Alert button
Picture for Raymond Li

Raymond Li

Alert button

University of British Columbia

Diversity-Aware Coherence Loss for Improving Neural Topic Models

May 26, 2023
Raymond Li, Felipe González-Pizarro, Linzi Xing, Gabriel Murray, Giuseppe Carenini

Figure 1 for Diversity-Aware Coherence Loss for Improving Neural Topic Models
Figure 2 for Diversity-Aware Coherence Loss for Improving Neural Topic Models
Figure 3 for Diversity-Aware Coherence Loss for Improving Neural Topic Models
Figure 4 for Diversity-Aware Coherence Loss for Improving Neural Topic Models

The standard approach for neural topic modeling uses a variational autoencoder (VAE) framework that jointly minimizes the KL divergence between the estimated posterior and prior, in addition to the reconstruction loss. Since neural topic models are trained by recreating individual input documents, they do not explicitly capture the coherence between topic words on the corpus level. In this work, we propose a novel diversity-aware coherence loss that encourages the model to learn corpus-level coherence scores while maintaining a high diversity between topics. Experimental results on multiple datasets show that our method significantly improves the performance of neural topic models without requiring any pretraining or additional parameters.

* Minor Fixes, 11 pages, Camera-Ready for ACL 2023 (Short Paper) 
Viaarxiv icon

StarCoder: may the source be with you!

May 09, 2023
Raymond Li, Loubna Ben Allal, Yangtian Zi, Niklas Muennighoff, Denis Kocetkov, Chenghao Mou, Marc Marone, Christopher Akiki, Jia Li, Jenny Chim, Qian Liu, Evgenii Zheltonozhskii, Terry Yue Zhuo, Thomas Wang, Olivier Dehaene, Mishig Davaadorj, Joel Lamy-Poirier, João Monteiro, Oleh Shliazhko, Nicolas Gontier, Nicholas Meade, Armel Zebaze, Ming-Ho Yee, Logesh Kumar Umapathi, Jian Zhu, Benjamin Lipkin, Muhtasham Oblokulov, Zhiruo Wang, Rudra Murthy, Jason Stillerman, Siva Sankalp Patel, Dmitry Abulkhanov, Marco Zocca, Manan Dey, Zhihan Zhang, Nour Fahmy, Urvashi Bhattacharyya, Wenhao Yu, Swayam Singh, Sasha Luccioni, Paulo Villegas, Maxim Kunakov, Fedor Zhdanov, Manuel Romero, Tony Lee, Nadav Timor, Jennifer Ding, Claire Schlesinger, Hailey Schoelkopf, Jan Ebert, Tri Dao, Mayank Mishra, Alex Gu, Jennifer Robinson, Carolyn Jane Anderson, Brendan Dolan-Gavitt, Danish Contractor, Siva Reddy, Daniel Fried, Dzmitry Bahdanau, Yacine Jernite, Carlos Muñoz Ferrandis, Sean Hughes, Thomas Wolf, Arjun Guha, Leandro von Werra, Harm de Vries

Figure 1 for StarCoder: may the source be with you!
Figure 2 for StarCoder: may the source be with you!
Figure 3 for StarCoder: may the source be with you!
Figure 4 for StarCoder: may the source be with you!

The BigCode community, an open-scientific collaboration working on the responsible development of Large Language Models for Code (Code LLMs), introduces StarCoder and StarCoderBase: 15.5B parameter models with 8K context length, infilling capabilities and fast large-batch inference enabled by multi-query attention. StarCoderBase is trained on 1 trillion tokens sourced from The Stack, a large collection of permissively licensed GitHub repositories with inspection tools and an opt-out process. We fine-tuned StarCoderBase on 35B Python tokens, resulting in the creation of StarCoder. We perform the most comprehensive evaluation of Code LLMs to date and show that StarCoderBase outperforms every open Code LLM that supports multiple programming languages and matches or outperforms the OpenAI code-cushman-001 model. Furthermore, StarCoder outperforms every model that is fine-tuned on Python, can be prompted to achieve 40\% pass@1 on HumanEval, and still retains its performance on other programming languages. We take several important steps towards a safe open-access model release, including an improved PII redaction pipeline and a novel attribution tracing tool, and make the StarCoder models publicly available under a more commercially viable version of the Open Responsible AI Model license.

