no code implementations • Findings (EMNLP) 2021 • Meghana Moorthy Bhat, Saghar Hosseini, Ahmed Hassan Awadallah, Paul Bennett, Weisheng Li
Specifically, the lack of corpus, sparsity of toxicity in enterprise emails, and well-defined criteria for annotating toxic conversations have prevented researchers from addressing the problem at scale.
1 code implementation • Findings (EMNLP) 2021 • Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb, Asli Celikyilmaz, Ahmed Hassan Awadallah, Dragomir Radev
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
no code implementations • 22 Apr 2024 • Dujian Ding, Ankur Mallick, Chi Wang, Robert Sim, Subhabrata Mukherjee, Victor Ruhle, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah
Large language models (LLMs) excel in most NLP tasks but also require expensive cloud servers for deployment due to their size, while smaller models that can be deployed on lower cost (e. g., edge) devices, tend to lag behind in terms of response quality.
no code implementations • 4 Oct 2023 • Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Anastasios Kyrillidis, Robert Sim
Large Language Models (LLMs) have the ability to solve a variety of tasks, such as text summarization and mathematical questions, just out of the box, but they are often trained with a single task in mind.
1 code implementation • 3 Oct 2023 • Canwen Xu, Corby Rosset, Ethan C. Chau, Luciano del Corro, Shweti Mahajan, Julian McAuley, Jennifer Neville, Ahmed Hassan Awadallah, Nikhil Rao
Remarkably, our automatic contrastive post-training further improves the performance of Orca, already a state-of-the-art instruction learning model tuned with GPT-4 outputs, to outperform ChatGPT.
2 code implementations • 16 Aug 2023 • Qingyun Wu, Gagan Bansal, Jieyu Zhang, Yiran Wu, Beibin Li, Erkang Zhu, Li Jiang, Xiaoyun Zhang, Shaokun Zhang, Jiale Liu, Ahmed Hassan Awadallah, Ryen W White, Doug Burger, Chi Wang
AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks.
no code implementations • 14 Jun 2023 • Chen Dun, Mirian Hipolito Garcia, Guoqing Zheng, Ahmed Hassan Awadallah, Robert Sim, Anastasios Kyrillidis, Dimitrios Dimitriadis
Our gating function harnesses the knowledge of a pretrained model common expert to enhance its routing decisions on-the-fly.
no code implementations • 24 May 2023 • Woojeong Jin, Subhabrata Mukherjee, Yu Cheng, Yelong Shen, Weizhu Chen, Ahmed Hassan Awadallah, Damien Jose, Xiang Ren
Generalization to unseen tasks is an important ability for few-shot learners to achieve better zero-/few-shot performance on diverse tasks.
no code implementations • 21 Apr 2023 • Nikhil Mehta, Milagro Teruel, Patricio Figueroa Sanz, Xin Deng, Ahmed Hassan Awadallah, Julia Kiseleva
We explore multiple types of help players can give to the AI to guide it and analyze the impact of this help in AI behavior, resulting in performance improvements.
1 code implementation • 22 Jan 2023 • Saghar Hosseini, Hamid Palangi, Ahmed Hassan Awadallah
Large-scale Pre-Trained Language Models (PTLMs) capture knowledge from massive human-written data which contains latent societal biases and toxic contents.
1 code implementation • 31 Oct 2022 • Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
no code implementations • 20 Oct 2022 • Budhaditya Deb, Guoqing Zheng, Ahmed Hassan Awadallah
Recent work has shown that language models (LMs) trained with multi-task \textit{instructional learning} (MTIL) can solve diverse NLP tasks in zero- and few-shot settings with improved performance compared to prompt tuning.
1 code implementation • 14 Oct 2022 • Ganesh Jawahar, Subhabrata Mukherjee, Xiaodong Liu, Young Jin Kim, Muhammad Abdul-Mageed, Laks V. S. Lakshmanan, Ahmed Hassan Awadallah, Sebastien Bubeck, Jianfeng Gao
Furthermore, existing MoE works do not consider computational constraints (e. g., FLOPs, latency) to guide their design.
1 code implementation • 24 May 2022 • Yaqing Wang, Sahaj Agarwal, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
Standard fine-tuning of large pre-trained language models (PLMs) for downstream tasks requires updating hundreds of millions to billions of parameters, and storing a large copy of the PLM weights for every task resulting in increased cost for storing, sharing and serving the models.
