms Discrete Mathematics Combinatorics

Explain and Predict, and then Predict Again

1 code implementation11 Jan 2021 Zijian Zhang, Koustav Rudra, Avishek Anand

A desirable property of learning systems is to be both effective and interpretable.

Fact Verification Multi-Task Learning +1

Hard Masking for Explaining Graph Neural Networks

no code implementations1 Jan 2021 Thorben Funke, Megha Khosla, Avishek Anand

Graph Neural Networks (GNNs) are a flexible and powerful family of models that build nodes' representations on irregular graph-structured data.

Data Compression Decision Making +1

Valid Explanations for Learning to Rank Models

no code implementations29 Apr 2020 Jaspreet Singh, Zhenye Wang, Megha Khosla, Avishek Anand

In extensive quantitative experiments we show that our approach outperforms other model agnostic explanation approaches across pointwise, pairwise and listwise LTR models in validity while not compromising on completeness.

Learning-To-Rank

Question Answering over Curated and Open Web Sources

no code implementations24 Apr 2020 Rishiraj Saha Roy, Avishek Anand

The last few years have seen an explosion of research on the topic of automated question answering (QA), spanning the communities of information retrieval, natural language processing, and artificial intelligence.

Information Retrieval Knowledge Graphs +1

Boilerplate Removal using a Neural Sequence Labeling Model

1 code implementation22 Apr 2020 Jurek Leonhardt, Avishek Anand, Megha Khosla

The extraction of main content from web pages is an important task for numerous applications, ranging from usability aspects, like reader views for news articles in web browsers, to information retrieval or natural language processing.

Information Retrieval

Finding Interpretable Concept Spaces in Node Embeddings using Knowledge Bases

no code implementations11 Oct 2019 Maximilian Idahl, Megha Khosla, Avishek Anand

In this paper we propose and study the novel problem of explaining node embeddings by finding embedded human interpretable subspaces in already trained unsupervised node representation embeddings.

Understanding, Categorizing and Predicting Semantic Image-Text Relations

no code implementations20 Jun 2019 Christian Otto, Matthias Springstein, Avishek Anand, Ralph Ewerth

Two modalities are often used to convey information in a complementary and beneficial manner, e. g., in online news, videos, educational resources, or scientific publications.

Image Captioning Information Retrieval +1

A Comparative Study for Unsupervised Network Representation Learning

no code implementations19 Mar 2019 Megha Khosla, Vinay Setty, Avishek Anand

However, there is no common ground for systematic comparison of embeddings to understand their behavior for different graphs and tasks.

Experimental Design Link Prediction +2

Asynchronous Training of Word Embeddings for Large Text Corpora

1 code implementation7 Dec 2018 Avishek Anand, Megha Khosla, Jaspreet Singh, Jan-Hendrik Zab, Zijian Zhang

In this paper, we propose a scalable approach to train word embeddings by partitioning the input space instead in order to scale to massive text corpora while not sacrificing the performance of the embeddings.

Information Retrieval Word Embeddings

Node Representation Learning for Directed Graphs

no code implementations22 Oct 2018 Megha Khosla, Jurek Leonhardt, Wolfgang Nejdl, Avishek Anand

We also unearth the limitations of evaluations on directed graphs in previous works and propose a clear strategy for evaluating link prediction and graph reconstruction in directed graphs.

General Classification Graph Reconstruction +4

Fine Grained Citation Span for References in Wikipedia

no code implementations EMNLP 2017 Besnik Fetahu, Katja Markert, Avishek Anand

For a Wikipedia article, determining the \emph{citation span} of a citation, i. e. what content is covered by a citation, is important as it helps decide for which content citations are still missing.

Automated News Suggestions for Populating Wikipedia Entity Pages

no code implementations30 Mar 2017 Besnik Fetahu, Katja Markert, Avishek Anand

We propose a two-stage supervised approach for suggesting news articles to entity pages for a given state of Wikipedia.

Finding News Citations for Wikipedia

no code implementations30 Mar 2017 Besnik Fetahu, Katja Markert, Wolfgang Nejdl, Avishek Anand

An important editing policy in Wikipedia is to provide citations for added statements in Wikipedia pages, where statements can be arbitrary pieces of text, ranging from a sentence to a paragraph.

Balancing Novelty and Salience: Adaptive Learning to Rank Entities for Timeline Summarization of High-impact Events

no code implementations14 Jan 2017 Tuan Tran, Claudia Niederée, Nattiya Kanhabua, Ujwal Gadiraju, Avishek Anand

In this work, we present a novel approach for timeline summarization of high-impact events, which uses entities instead of sentences for summarizing the event at each individual point in time.

Learning-To-Rank Timeline Summarization

Cannot find the paper you are looking for? You can Submit a new open access paper.