Search Results for author: Ahmed El-Kishky

Found 27 papers, 9 papers with code

Findings of the WMT 2020 Shared Task on Parallel Corpus Filtering and Alignment

no code implementations WMT (EMNLP) 2020 Philipp Koehn, Vishrav Chaudhary, Ahmed El-Kishky, Naman Goyal, Peng-Jen Chen, Francisco Guzmán

Following two preceding WMT Shared Task on Parallel Corpus Filtering (Koehn et al., 2018, 2019), we posed again the challenge of assigning sentence-level quality scores for very noisy corpora of sentence pairs crawled from the web, with the goal of sub-selecting the highest-quality data to be used to train ma-chine translation systems.

Sentence Translation

URL-BERT: Training Webpage Representations via Social Media Engagements

no code implementations25 Oct 2023 Ayesha Qamar, Chetan Verma, Ahmed El-Kishky, Sumit Binnani, Sneha Mehta, Taylor Berg-Kirkpatrick

Common language model (LM) encoders such as BERT can be used to understand and represent the textual content of webpages.

Language Modelling

MiCRO: Multi-interest Candidate Retrieval Online

no code implementations28 Oct 2022 Frank Portman, Stephen Ragain, Ahmed El-Kishky

Providing personalized recommendations in an environment where items exhibit ephemerality and temporal relevancy (e. g. in social media) presents a few unique challenges: (1) inductively understanding ephemeral appeal for items in a setting where new items are created frequently, (2) adapting to trends within engagement patterns where items may undergo temporal shifts in relevance, (3) accurately modeling user preferences over this item space where users may express multiple interests.

Retrieval

TwHIN-BERT: A Socially-Enriched Pre-trained Language Model for Multilingual Tweet Representations at Twitter

1 code implementation15 Sep 2022 Xinyang Zhang, Yury Malkov, Omar Florez, Serim Park, Brian McWilliams, Jiawei Han, Ahmed El-Kishky

Most existing PLMs are not tailored to the noisy user-generated text on social media, and the pre-training does not factor in the valuable social engagement logs available in a social network.

Language Modelling

Non-Parametric Temporal Adaptation for Social Media Topic Classification

no code implementations13 Sep 2022 FatemehSadat Mireshghallah, Nikolai Vogler, Junxian He, Omar Florez, Ahmed El-Kishky, Taylor Berg-Kirkpatrick

User-generated social media data is constantly changing as new trends influence online discussion and personal information is deleted due to privacy concerns.

Classification Retrieval +1

Learning Stance Embeddings from Signed Social Graphs

1 code implementation27 Jan 2022 John Pougué-Biyong, Akshay Gupta, Aria Haghighi, Ahmed El-Kishky

We propose the Stance Embeddings Model(SEM), which jointly learns embeddings for each user and topic in signed social graphs with distinct edge types for each topic.

Misinformation Stance Detection

Classification-based Quality Estimation: Small and Efficient Models for Real-world Applications

no code implementations EMNLP 2021 Shuo Sun, Ahmed El-Kishky, Vishrav Chaudhary, James Cross, Francisco Guzmán, Lucia Specia

Sentence-level Quality estimation (QE) of machine translation is traditionally formulated as a regression task, and the performance of QE models is typically measured by Pearson correlation with human labels.

Machine Translation Model Compression +3

Putting words into the system's mouth: A targeted attack on neural machine translation using monolingual data poisoning

1 code implementation12 Jul 2021 Jun Wang, Chang Xu, Francisco Guzman, Ahmed El-Kishky, Yuqing Tang, Benjamin I. P. Rubinstein, Trevor Cohn

Neural machine translation systems are known to be vulnerable to adversarial test inputs, however, as we show in this paper, these systems are also vulnerable to training attacks.

Data Poisoning Machine Translation +3

An Exploratory Study on Multilingual Quality Estimation

no code implementations Asian Chapter of the Association for Computational Linguistics 2020 Shuo Sun, Marina Fomicheva, Fr{\'e}d{\'e}ric Blain, Vishrav Chaudhary, Ahmed El-Kishky, Adithya Renduchintala, Francisco Guzm{\'a}n, Lucia Specia

Predicting the quality of machine translation has traditionally been addressed with language-specific models, under the assumption that the quality label distribution or linguistic features exhibit traits that are not shared across languages.

Machine Translation Translation

Beyond English-Centric Multilingual Machine Translation

7 code implementations21 Oct 2020 Angela Fan, Shruti Bhosale, Holger Schwenk, Zhiyi Ma, Ahmed El-Kishky, Siddharth Goyal, Mandeep Baines, Onur Celebi, Guillaume Wenzek, Vishrav Chaudhary, Naman Goyal, Tom Birch, Vitaliy Liptchinsky, Sergey Edunov, Edouard Grave, Michael Auli, Armand Joulin

Existing work in translation demonstrated the potential of massively multilingual machine translation by training a single model able to translate between any pair of languages.

Machine Translation Translation

Mining News Events from Comparable News Corpora: A Multi-Attribute Proximity Network Modeling Approach

no code implementations14 Nov 2019 Hyungsul Kim, Ahmed El-Kishky, Xiang Ren, Jiawei Han

This proximity network captures the corpus-level co-occurence statistics for candidate event descriptors, event attributes, as well as their connections.

Attribute News Summarization

CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairs

no code implementations EMNLP 2020 Ahmed El-Kishky, Vishrav Chaudhary, Francisco Guzman, Philipp Koehn

We mine sixty-eight snapshots of the Common Crawl corpus and identify web document pairs that are translations of each other.

Leveraging Pretrained Image Classifiers for Language-Based Segmentation

no code implementations3 Nov 2019 David Golub, Ahmed El-Kishky, Roberto Martín-Martín

Current semantic segmentation models cannot easily generalize to new object classes unseen during train time: they require additional annotated images and retraining.

Object Segmentation +1

Parsimonious Morpheme Segmentation with an Application to Enriching Word Embeddings

no code implementations18 Aug 2019 Ahmed El-Kishky, Frank Xu, Aston Zhang, Jiawei Han

However, in many languages and specialized corpora, words are composed by concatenating semantically meaningful subword structures.

Language Modelling Segmentation +1

Entropy-Based Subword Mining with an Application to Word Embeddings

no code implementations WS 2018 Ahmed El-Kishky, Frank Xu, Aston Zhang, Stephen Macke, Jiawei Han

Recent literature has shown a wide variety of benefits to mapping traditional one-hot representations of words and phrases to lower-dimensional real-valued vectors known as word embeddings.

Language Modelling Machine Translation +3

Integrating Local Context and Global Cohesiveness for Open Information Extraction

1 code implementation26 Apr 2018 Qi Zhu, Xiang Ren, Jingbo Shang, Yu Zhang, Ahmed El-Kishky, Jiawei Han

However, current Open IE systems focus on modeling local context information in a sentence to extract relation tuples, while ignoring the fact that global statistics in a large corpus can be collectively leveraged to identify high-quality sentence-level extractions.

Open Information Extraction Relation +1

Scalable Topical Phrase Mining from Text Corpora

no code implementations24 Jun 2014 Ahmed El-Kishky, Yanglei Song, Chi Wang, Clare Voss, Jiawei Han

Our solution combines a novel phrase mining framework to segment a document into single and multi-word phrases, and a new topic model that operates on the induced document partition.

Topic Models

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