Papers by Kenneth Church
Hubless Nearest Neighbor Search for Bilingual Lexicon Induction (P19-1)
Copied to clipboard
| Challenge: | Existing methods for bilingual Lexicon Induction use nonparallel corpora, but hubness often degrades accuracy. |
| Approach: | They propose a method to create a lexicon of translation equivalents from non-parallel corpora by aligning two word embedding spaces and retrieving the nearest neighbor (NN) this method reduces hubness, which is necessary for retrieval tasks. |
| Outcome: | The proposed method outperforms NN, Inverted SoFtmax and other state-of-the-art methods. |
On Attention Redundancy: A Comprehensive Study (2021.naacl-main)
Copied to clipboard
| Challenge: | Attention redundancy has been observed among attention heads but has not been deeply studied in the literature. |
| Approach: | They propose a multi-layer multi-head self-attention mechanism which is widely applied in modern neural language models. |
| Outcome: | The proposed model is useful for interpretation and model compression. |
Comparing Edge-based and Node-based Methods on a Citation Prediction Task (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Citation Prediction is the task of estimating whether paper a cites paper b. |
| Approach: | They propose a new Citation Prediction task that evaluates both a node-based model and an edge-based one to quantify these trends. |
| Outcome: | The proposed model improves with larger training sets and degrades with longer forecast horizons. |
Fluent and Low-latency Simultaneous Speech-to-Speech Translation with Self-adaptive Training (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Current approaches to simultaneous speech-to-speech translation accumulate more and more latencies in later sentences when the speaker talks faster. |
| Approach: | They propose a method which generates more fluent target speech latency than the baseline . they propose to use self-adaptive translation to adjust the length of translations to accommodate different source speech rates. |
| Outcome: | Xiong et al., 2019) show that the proposed method generates more fluent target speech latency than baseline . authors say it provides more natural communication process than speech-to-text translation . xiong and colleagues say the proposed technique is more efficient than current approaches . |
A Gentle Introduction to Deep Nets and Opportunities for the Future (2022.acl-tutorials)
Copied to clipboard
| Challenge: | a tutorial on deep nets will introduce a new language for fine tuning deep net programs . the tutorial will be divided into two parts: Part A will make deep net programming accessible to a broader audience . |
| Approach: | This tutorial introduces a new language for fine tuning deep nets with short (1-line) programs that are as easy to code as regression in statistics packages such as R. |
| Outcome: | This tutorial will introduce gft (general fine tuning), a new language for deep nets . glm is a "little language" similar to gslm in statistics package R . |
Training on Lexical Resources (2022.lrec-1)
Copied to clipboard
| Challenge: | In this paper, we fine-tune pretrained deep nets such as BERT and ERNIE . at inference time, these nets can be used to distinguish synonyms from antonyms . |
| Approach: | They propose to use lexical resources to fine-tune pretrained deep nets such as BERT and ERNIE to distinguish synonyms from antonyms. |
| Outcome: | The proposed method can be applied to multiword expressions, out of vocabulary words, morphological variants and more. |
Data Collection vs. Knowledge Graph Completion: What is Needed to Improve Coverage? (2021.emnlp-main)
Copied to clipboard
| Challenge: | Knowledge Graph Completion (KGC) attempts to learn missing links from subsets. |
| Approach: | This survey/position paper discusses ways to improve coverage of resources such as WordNet. |
| Outcome: | The proposed method improves WordNet coverage by reducing the number of words in the sample and reducing unbalanced corpora. |
No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages (2024.emnlp-main)
Copied to clipboard
Youssef Mohamed, Runjia Li, Ibrahim Ahmad, Kilichbek Haydarov, Philip Torr, Kenneth Church, Mohamed Elhoseiny
| Challenge: | Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo emphasizes diversity of opinions over languages and cultures. |
| Approach: | They propose a vision-language benchmark that spans 28 languages and encompasses approximately 200,000 annotations. |
| Outcome: | The proposed benchmark spans 28 languages and encompasses approximately 200,000 annotations . the challenge is to build machine learning systems that assign emotional captions to images . |
ArtELingo: A Million Emotion Annotations of WikiArt with Emphasis on Diversity over Language and Culture (2022.emnlp-main)
Copied to clipboard
Youssef Mohamed, Mohamed Abdelfattah, Shyma Alhuwaider, Feifan Li, Xiangliang Zhang, Kenneth Church, Mohamed Elhoseiny
| Challenge: | ArtELingo is a benchmark and dataset designed to encourage work on diversity across languages and cultures. |
| Approach: | They introduce a benchmark and dataset designed to encourage work on diversity across languages and cultures. |
| Outcome: | The new benchmark and dataset compared artELingo annotations across languages and cultures and found that diversity improves the performance of baseline models. |
Incremental Text-to-Speech Synthesis with Prefix-to-Prefix Framework (2020.findings-emnlp)
Copied to clipboard
Mingbo Ma, Baigong Zheng, Kaibo Liu, Renjie Zheng, Hairong Liu, Kainan Peng, Kenneth Church, Liang Huang
| Challenge: | Text-to-speech synthesis (TTS) has seen rapid progress in recent years, but still suffers from latencies. |
| Approach: | They propose a neural incremental TTS approach that synthesizes speech in an online fashion, playing a segment of audio while generating the next. |
| Outcome: | Experiments on English and Chinese TTS show that the proposed approach achieves similar speech naturalness compared to full sentence TTS, but with a constant (1-2 words) latency. |
Improving Bilingual Lexicon Induction for Low Frequency Words (2020.emnlp-main)
Copied to clipboard
| Challenge: | Existing methods to generate word-level translations from non-parallel corpora are based on word embeddings. |
| Approach: | They propose two methods to address two factors that degrade bilingual lexicon induction accuracy . they propose a method that assumes a seeding dictionary is available . |
| Outcome: | The proposed method improves bilingual lexicon induction significantly for rare words. |