Natural Language Understanding parameter-efficient fine-tuning +1
1 code implementation • 5 May 2022 • Negar Arabzadeh, Ali Ahmadvand, Julia Kiseleva, Yang Liu, Ahmed Hassan Awadallah, Ming Zhong, Milad Shokouhi
The recent increase in the volume of online meetings necessitates automated tools for managing and organizing the material, especially when an attendee has missed the discussion and needs assistance in quickly exploring it.
no code implementations • insights (ACL) 2022 • Hanjie Chen, Guoqing Zheng, Ahmed Hassan Awadallah, Yangfeng Ji
Although adapting pre-trained language models with few examples has shown promising performance on text classification, there is a lack of understanding of where the performance gain comes from.
1 code implementation • ICLR 2022 • Ruibo Liu, Guoqing Zheng, Shashank Gupta, Radhika Gaonkar, Chongyang Gao, Soroush Vosoughi, Milad Shokouhi, Ahmed Hassan Awadallah
Hence, they tend to suffer from counterfactual or hallucinatory generation when used in knowledge-intensive natural language generation (NLG) tasks.
Ranked #2 on Question Answering on KILT: ELI5
no code implementations • 29 Jan 2022 • Dongkuan Xu, Subhabrata Mukherjee, Xiaodong Liu, Debadeepta Dey, Wenhui Wang, Xiang Zhang, Ahmed Hassan Awadallah, Jianfeng Gao
Our framework AutoDistil addresses above challenges with the following steps: (a) Incorporates inductive bias and heuristics to partition Transformer search space into K compact sub-spaces (K=3 for typical student sizes of base, small and tiny); (b) Trains one SuperLM for each sub-space using task-agnostic objective (e. g., self-attention distillation) with weight-sharing of students; (c) Lightweight search for the optimal student without re-training.
no code implementations • 9 Dec 2021 • Saghar Hosseini, Ahmed Hassan Awadallah, Yu Su
We define new compositional generalization tasks for NL2API which explore the models' ability to extrapolate from simple API calls in the training set to new and more complex API calls in the inference phase.
1 code implementation • 4 Nov 2021 • Boxin Wang, Chejian Xu, Shuohang Wang, Zhe Gan, Yu Cheng, Jianfeng Gao, Ahmed Hassan Awadallah, Bo Li
In this paper, we present Adversarial GLUE (AdvGLUE), a new multi-task benchmark to quantitatively and thoroughly explore and evaluate the vulnerabilities of modern large-scale language models under various types of adversarial attacks.
Ranked #1 on Adversarial Robustness on AdvGLUE
1 code implementation • 4 Nov 2021 • Subhabrata Mukherjee, Xiaodong Liu, Guoqing Zheng, Saghar Hosseini, Hao Cheng, Greg Yang, Christopher Meek, Ahmed Hassan Awadallah, Jianfeng Gao
We demonstrate that while recent models reach human performance when they have access to large amounts of labeled data, there is a huge gap in performance in the few-shot setting for most tasks.
1 code implementation • 30 Oct 2021 • Xuxi Chen, Tianlong Chen, Weizhu Chen, Ahmed Hassan Awadallah, Zhangyang Wang, Yu Cheng
To address these pain points, we propose a framework for resource- and parameter-efficient fine-tuning by leveraging the sparsity prior in both weight updates and the final model weights.
no code implementations • 16 Oct 2021 • Mengnan Du, Subhabrata Mukherjee, Yu Cheng, Milad Shokouhi, Xia Hu, Ahmed Hassan Awadallah
Recent work has focused on compressing pre-trained language models (PLMs) like BERT where the major focus has been to improve the in-distribution performance for downstream tasks.
1 code implementation • Findings (NAACL) 2022 • Yaqing Wang, Subhabrata Mukherjee, Xiaodong Liu, Jing Gao, Ahmed Hassan Awadallah, Jianfeng Gao
The first is the use of self-training to leverage large amounts of unlabeled data for prompt-based FN in few-shot settings.
no code implementations • Findings (EMNLP) 2021 • Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
We study the problem of multilingual automated reply suggestions (RS) model serving many languages simultaneously.
1 code implementation • 10 Sep 2021 • Yusen Zhang, Ansong Ni, Tao Yu, Rui Zhang, Chenguang Zhu, Budhaditya Deb, Asli Celikyilmaz, Ahmed Hassan Awadallah, Dragomir Radev
Dialogue summarization helps readers capture salient information from long conversations in meetings, interviews, and TV series.
no code implementations • 9 Sep 2021 • Srinagesh Sharma, Guoqing Zheng, Ahmed Hassan Awadallah
In this paper, we aim to the address of the problem of few shot task learning by exploiting and transferring from a different task which admits a related but disparate label space.
