Papers by Wael Hamza

14 papers
A Hybrid Approach to Cross-lingual Product Review Summarization (2022.emnlp-industry)

Copied to clipboard

Challenge: Existing methods for summarizing product reviews with thousands of reviews are inefficient and time consuming.
Approach: They propose an unsupervised extractive step and a supervised abstractive step to generate a short summary in any language.
Outcome: The proposed model is as good as human written summaries in coherence, informativeness, non-redundancy, and fluency as human summary summators.
Zero-shot Generalization in Dialog State Tracking through Generative Question Answering (2021.eacl-main)

Copied to clipboard

Challenge: Existing methods for Dialog State Tracking do not generalize well to new domains and unseen slots.
Approach: They propose an ontology-free framework that queries for unseen constraints and slots in multi-domain task-oriented dialogs using a conditional language model pre-trained on substantive English sentences.
Outcome: The proposed framework improves goal accuracy in zero-shot domain adaptation settings by up to 9% over the previous state-of-the-art on the MultiWOZ 2.1 dataset.
Low-Resource Compositional Semantic Parsing with Concept Pretraining (2023.eacl-main)

Copied to clipboard

Challenge: Semantic parsing is a key role in voice assistants by mapping natural language to structured meaning representations.
Approach: They propose an architecture to perform domain adaptation automatically with only a small amount of metadata about the new domain and without any new training data.
Outcome: The proposed architecture outperforms existing models in low-resource settings.
Recipes for Sequential Pre-training of Multilingual Encoder and Seq2Seq Models (2023.findings-acl)

Copied to clipboard

Challenge: Pre-trained encoder-only and sequence-to-sequence models are computationally expensive.
Approach: They propose a recipe to initialize one model from the other to improve pre-training efficiency.
Outcome: The proposed method matches the performance of a from-scratch model with a multilingual encoder while reducing the total compute cost by 27%.
Attention Fusion: a light yet efficient late fusion mechanism for task adaptation in NLU (2022.findings-naacl)

Copied to clipboard

Challenge: a recent study has shown that fine-tuning pre-trained models is parameter-inefficient and expensive.
Approach: They propose a task-attuned token module which integrates pre-trained network representations into a pre-trainer.
Outcome: The proposed model trains only 0.0009% of the parameters and is efficient during computation and scalable during deployment.
Delexicalized Paraphrase Generation (2020.coling-industry)

Copied to clipboard

Challenge: Using convolutional neural networks, we generate delexicalized sentences . 1.29% accuracy is achieved with the generated paraphrases .
Approach: They propose a neural paraphrasing model that generates delexicalized sentences . they use convolutional neural networks to pool on slot values and use pointers to locate them .
Outcome: The proposed model generates delexicalized sentences with high quality . it can be used for intent classification and named entity recognition tasks .
LINGUIST: Language Model Instruction Tuning to Generate Annotated Utterances for Intent Classification and Slot Tagging (2022.coling-1)

Copied to clipboard

Challenge: LINGUIST generates annotated data for Intent Classification and Slot Tagging (IC+ST) we demonstrate fine-tuning of a large-scale seq2seq model to control outputs of multilingual data generation.
Approach: They propose a method for generating annotated data for Intent Classification and Slot Tagging (IC+ST) they use a 5-billion-parameter multilingual sequence-to-sequence model to fine-tune it on a flexible instruction prompt.
Outcome: The proposed method outperforms state-of-the-art approaches on a SNIPS intent setting and shows significant improvement on IC+ST in a cross-lingual setting.
CLASP: Few-Shot Cross-Lingual Data Augmentation for Semantic Parsing (2022.aacl-short)

Copied to clipboard

Challenge: Large Language Models excel at a low-resource level given limited data, but are unsuitable for runtime systems which require low latency.
Approach: They propose a method to augment training data for a model 40x smaller (500M parameters) they use Alexa to generate synthetic data from Alexa 20B to augment the training set .
Outcome: The proposed method improves low-resource SP on two datasets in low-source settings.
Neural Cross-Lingual Coreference Resolution And Its Application To Entity Linking (P18-2)

Copied to clipboard

Challenge: a cross-lingual coreference model is based on multi-lingual embeddings and language independent features.
Approach: They propose a crosslingual coreference model that builds on multi-lingual embeddings and language independent features.
Outcome: The proposed model outperforms the existing models on Chinese and Spanish test sets.
Leveraging Context Information for Natural Question Generation (N18-2)

Copied to clipboard

Challenge: Existing work for natural question generation ignores the input passage or hard-codes answer positions.
Approach: They propose a model that matches the answer with the passage before generating a question.
Outcome: The proposed model outperforms the state-of-the-art model using rich features.
Contextual Domain Classification with Temporal Representations (2021.naacl-industry)

Copied to clipboard

Challenge: Existing studies that incorporate context in SLU have focused on domains where context is limited to a few minutes.
Approach: They propose temporal representations that combine wall-clock second difference and turn order offset information to utilize both recent and distant context in a novel large-scale setup.
Outcome: The proposed model reduces 13.04% of classification errors compared to baseline . previous studies have focused on domains where context is limited to a few minutes .
Instilling Type Knowledge in Language Models via Multi-Task QA (2022.findings-naacl)

Copied to clipboard

Challenge: Current methods to learn entity types rely on coarse, noisy labels . current methods rely only on text-to-text pre-training on type-centric questions .
Approach: They propose to instill fine-grained type knowledge in language models by pre-training on type-centric questions.
Outcome: The proposed model achieves state-of-the-art in zero-shot dialog state tracking benchmarks and can accurately infer entity types in Wikipedia articles.
Controlled Data Generation via Insertion Operations for NLU (2022.naacl-industry)

Copied to clipboard

Challenge: a new approach to annotate live traffic is emerging to be cost-effective and efficient . manual data annotation is expensive and not preferred for meeting customer privacy expectations .
Approach: They propose a targeted synthetic data generation technique by inserting tokens into a given semantic signature.
Outcome: The proposed approach achieves the same accuracy as training with all available data on a voice assistant dataset.
Multi-task Learning of Spoken Language Understanding by Integrating N-Best Hypotheses with Hierarchical Attention (2020.coling-industry)

Copied to clipboard

Challenge: Existing methods to integrate hypotheses into speech recognition systems are noisy and can cause information loss.
Approach: They propose to integrate hypotheses into multi-task learning and transfer learning to improve performance.
Outcome: The proposed model improves domain and intent classification by 19% and 37% compared to current methods . the proposed model could recover transcription and rewrite the query for a better understanding .

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations