Search Results - "Wang, Sida I"

Accessing Higher Dimensions for Unsupervised Word Translation by Wang, Sida I

“…The striking ability of unsupervised word translation has been demonstrated with the help of word vectors / pretraining; however, they require large amounts of…”
Get full text

Learning Adaptive Language Interfaces Through Interaction by Wang, Sida I

“…Natural language interfaces have the potential to complement GUIs and programming for many tasks, and enable all of us to better communicate with computers…”
Get full text

Bilingual Lexicon Induction via Unsupervised Bitext Construction and Word Alignment by Shi, Haoyue, Zettlemoyer, Luke, Wang, Sida I

“…Bilingual lexicons map words in one language to their translations in another, and are typically induced by learning linear projections to align monolingual…”
Get full text

CRUXEval: A Benchmark for Code Reasoning, Understanding and Execution by Gu, Alex, Rozière, Baptiste, Leather, Hugh, Solar-Lezama, Armando, Synnaeve, Gabriel, Wang, Sida I

“…We present CRUXEval (Code Reasoning, Understanding, and eXecution Evaluation), a benchmark consisting of 800 Python functions (3-13 lines). Each function comes…”
Get full text

BitextEdit: Automatic Bitext Editing for Improved Low-Resource Machine Translation by Briakou, Eleftheria, Wang, Sida I, Zettlemoyer, Luke, Ghazvininejad, Marjan

“…Mined bitexts can contain imperfect translations that yield unreliable training signals for Neural Machine Translation (NMT). While filtering such pairs out is…”
Get full text

Learning to Simulate Natural Language Feedback for Interactive Semantic Parsing by Yan, Hao, Srivastava, Saurabh, Tai, Yintao, Wang, Sida I, Yih, Wen-tau, Yao, Ziyu

“…Interactive semantic parsing based on natural language (NL) feedback, where users provide feedback to correct the parser mistakes, has emerged as a more…”
Get full text

Grounded Adaptation for Zero-shot Executable Semantic Parsing by Zhong, Victor, Lewis, Mike, Wang, Sida I, Zettlemoyer, Luke

“…We propose Grounded Adaptation for Zero-shot Executable Semantic Parsing (GAZP) to adapt an existing semantic parser to new environments (e.g. new database…”
Get full text

Natural Language to Code Translation with Execution by Shi, Freda, Fried, Daniel, Ghazvininejad, Marjan, Zettlemoyer, Luke, Wang, Sida I

“…Generative models of code, pretrained on large corpora of programs, have shown great success in translating natural language to code (Chen et al., 2021; Austin…”
Get full text

LEVER: Learning to Verify Language-to-Code Generation with Execution by Ni, Ansong, Iyer, Srini, Radev, Dragomir, Stoyanov, Ves, Yih, Wen-tau, Wang, Sida I, Lin, Xi Victoria

“…The advent of large language models trained on code (code LLMs) has led to significant progress in language-to-code generation. State-of-the-art approaches in…”
Get full text

SWE-bench Multimodal: Do AI Systems Generalize to Visual Software Domains? by Yang, John, Jimenez, Carlos E, Zhang, Alex L, Lieret, Kilian, Yang, Joyce, Wu, Xindi, Press, Ori, Muennighoff, Niklas, Synnaeve, Gabriel, Narasimhan, Karthik R, Yang, Diyi, Wang, Sida I, Press, Ofir

“…Autonomous systems for software engineering are now capable of fixing bugs and developing features. These systems are commonly evaluated on SWE-bench (Jimenez…”
Get full text

Coder Reviewer Reranking for Code Generation by Zhang, Tianyi, Yu, Tao, Hashimoto, Tatsunori B, Lewis, Mike, Yih, Wen-tau, Fried, Daniel, Wang, Sida I

“…Sampling diverse programs from a code language model and reranking with model likelihood is a popular method for code generation but it is prone to preferring…”
Get full text

SILG: The Multi-environment Symbolic Interactive Language Grounding Benchmark by Zhong, Victor, Hanjie, Austin W, Wang, Sida I, Narasimhan, Karthik, Zettlemoyer, Luke

“…Existing work in language grounding typically study single environments. How do we build unified models that apply across multiple environments? We propose the…”
Get full text

A sub-constant improvement in approximating the positive semidefinite Grothendieck problem by Frostig, Roy, Wang, Sida I

“…Semidefinite relaxations are a powerful tool for approximately solving combinatorial optimization problems such as MAX-CUT and the Grothendieck problem. By…”
Get full text

Naturalizing a Programming Language via Interactive Learning by Wang, Sida I, Ginn, Samuel, Liang, Percy, Manning, Christoper D

“…Our goal is to create a convenient natural language interface for performing well-specified but complex actions such as analyzing data, manipulating text, and…”
Get full text

UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models by Xie, Tianbao, Wu, Chen Henry, Shi, Peng, Zhong, Ruiqi, Scholak, Torsten, Yasunaga, Michihiro, Wu, Chien-Sheng, Zhong, Ming, Yin, Pengcheng, Wang, Sida I, Zhong, Victor, Wang, Bailin, Li, Chengzu, Boyle, Connor, Ni, Ansong, Yao, Ziyu, Radev, Dragomir, Xiong, Caiming, Kong, Lingpeng, Zhang, Rui, Smith, Noah A, Zettlemoyer, Luke, Yu, Tao

“…Structured knowledge grounding (SKG) leverages structured knowledge to complete user requests, such as semantic parsing over databases and question answering…”
Get full text

Learning Language Games through Interaction by Wang, Sida I, Liang, Percy, Manning, Christopher D

“…We introduce a new language learning setting relevant to building adaptive natural language interfaces. It is inspired by Wittgenstein's language games: a…”
Get full text

Estimating Mixture Models via Mixtures of Polynomials by Wang, Sida I, Chaganty, Arun Tejasvi, Liang, Percy

“…Mixture modeling is a general technique for making any simple model more expressive through weighted combination. This generality and simplicity in part…”
Get full text

Simple Recurrent Units for Highly Parallelizable Recurrence by Lei, Tao, Zhang, Yu, Wang, Sida I, Dai, Hui, Artzi, Yoav

“…Common recurrent neural architectures scale poorly due to the intrinsic difficulty in parallelizing their state computations. In this work, we propose the…”
Get full text

Data Noising as Smoothing in Neural Network Language Models by Xie, Ziang, Wang, Sida I, Li, Jiwei, Lévy, Daniel, Nie, Aiming, Jurafsky, Dan, Ng, Andrew Y

“…Data noising is an effective technique for regularizing neural network models. While noising is widely adopted in application domains such as vision and…”
Get full text

Relaxations for inference in restricted Boltzmann machines by Wang, Sida I, Frostig, Roy, Liang, Percy, Manning, Christopher D

“…We propose a relaxation-based approximate inference algorithm that samples near-MAP configurations of a binary pairwise Markov random field. We experiment on…”
Get full text