1 code implementation • EMNLP (ACL) 2021 • Ansong Ni, Zhangir Azerbayev, Mutethia Mutuma, Troy Feng, Yusen Zhang, Tao Yu, Ahmed Hassan Awadallah, Dragomir Radev
We also provide explanations for models and evaluation metrics to help users understand the model behaviors and select models that best suit their needs.
no code implementations • NAACL 2022 • Guoqing Zheng, Giannis Karamanolakis, Kai Shu, Ahmed Hassan Awadallah
In this paper, we propose such a benchmark, named WALNUT (semi-WeAkly supervised Learning for Natural language Understanding Testbed), to advocate and facilitate research on weak supervision for NLU.
no code implementations • NeurIPS 2021 • Mengnan Du, Subhabrata Mukherjee, Guanchu Wang, Ruixiang Tang, Ahmed Hassan Awadallah, Xia Hu
This process not only requires a lot of instance-level annotations for sensitive attributes, it also does not guarantee that all fairness sensitive information has been removed from the encoder.
1 code implementation • 8 Jun 2021 • Subhabrata Mukherjee, Ahmed Hassan Awadallah, Jianfeng Gao
While deep and large pre-trained models are the state-of-the-art for various natural language processing tasks, their huge size poses significant challenges for practical uses in resource constrained settings.
1 code implementation • ACL 2021 • Mozhi Zhang, Wei Wang, Budhaditya Deb, Guoqing Zheng, Milad Shokouhi, Ahmed Hassan Awadallah
Reply suggestion models help users process emails and chats faster.
2 code implementations • NAACL 2021 • Mengzhou Xia, Guoqing Zheng, Subhabrata Mukherjee, Milad Shokouhi, Graham Neubig, Ahmed Hassan Awadallah
Extensive experiments on real-world low-resource languages - without access to large-scale monolingual corpora or large amounts of labeled data - for tasks like cross-lingual sentiment analysis and named entity recognition show the effectiveness of our approach.
1 code implementation • NAACL 2021 • Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, Dragomir Radev
As increasing numbers of meetings are recorded and transcribed, meeting summaries have become essential to remind those who may or may not have attended the meetings about the key decisions made and the tasks to be completed.
1 code implementation • NAACL 2021 • Giannis Karamanolakis, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah
In this work, we develop a weak supervision framework (ASTRA) that leverages all the available data for a given task.
1 code implementation • NAACL 2021 • Ahmed Elgohary, Christopher Meek, Matthew Richardson, Adam Fourney, Gonzalo Ramos, Ahmed Hassan Awadallah
We present NL-EDIT, a model for interpreting natural language feedback in the interaction context to generate a sequence of edits that can be applied to the initial parse to correct its errors.
no code implementations • 1 Jan 2021 • Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Hassan Awadallah
Neural sequence labeling is an important technique employed for many Natural Language Processing (NLP) tasks, such as Named Entity Recognition (NER), slot tagging for dialog systems and semantic parsing.
no code implementations • NeurIPS Workshop CAP 2020 • Tao Yu, Rui Zhang, Alex Polozov, Christopher Meek, Ahmed Hassan Awadallah
Conversational Semantic Parsing (CSP) is the task of converting a sequence of natural language queries to formal language (e. g., SQL, SPARQL) that can be executed against a structured ontology (e. g. databases, knowledge bases).
Ranked #3 on Multi-domain Dialogue State Tracking on MULTIWOZ 2.1 (using extra training data)
no code implementations • Asian Chapter of the Association for Computational Linguistics 2020 • Xinya Du, Ahmed Hassan Awadallah, Adam Fourney, Robert Sim, Paul Bennett, Claire Cardie
We show that leveraging metadata information from web pages can improve the performance of models for answer passage selection/reranking.
no code implementations • NAACL 2021 • Xiang Deng, Ahmed Hassan Awadallah, Christopher Meek, Oleksandr Polozov, Huan Sun, Matthew Richardson
Additionally, to evaluate different methods under more realistic text-table alignment settings, we create a new evaluation set Spider-Realistic based on Spider dev set with explicit mentions of column names removed, and adopt eight existing text-to-SQL datasets for cross-database evaluation.
no code implementations • 7 Oct 2020 • Yaqing Wang, Subhabrata Mukherjee, Haoda Chu, Yuancheng Tu, Ming Wu, Jing Gao, Ahmed Hassan Awadallah
While self-training serves as an effective mechanism to learn from large amounts of unlabeled data -- meta-learning helps in adaptive sample re-weighting to mitigate error propagation from noisy pseudo-labels.
no code implementations • ACL 2020 • Sudipto Mukherjee, Subhabrata Mukherjee, Marcello Hasegawa, Ahmed Hassan Awadallah, Ryen White
Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks.
no code implementations • NeurIPS 2020 • Subhabrata Mukherjee, Ahmed Hassan Awadallah
Standard self-training mechanism randomly samples instances from the unlabeled pool to pseudo-label and augment labeled data.
no code implementations • 30 May 2020 • Foyzul Hassan, Chetan Bansal, Nachiappan Nagappan, Thomas Zimmermann, Ahmed Hassan Awadallah
Using the machine learning model, we extracted exceptions from raw queries and performed popularity, effort, success, query characteristic and web domain analysis.
no code implementations • 26 May 2020 • Kai Shu, Subhabrata Mukherjee, Guoqing Zheng, Ahmed Hassan Awadallah, Milad Shokouhi, Susan Dumais
In this paper, we propose to leverage user actions as a source of weak supervision, in addition to a limited set of annotated examples, to detect intents in emails.
no code implementations • ACL 2020 • Ahmed Elgohary, Saghar Hosseini, Ahmed Hassan Awadallah
We study the task of semantic parse correction with natural language feedback.
no code implementations • 5 May 2020 • Sudipto Mukherjee, Subhabrata Mukherjee, Marcello Hasegawa, Ahmed Hassan Awadallah, Ryen White
Intelligent features in email service applications aim to increase productivity by helping people organize their folders, compose their emails and respond to pending tasks.
1 code implementation • ACL 2020 • Jieyu Zhao, Subhabrata Mukherjee, Saghar Hosseini, Kai-Wei Chang, Ahmed Hassan Awadallah
In this paper, we study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications.
no code implementations • 3 Apr 2020 • Kai Shu, Guoqing Zheng, Yichuan Li, Subhabrata Mukherjee, Ahmed Hassan Awadallah, Scott Ruston, Huan Liu
Social media has greatly enabled people to participate in online activities at an unprecedented rate.
no code implementations • 19 Dec 2019 • Nikitha Rao, Chetan Bansal, Thomas Zimmermann, Ahmed Hassan Awadallah, Nachiappan Nagappan
Subsequently, we propose a taxonomy of intents to identify the various contexts in which web search is used in software engineering.
1 code implementation • 10 Nov 2019 • Guoqing Zheng, Ahmed Hassan Awadallah, Susan Dumais
We view the label correction procedure as a meta-process and propose a new meta-learning based framework termed MLC (Meta Label Correction) for learning with noisy labels.
Ranked #9 on Image Classification on Clothing1M (using clean data) (using extra training data)
no code implementations • 24 Oct 2019 • Kai Shu, Ahmed Hassan Awadallah, Susan Dumais, Huan Liu
This is especially the case for many real-world tasks where large scale annotated examples are either too expensive to acquire or unavailable due to privacy or data access constraints.
no code implementations • 4 Oct 2019 • Subhabrata Mukherjee, Ahmed Hassan Awadallah
We show that our student models can compress the huge teacher by up to 26x while still matching or even marginally exceeding the teacher performance in low-resource settings with small amount of labeled data.
no code implementations • NeurIPS Workshop Document_Intelligen 2019 • Petar Stojanov, Ahmed Hassan Awadallah, Paul Bennett, Saghar Hosseini
In many domains, especially enterprise text analysis, there is an abundance of data which can be used for the development of new AI-powered intelligent experiences to improve people's productivity.
1 code implementation • ACL 2019 • Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie
In this work, we focus on the multilingual transfer setting where training data in multiple source languages is leveraged to further boost target language performance.
Ranked #10 on Cross-Lingual NER on CoNLL Dutch
no code implementations • 27 Sep 2018 • Xilun Chen, Ahmed Hassan Awadallah, Hany Hassan, Wei Wang, Claire Cardie
In this work, we propose a zero-resource multilingual transfer learning model that can utilize training data in multiple source languages, while not requiring target language training data nor cross-lingual supervision.
no code implementations • 26 Dec 2017 • Chu-Cheng Lin, Dongyeop Kang, Michael Gamon, Madian Khabsa, Ahmed Hassan Awadallah, Patrick Pantel
Emails in the workplace are often intentional calls to action for its recipients.
no code implementations • SIGIR 2017 • Liu Yang, Susan T. Dumais, Paul N. Bennett, Ahmed Hassan Awadallah
Email is still among the most popular online activities.