Papers by Irshad Bhat

4 papers
wikiHowToImprove: A Resource and Analyses on Edits in Instructional Texts (2020.lrec-1)

Copied to clipboard

Challenge: wikiHow articles are subject to revision edits, but do they provide clarifications? a new study compares changes made across multiple versions of the same set of instructions .
Approach: They use wikiHow to analyze revision histories for 2.7 million sentences from wikihow . they use human annotation to categorize subset of edits and provide models .
Outcome: The proposed model can distinguish between “older” and “newer” revisions of a sentence.
Answering Naturally: Factoid to Full length Answer Generation (D19-54)

Copied to clipboard

Challenge: Factoid question answering systems extract answers for a question from passages, which are usually short spans of text . but, these spans would result in an unnatural reading experience in a conversational system . a pointer generator based full-length answer generator can be used with most QA systems .
Approach: They propose a pointer generator based full-length answer generator which can be used with most QA systems.
Outcome: The proposed system generates full length answer without relying on passage from which it was extracted.
Towards Modeling Revision Requirements in wikiHow Instructions (2020.emnlp-main)

Copied to clipboard

Challenge: wikiHow is a collaboratively edited platform of how-to guides . authors extend existing textual edits with 4 million sentences that remain unedited .
Approach: They extend existing textual edits with a set of 4 million sentences that remain unedited over time.
Outcome: The proposed model can predict the need for edits in wikiHow guides . the authors extend an existing resource of textual edits with a complementary set of 4 million sentences that remain unedited over time .
Universal Dependency Parsing for Hindi-English Code-Switching (N18-1)

Copied to clipboard

Challenge: Code-switching data often need additional processes such as language identification, normalization and/or back-transliteration to be processed.
Approach: They propose a neural stacking model that leverages part-of-speech tags and syntactic tree annotations in tweets to parse code-switching data.
Outcome: The proposed model is 1.5% better than the augmented model and 3.8% better than one which uses first-best normalization and/or back-transliteration.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations