Search Results for author: Salim Roukos

Found 38 papers, 12 papers with code

Zero-shot Entity Linking with Less Data

2 code implementations Findings (NAACL) 2022 G P Shrivatsa Bhargav, Dinesh Khandelwal, Saswati Dana, Dinesh Garg, Pavan Kapanipathi, Salim Roukos, Alexander Gray, L Venkata Subramaniam

Interestingly, we discovered that BLINK exhibits diminishing returns, i. e., it reaches 98% of its performance with just 1% of the training data and the remaining 99% of the data yields only a marginal increase of 2% in the performance.

Entity Linking Multi-Task Learning +2

Ensemble-Instruct: Generating Instruction-Tuning Data with a Heterogeneous Mixture of LMs

1 code implementation21 Oct 2023 Young-suk Lee, Md Arafat Sultan, Yousef El-Kurdi, Tahira Naseem Asim Munawar, Radu Florian, Salim Roukos, Ramón Fernandez Astudillo

Using in-context learning (ICL) for data generation, techniques such as Self-Instruct (Wang et al., 2023) or the follow-up Alpaca (Taori et al., 2023) can train strong conversational agents with only a small amount of human supervision.

In-Context Learning

Formally Specifying the High-Level Behavior of LLM-Based Agents

no code implementations12 Oct 2023 Maxwell Crouse, Ibrahim Abdelaziz, Ramon Astudillo, Kinjal Basu, Soham Dan, Sadhana Kumaravel, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Luis Lastras

We demonstrate how the proposed framework can be used to implement recent LLM-based agents (e. g., ReACT), and show how the flexibility of our approach can be leveraged to define a new agent with more complex behavior, the Plan-Act-Summarize-Solve (PASS) agent.

Question Answering

AMR Parsing with Instruction Fine-tuned Pre-trained Language Models

no code implementations24 Apr 2023 Young-suk Lee, Ramón Fernandez Astudillo, Radu Florian, Tahira Naseem, Salim Roukos

Instruction fine-tuned language models on a collection of instruction annotated datasets (FLAN) have shown highly effective to improve model performance and generalization to unseen tasks.

AMR Parsing Semantic Role Labeling

PrimeQA: The Prime Repository for State-of-the-Art Multilingual Question Answering Research and Development

1 code implementation23 Jan 2023 Avirup Sil, Jaydeep Sen, Bhavani Iyer, Martin Franz, Kshitij Fadnis, Mihaela Bornea, Sara Rosenthal, Scott McCarley, Rong Zhang, Vishwajeet Kumar, Yulong Li, Md Arafat Sultan, Riyaz Bhat, Radu Florian, Salim Roukos

The field of Question Answering (QA) has made remarkable progress in recent years, thanks to the advent of large pre-trained language models, newer realistic benchmark datasets with leaderboards, and novel algorithms for key components such as retrievers and readers.

Question Answering Reading Comprehension +1

Moving Beyond Downstream Task Accuracy for Information Retrieval Benchmarking

no code implementations2 Dec 2022 Keshav Santhanam, Jon Saad-Falcon, Martin Franz, Omar Khattab, Avirup Sil, Radu Florian, Md Arafat Sultan, Salim Roukos, Matei Zaharia, Christopher Potts

Neural information retrieval (IR) systems have progressed rapidly in recent years, in large part due to the release of publicly available benchmarking tasks.

Benchmarking Information Retrieval +1

A Closer Look at the Calibration of Differentially Private Learners

no code implementations15 Oct 2022 HANLIN ZHANG, Xuechen Li, Prithviraj Sen, Salim Roukos, Tatsunori Hashimoto

Across 7 tasks, temperature scaling and Platt scaling with DP-SGD result in an average 3. 1-fold reduction in the in-domain expected calibration error and only incur at most a minor percent drop in accuracy.

A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases

no code implementations15 Jan 2022 Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G P Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Maria Chang, Rosario Uceda-Sosa, Salim Roukos, Alexander Gray, Guilherme Lima, Ryan Riegel, Francois Luus, L Venkata Subramaniam

Specifically, our benchmark is a temporal question answering dataset with the following advantages: (a) it is based on Wikidata, which is the most frequently curated, openly available knowledge base, (b) it includes intermediate sparql queries to facilitate the evaluation of semantic parsing based approaches for KBQA, and (c) it generalizes to multiple knowledge bases: Freebase and Wikidata.

Knowledge Base Question Answering Semantic Parsing

DocAMR: Multi-Sentence AMR Representation and Evaluation

1 code implementation NAACL 2022 Tahira Naseem, Austin Blodgett, Sadhana Kumaravel, Tim O'Gorman, Young-suk Lee, Jeffrey Flanigan, Ramón Fernandez Astudillo, Radu Florian, Salim Roukos, Nathan Schneider

Despite extensive research on parsing of English sentences into Abstraction Meaning Representation (AMR) graphs, which are compared to gold graphs via the Smatch metric, full-document parsing into a unified graph representation lacks well-defined representation and evaluation.

coreference-resolution Sentence

Learning to Transpile AMR into SPARQL

no code implementations15 Dec 2021 Mihaela Bornea, Ramon Fernandez Astudillo, Tahira Naseem, Nandana Mihindukulasooriya, Ibrahim Abdelaziz, Pavan Kapanipathi, Radu Florian, Salim Roukos

We propose a transition-based system to transpile Abstract Meaning Representation (AMR) into SPARQL for Knowledge Base Question Answering (KBQA).

Knowledge Base Question Answering Semantic Parsing

Maximum Bayes Smatch Ensemble Distillation for AMR Parsing

2 code implementations NAACL 2022 Young-suk Lee, Ramon Fernandez Astudillo, Thanh Lam Hoang, Tahira Naseem, Radu Florian, Salim Roukos

AMR parsing has experienced an unprecendented increase in performance in the last three years, due to a mixture of effects including architecture improvements and transfer learning.

 Ranked #1 on AMR Parsing on LDC2020T02 (using extra training data)

AMR Parsing Data Augmentation +3

Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing

1 code implementation EMNLP 2021 Jiawei Zhou, Tahira Naseem, Ramón Fernandez Astudillo, Young-suk Lee, Radu Florian, Salim Roukos

We provide a detailed comparison with recent progress in AMR parsing and show that the proposed parser retains the desirable properties of previous transition-based approaches, while being simpler and reaching the new parsing state of the art for AMR 2. 0, without the need for graph re-categorization.

Ranked #9 on AMR Parsing on LDC2017T10 (using extra training data)

AMR Parsing Sentence

Combining Rules and Embeddings via Neuro-Symbolic AI for Knowledge Base Completion

no code implementations16 Sep 2021 Prithviraj Sen, Breno W. S. R. Carvalho, Ibrahim Abdelaziz, Pavan Kapanipathi, Francois Luus, Salim Roukos, Alexander Gray

Recent interest in Knowledge Base Completion (KBC) has led to a plethora of approaches based on reinforcement learning, inductive logic programming and graph embeddings.

Inductive logic programming Knowledge Base Completion +1

Bootstrapping Multilingual AMR with Contextual Word Alignments

no code implementations EACL 2021 Janaki Sheth, Young-suk Lee, Ramon Fernandez Astudillo, Tahira Naseem, Radu Florian, Salim Roukos, Todd Ward

We develop high performance multilingualAbstract Meaning Representation (AMR) sys-tems by projecting English AMR annotationsto other languages with weak supervision.

Multilingual Word Embeddings Word Alignment +1

End-to-End QA on COVID-19: Domain Adaptation with Synthetic Training

no code implementations2 Dec 2020 Revanth Gangi Reddy, Bhavani Iyer, Md Arafat Sultan, Rong Zhang, Avi Sil, Vittorio Castelli, Radu Florian, Salim Roukos

End-to-end question answering (QA) requires both information retrieval (IR) over a large document collection and machine reading comprehension (MRC) on the retrieved passages.

