Search Results for author: Maryam Fazel-Zarandi

Found 16 papers, 6 papers with code

PathFinder: Guided Search over Multi-Step Reasoning Paths

no code implementations8 Dec 2023 Olga Golovneva, Sean O'Brien, Ramakanth Pasunuru, Tianlu Wang, Luke Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz

Using constrained reasoning, PathFinder integrates novel quality constraints, pruning, and exploration methods to enhance the efficiency and the quality of generation.


DOMINO: A Dual-System for Multi-step Visual Language Reasoning

1 code implementation4 Oct 2023 Peifang Wang, Olga Golovneva, Armen Aghajanyan, Xiang Ren, Muhao Chen, Asli Celikyilmaz, Maryam Fazel-Zarandi

By fine-tuning the System-2 module (LLaMA-2 70B) on only a small amount of data on multi-step reasoning, the accuracy of our method is further improved and surpasses the best fully-supervised end-to-end approach by 5. 7% and a pipeline approach with FlanPaLM (540B) by 7. 5% on a challenging dataset with human-authored questions.

Arithmetic Reasoning Language Modelling +2

Shepherd: A Critic for Language Model Generation

1 code implementation8 Aug 2023 Tianlu Wang, Ping Yu, Xiaoqing Ellen Tan, Sean O'Brien, Ramakanth Pasunuru, Jane Dwivedi-Yu, Olga Golovneva, Luke Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz

As large language models improve, there is increasing interest in techniques that leverage these models' capabilities to refine their own outputs.

Language Modelling

Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source Speech

no code implementations20 Mar 2023 Maryam Fazel-Zarandi, Wei-Ning Hsu

Self-supervised learning leverages unlabeled data effectively, improving label efficiency and generalization to domains without labeled data.

Self-Supervised Learning

ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning

1 code implementation15 Dec 2022 Olga Golovneva, Moya Chen, Spencer Poff, Martin Corredor, Luke Zettlemoyer, Maryam Fazel-Zarandi, Asli Celikyilmaz

Large language models show improved downstream task performance when prompted to generate step-by-step reasoning to justify their final answers.

Informativeness Text Generation

Logical Reasoning for Task Oriented Dialogue Systems

no code implementations ECNLP (ACL) 2022 Sajjad Beygi, Maryam Fazel-Zarandi, Alessandra Cervone, Prakash Krishnan, Siddhartha Reddy Jonnalagadda

We observe that transformer based models such as UnifiedQA-T5 can be fine-tuned to perform logical reasoning (such as numerical and categorical attributes' comparison) over attributes that been seen in training time (e. g., accuracy of 90\%+ for comparison of smaller than $k_{\max}$=5 values over heldout test dataset).

Logical Reasoning Negation +2

Dialog Simulation with Realistic Variations for Training Goal-Oriented Conversational Systems

no code implementations16 Nov 2020 Chien-Wei Lin, Vincent Auvray, Daniel Elkind, Arijit Biswas, Maryam Fazel-Zarandi, Nehal Belgamwar, Shubhra Chandra, Matt Zhao, Angeliki Metallinou, Tagyoung Chung, Charlie Shucheng Zhu, Suranjit Adhikari, Dilek Hakkani-Tur

Our approach includes a novel goal-sampling technique for sampling plausible user goals and a dialog simulation technique that uses heuristic interplay between the user and the system (Alexa), where the user tries to achieve the sampled goal.

Goal-Oriented Dialog Natural Language Understanding

Data Augmentation for Training Dialog Models Robust to Speech Recognition Errors

no code implementations WS 2020 Longshaokan Wang, Maryam Fazel-Zarandi, Aditya Tiwari, Spyros Matsoukas, Lazaros Polymenakos

Speech-based virtual assistants, such as Amazon Alexa, Google assistant, and Apple Siri, typically convert users' audio signals to text data through automatic speech recognition (ASR) and feed the text to downstream dialog models for natural language understanding and response generation.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Towards Personalized Dialog Policies for Conversational Skill Discovery

no code implementations15 Nov 2019 Maryam Fazel-Zarandi, Sampat Biswas, Ryan Summers, Ahmed Elmalt, Andy McCraw, Michael McPhilips, John Peach

Many businesses and consumers are extending the capabilities of voice-based services such as Amazon Alexa, Google Home, Microsoft Cortana, and Apple Siri to create custom voice experiences (also known as skills).

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