Abstract

Subjective bias in Wikipedia textual data is a significant problem and affects millions of readers worldwide. Though some monolingual work has been done in classifying and debiasing biased text in resource-rich languages, the low-resource languages with large numbers of speakers remain unattended. We present an approach for the dual problems of multilingual bias detection and its mitigation with a thorough analysis. In this work, we establish competitive baselines on our preliminary approach, which includes classification-based modelling for bias detection on a multilingual dataset curated from existing monolingual sources. For the problem of bias mitigation, we follow the style transfer paradigm and model using transformer-based seq2seq architectures. We also discuss several approaches for further improvement in both problems as a part of our ongoing work.

Abstract

Lack of diverse perspectives causes neutrality bias in Wikipedia content leading to millions of worldwide readers getting exposed by potentially inaccurate information. Hence, neutrality bias detection and mitigation is a critical problem. Although previous studies have proposed effective solutions for English, no work exists for Indian languages. First, we contribute two large datasets, mWIKIBIAS and mWNC, covering 8 languages, for the bias detection and mitigation tasks respectively. Next, we investigate the effectiveness of popular multilingual Transformer-based models for the two tasks by modeling detection as a binary classification problem and mitigation as a style transfer problem. We make the code and data publicly available.

Abstract

No Results Found

Abstract

Multiple business scenarios require an automated generation of descriptive human-readable long text from structured input data, where the source is typically a high-resource language and the target is a low or medium resource language. We define the Cross-Lingual Fact to Long Text Generation (XFLT) as a novel natural language generation (NLG) task that involves generating descriptive and human-readable long text in a target language from structured input data (such as fact triples) in a source language. XFLT is challenging because of (a) hallucinatory nature of the state-of-the-art NLG models, (b) lack of good quality training data, and (c) lack of a suitable cross-lingual NLG metric. Unfortunately previous work focuses on different related problem settings (cross-lingual facts to short text or monolingual graph to text) and has made no efforts to handle hallucinations. In this paper, we contribute a novel dataset, XLALIGN with over 64,000 paragraphs across 12 different languages, and English facts. We propose a novel solution to the XFLT task which addresses these challenges by training multilingual Transformer-based encoder-decoder models with coverage prompts and grounded decoding. Further, it improves on the XFLT quality by defining task-specific reward functions and training on them using reinforcement learning. On XLALIGN, we compare this novel solution with several strong baselines using a new metric, cross-lingual PARENT. We also make our code and data publicly available

Abstract

One crucial aspect of content organization is the creation of article outlines, which summarize the primary topics and subtopics covered in an article in a structured manner. This paper introduces a solution called XOutlineGen, which generates cross-lingual outlines for encyclopedic texts from reference articles. XOutlineGen uses the XWikiRef dataset, which consists of encyclopedic texts generated from reference articles and section titles. The dataset is enhanced with two new languages and three new domains, resulting in ∼92K articles. Our pipeline employs this dataset to train a two-step generation model, which takes the article title and set of references as inputs and produces the article outline.

Abstract

A system and method for automatically extracting contract data from electronic contracts includes an administrator module configured to provide templates for inputting document patterns and a list of contract data tags for each of a plurality of contract document types. A parser is configured to convert an electronic contract document into a contract text document and reformat the contract text document to provide a pattern for the text contract document. A pattern recognition engine is configured to determine a list of contract document types in the electronic contract by comparing and matching patterns of all known contract document types with the pattern of the contract text document. A contract data extraction engine is configured to extract contract data for each contract document type on the list.

Abstract

The task of multilingual news article similarity en- tails determining the degree of similarity of a given pair of news articles in a language-agnostic setting. This task aims to determine the extent to which the articles deal with the entities and events in ques- tion without much consideration of the subjective aspects of the discourse. Considering the supe- rior representations being given by these models as validated on other tasks in NLP across an array of high and low-resource languages and this task not having any restricted set of languages to focus on, we adopted using the encoder representations from these models as our choice throughout our experiments. For modeling the similarity task by using the representations given by these models, a Siamese architecture was used as the underlying architecture. In experimentation, we investigated on several fronts including features passed to the encoder model, data augmentation and ensembling among our major experiments. We found data aug- mentation to be the most effective working strategy among our experiments.

Abstract

This paper provides a comparison of different deep learning methods for identifying misogy- nous memes for SemEval-2022 Task 5: Multi- media Automatic Misogyny Identification. In this task, we experiment with architectures in the identification of misogynous content in memes by making use of text and image-based information. The different deep learning meth- ods compared in this paper are: (i) unimodal image or text models (ii) fusion of unimodal models (iii) multimodal transformers models and (iv) transformers further pretrained on a multimodal task. From our experiments, we found pretrained multimodal transformer ar- chitectures to strongly outperform the models involving fusion of representation from both the modalities.

Abstract

Clause recommendation is the problem of recommending a clause to a legal contract, given the context of the contract in question and the clause type to which the clause should belong. With not much prior work being done toward the generation of legal contracts, this problem was proposed as a first step toward the bigger problem of contract generation. As an open-ended text generation prob-lem, the distinguishing characteristics of this problem lie in the nature of legal lan-guage as a sublanguage and the considerable similarity of textual content within the clauses of a specific type. This similarity aspect in legal clauses drives us to investi-gate the importance of similar contracts’ representation for recommending clauses. In our work, we experiment with generating clauses for 15 commonly occurring clause types in contracts expanding upon the previous work on this problem and analyzing clause recommendations in varying settings using information derived from similar contracts.

Abstract

XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages Tushar Abhishek, Shivprasad Sagare, Bhavyajeet Singh, Anubhav Sharma, Manish Gupta∗ and Vasudeva Varma Information Retrieval and Extraction Lab, IIIT Hyderabad, India {tushar.abhishek,shivprasad.sagare,bhavyajeet.singh,anubhav.sharma}@research.iiit.ac.in, {manish.gupta,vv}@iiit.ac.in Abstract Multiple critical scenarios (like Wikipedia text generation given English Infoboxes) need au- tomated generation of descriptive text in low resource (LR) languages from English fact triples. Previous work has focused on English fact-to-text (F2T) generation. To the best of our knowledge, there has been no previous at- tempt on cross-lingual alignment or generation for LR languages. Building an effective cross- lingual F2T (XF2T) system requires alignment between English structured facts and LR sen- tences. We propose two unsupervised meth- ods for cross-lingual alignment. We contribute XALIGN, an XF2T dataset with 0.45M pairs across 8 languages, of which 5402 pairs have been manually annotated. We also train strong baseline XF2T generation models on XAlign dataset