Domain Adaptation Information Retrieval +3

Towards building a Robust Industry-scale Question Answering System

no code implementations COLING 2020 Rishav Chakravarti, Anthony Ferritto, Bhavani Iyer, Lin Pan, Radu Florian, Salim Roukos, Avi Sil

Building on top of the powerful BERTQA model, GAAMA provides a ∼2. 0{\%} absolute boost in F1 over the industry-scale state-of-the-art (SOTA) system on NQ.

Data Augmentation Natural Questions +2

Pushing the Limits of AMR Parsing with Self-Learning

1 code implementation Findings of the Association for Computational Linguistics 2020 Young-suk Lee, Ramon Fernandez Astudillo, Tahira Naseem, Revanth Gangi Reddy, Radu Florian, Salim Roukos

Abstract Meaning Representation (AMR) parsing has experienced a notable growth in performance in the last two years, due both to the impact of transfer learning and the development of novel architectures specific to AMR.

AMR Parsing Machine Translation +4

ARES: A Reading Comprehension Ensembling Service

no code implementations EMNLP 2020 Anthony Ferritto, Lin Pan, Rishav Chakravarti, Salim Roukos, Radu Florian, J. William Murdock, Avi Sil

We introduce ARES (A Reading Comprehension Ensembling Service): a novel Machine Reading Comprehension (MRC) demonstration system which utilizes an ensemble of models to increase F1 by 2. 3 points.

Machine Reading Comprehension Natural Questions +1

Path-Based Contextualization of Knowledge Graphs for Textual Entailment

no code implementations5 Nov 2019 Kshitij Fadnis, Kartik Talamadupula, Pavan Kapanipathi, Haque Ishfaq, Salim Roukos, Achille Fokoue

In this paper, we introduce the problem of knowledge graph contextualization -- that is, given a specific NLP task, the problem of extracting meaningful and relevant sub-graphs from a given knowledge graph.

Knowledge Graphs Natural Language Inference

Ensembling Strategies for Answering Natural Questions

no code implementations30 Oct 2019 Anthony Ferritto, Lin Pan, Rishav Chakravarti, Salim Roukos, Radu Florian, J. William Murdock, Avirup Sil

Many of the top question answering systems today utilize ensembling to improve their performance on tasks such as the Stanford Question Answering Dataset (SQuAD) and Natural Questions (NQ) challenges.

Natural Questions Question Answering

Frustratingly Easy Natural Question Answering

no code implementations11 Sep 2019 Lin Pan, Rishav Chakravarti, Anthony Ferritto, Michael Glass, Alfio Gliozzo, Salim Roukos, Radu Florian, Avirup Sil

Existing literature on Question Answering (QA) mostly focuses on algorithmic novelty, data augmentation, or increasingly large pre-trained language models like XLNet and RoBERTa.

Data Augmentation Natural Questions +2

CFO: A Framework for Building Production NLP Systems

no code implementations IJCNLP 2019 Rishav Chakravarti, Cezar Pendus, Andrzej Sakrajda, Anthony Ferritto, Lin Pan, Michael Glass, Vittorio Castelli, J. William Murdock, Radu Florian, Salim Roukos, Avirup Sil

This paper introduces a novel orchestration framework, called CFO (COMPUTATION FLOW ORCHESTRATOR), for building, experimenting with, and deploying interactive NLP (Natural Language Processing) and IR (Information Retrieval) systems to production environments.

Information Retrieval Machine Reading Comprehension +2

Rewarding Smatch: Transition-Based AMR Parsing with Reinforcement Learning

no code implementations ACL 2019 Tahira Naseem, Abhishek Shah, Hui Wan, Radu Florian, Salim Roukos, Miguel Ballesteros

Our work involves enriching the Stack-LSTM transition-based AMR parser (Ballesteros and Al-Onaizan, 2017) by augmenting training with Policy Learning and rewarding the Smatch score of sampled graphs.

AMR Parsing reinforcement-learning +1

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