Yuval Merhav


2022

pdf
Controlled Data Generation via Insertion Operations for NLU
Manoj Kumar | Yuval Merhav | Haidar Khan | Rahul Gupta | Anna Rumshisky | Wael Hamza
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies: Industry Track

Use of synthetic data is rapidly emerging as a realistic alternative to manually annotating live traffic for industry-scale model building. Manual data annotation is slow, expensive and not preferred for meeting customer privacy expectations. Further, commercial natural language applications are required to support continuously evolving features as well as newly added experiences. To address these requirements, we propose a targeted synthetic data generation technique by inserting tokens into a given semantic signature. The generated data are used as additional training samples in the tasks of intent classification and named entity recognition. We evaluate on a real-world voice assistant dataset, and using only 33% of the available training set, we achieve the same accuracy as training with all available data. Further, we analyze the effects of data generation across varied real-world applications and propose heuristics that improve the task performance further.

pdf
Robust Candidate Generation for Entity Linking on Short Social Media Texts
Liam Hebert | Raheleh Makki | Shubhanshu Mishra | Hamidreza Saghir | Anusha Kamath | Yuval Merhav
Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)

Entity Linking (EL) is the gateway into Knowledge Bases. Recent advances in EL utilize dense retrieval approaches for Candidate Generation, which addresses some of the shortcomings of the Lookup based approach of matching NER mentions against pre-computed dictionaries. In this work, we show that in the domain of Tweets, such methods suffer as users often include informal spelling, limited context, and lack of specificity, among other issues. We investigate these challenges on a large and recent Tweets benchmark for EL, empirically evaluate lookup and dense retrieval approaches, and demonstrate a hybrid solution using long contextual representation from Wikipedia is necessary to achieve considerable gains over previous work, achieving 0.93 recall.

2021

pdf
Towards Realistic Single-Task Continuous Learning Research for NER
Justin Payan | Yuval Merhav | He Xie | Satyapriya Krishna | Anil Ramakrishna | Mukund Sridhar | Rahul Gupta
Findings of the Association for Computational Linguistics: EMNLP 2021

There is an increasing interest in continuous learning (CL), as data privacy is becoming a priority for real-world machine learning applications. Meanwhile, there is still a lack of academic NLP benchmarks that are applicable for realistic CL settings, which is a major challenge for the advancement of the field. In this paper we discuss some of the unrealistic data characteristics of public datasets, study the challenges of realistic single-task continuous learning as well as the effectiveness of data rehearsal as a way to mitigate accuracy loss. We construct a CL NER dataset from an existing publicly available dataset and release it along with the code to the research community.

2018

pdf
Design Challenges in Named Entity Transliteration
Yuval Merhav | Stephen Ash
Proceedings of the 27th International Conference on Computational Linguistics

We analyze some of the fundamental design challenges that impact the development of a multilingual state-of-the-art named entity transliteration system, including curating bilingual named entity datasets and evaluation of multiple transliteration methods. We empirically evaluate the transliteration task using the traditional weighted finite state transducer (WFST) approach against two neural approaches: the encoder-decoder recurrent neural network method and the recent, non-sequential Transformer method. In order to improve availability of bilingual named entity transliteration datasets, we release personal name bilingual dictionaries mined from Wikidata for English to Russian, Hebrew, Arabic, and Japanese Katakana. Our code and dictionaries are publicly available.

2012

pdf
A Weighting Scheme for Open Information Extraction
Yuval Merhav
Proceedings of the NAACL HLT 2012 Student Research Workshop