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

no code implementations • 12 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

Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency

no code implementations • 31 May 2023 • Maxwell Crouse, Ramon Astudillo, Tahira Naseem, Subhajit Chaudhury, Pavan Kapanipathi, Salim Roukos, Alexander Gray

We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser.

Self-Learning Text Generation +2

Laziness Is a Virtue When It Comes to Compositionality in Neural Semantic Parsing

no code implementations • 7 May 2023 • Maxwell Crouse, Pavan Kapanipathi, Subhajit Chaudhury, Tahira Naseem, Ramon Astudillo, Achille Fokoue, Tim Klinger

Nearly all general-purpose neural semantic parsers generate logical forms in a strictly top-down autoregressive fashion.

Text-To-SQL

Leveraging Abstract Meaning Representation for Knowledge Base Question Answering

1 code implementation • Findings (ACL) 2021 • Pavan Kapanipathi, Ibrahim Abdelaziz, Srinivas Ravishankar, Salim Roukos, Alexander Gray, Ramon Astudillo, Maria Chang, Cristina Cornelio, Saswati Dana, Achille Fokoue, Dinesh Garg, Alfio Gliozzo, Sairam Gurajada, Hima Karanam, Naweed Khan, Dinesh Khandelwal, Young-suk Lee, Yunyao Li, Francois Luus, Ndivhuwo Makondo, Nandana Mihindukulasooriya, Tahira Naseem, Sumit Neelam, Lucian Popa, Revanth Reddy, Ryan Riegel, Gaetano Rossiello, Udit Sharma, G P Shrivatsa Bhargav, Mo Yu

Knowledge base question answering (KBQA)is an important task in Natural Language Processing.

Abstract Meaning Representation Entity Linking +2

Semi-supervised Sequence-to-sequence ASR using Unpaired Speech and Text

no code implementations • 30 Apr 2019 • Murali Karthick Baskar, Shinji Watanabe, Ramon Astudillo, Takaaki Hori, Lukáš Burget, Jan Černocký

Such techniques derive training procedures and losses able to leverage unpaired speech and/or text data by combining ASR with Text-to-Speech (TTS) models.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +3

Cycle-consistency training for end-to-end speech recognition

no code implementations • 2 Nov 2018 • Takaaki Hori, Ramon Astudillo, Tomoki Hayashi, Yu Zhang, Shinji Watanabe, Jonathan Le Roux

To solve this problem, this work presents a loss that is based on the speech encoder state sequence instead of the raw speech signal.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +4

Back-Translation-Style Data Augmentation for End-to-End ASR

no code implementations • 28 Jul 2018 • Tomoki Hayashi, Shinji Watanabe, Yu Zhang, Tomoki Toda, Takaaki Hori, Ramon Astudillo, Kazuya Takeda

In this paper we propose a novel data augmentation method for attention-based end-to-end automatic speech recognition (E2E-ASR), utilizing a large amount of text which is not paired with speech signals.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +5

Fusion of Simple Models for Native Language Identification

no code implementations • WS 2017 • Fabio Kepler, Ramon Astudillo, Alberto Abad

In this paper we describe the approaches we explored for the 2017 Native Language Identification shared task.

Information Retrieval Native Language Identification

INESC-ID at SemEval-2016 Task 4-A: Reducing the Problem of Out-of-Embedding Words

no code implementations • SEMEVAL 2016 • Silvio Amir, Ramon Astudillo, Wang Ling, M{\'a}rio J. Silva, Isabel Trancoso

Feature Engineering Twitter Sentiment Analysis +1

Learning Word Representations from Scarce and Noisy Data with Embedding Subspaces

no code implementations • IJCNLP 2015 • Ramon Astudillo, Silvio Amir, Wang Ling, M{\'a}rio Silva, Isabel Trancoso

Part-Of-Speech Tagging Twitter Sentiment Analysis +1

INESC-ID: A Regression Model for Large Scale Twitter Sentiment Lexicon Induction

no code implementations • SEMEVAL 2015 • Silvio Amir, Ramon Astudillo, Wang Ling, Bruno Martins, Mario J. Silva, Isabel Trancoso

regression Twitter Sentiment Analysis +1

INESC-ID: Sentiment Analysis without Hand-Coded Features or Linguistic Resources using Embedding Subspaces

no code implementations • SEMEVAL 2015 • Ramon Astudillo, Silvio Amir, Wang Ling, Bruno Martins, Mario J. Silva, Isabel Trancoso

Feature Engineering Twitter Sentiment Analysis +1