Viaarxiv icon

NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

Mar 27, 2023
Rindranirina Ramamonjison, Timothy T. Yu, Raymond Li, Haley Li, Giuseppe Carenini, Bissan Ghaddar, Shiqi He, Mahdi Mostajabdaveh, Amin Banitalebi-Dehkordi, Zirui Zhou, Yong Zhang

Figure 1 for NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
Figure 2 for NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
Figure 3 for NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions
Figure 4 for NL4Opt Competition: Formulating Optimization Problems Based on Their Natural Language Descriptions

The Natural Language for Optimization (NL4Opt) Competition was created to investigate methods of extracting the meaning and formulation of an optimization problem based on its text description. Specifically, the goal of the competition is to increase the accessibility and usability of optimization solvers by allowing non-experts to interface with them using natural language. We separate this challenging goal into two sub-tasks: (1) recognize and label the semantic entities that correspond to the components of the optimization problem; (2) generate a meaning representation (i.e., a logical form) of the problem from its detected problem entities. The first task aims to reduce ambiguity by detecting and tagging the entities of the optimization problems. The second task creates an intermediate representation of the linear programming (LP) problem that is converted into a format that can be used by commercial solvers. In this report, we present the LP word problem dataset and shared tasks for the NeurIPS 2022 competition. Furthermore, we investigate and compare the performance of the ChatGPT large language model against the winning solutions. Through this competition, we hope to bring interest towards the development of novel machine learning applications and datasets for optimization modeling.

Viaarxiv icon

SantaCoder: don't reach for the stars!

Jan 09, 2023
Loubna Ben Allal, Raymond Li, Denis Kocetkov, Chenghao Mou, Christopher Akiki, Carlos Munoz Ferrandis, Niklas Muennighoff, Mayank Mishra, Alex Gu, Manan Dey, Logesh Kumar Umapathi, Carolyn Jane Anderson, Yangtian Zi, Joel Lamy Poirier, Hailey Schoelkopf, Sergey Troshin, Dmitry Abulkhanov, Manuel Romero, Michael Lappert, Francesco De Toni, Bernardo García del Río, Qian Liu, Shamik Bose, Urvashi Bhattacharyya, Terry Yue Zhuo, Ian Yu, Paulo Villegas, Marco Zocca, Sourab Mangrulkar, David Lansky, Huu Nguyen, Danish Contractor, Luis Villa, Jia Li, Dzmitry Bahdanau, Yacine Jernite, Sean Hughes, Daniel Fried, Arjun Guha, Harm de Vries, Leandro von Werra

Figure 1 for SantaCoder: don't reach for the stars!
Figure 2 for SantaCoder: don't reach for the stars!
Figure 3 for SantaCoder: don't reach for the stars!
Figure 4 for SantaCoder: don't reach for the stars!

The BigCode project is an open-scientific collaboration working on the responsible development of large language models for code. This tech report describes the progress of the collaboration until December 2022, outlining the current state of the Personally Identifiable Information (PII) redaction pipeline, the experiments conducted to de-risk the model architecture, and the experiments investigating better preprocessing methods for the training data. We train 1.1B parameter models on the Java, JavaScript, and Python subsets of The Stack and evaluate them on the MultiPL-E text-to-code benchmark. We find that more aggressive filtering of near-duplicates can further boost performance and, surprisingly, that selecting files from repositories with 5+ GitHub stars deteriorates performance significantly. Our best model outperforms previous open-source multilingual code generation models (InCoder-6.7B and CodeGen-Multi-2.7B) in both left-to-right generation and infilling on the Java, JavaScript, and Python portions of MultiPL-E, despite being a substantially smaller model. All models are released under an OpenRAIL license at https://hf.co/bigcode.

Viaarxiv icon

The Stack: 3 TB of permissively licensed source code

Nov 20, 2022
Denis Kocetkov, Raymond Li, Loubna Ben Allal, Jia Li, Chenghao Mou, Carlos Muñoz Ferrandis, Yacine Jernite, Margaret Mitchell, Sean Hughes, Thomas Wolf, Dzmitry Bahdanau, Leandro von Werra, Harm de Vries

Figure 1 for The Stack: 3 TB of permissively licensed source code
Figure 2 for The Stack: 3 TB of permissively licensed source code
Figure 3 for The Stack: 3 TB of permissively licensed source code
Figure 4 for The Stack: 3 TB of permissively licensed source code

Large Language Models (LLMs) play an ever-increasing role in the field of Artificial Intelligence (AI)--not only for natural language processing but also for code understanding and generation. To stimulate open and responsible research on LLMs for code, we introduce The Stack, a 3.1 TB dataset consisting of permissively licensed source code in 30 programming languages. We describe how we collect the full dataset, construct a permissively licensed subset, present a data governance plan, discuss limitations, and show promising results on text2code benchmarks by training 350M-parameter decoders on different Python subsets. We find that (1) near-deduplicating the data significantly boosts performance across all experiments, and (2) it is possible to match previously reported HumanEval and MBPP performance using only permissively licensed data. We make the dataset available at https://hf.co/BigCode, provide a tool called "Am I in The Stack" (https://hf.co/spaces/bigcode/in-the-stack) for developers to search The Stack for copies of their code, and provide a process for code to be removed from the dataset by following the instructions at https://www.bigcode-project.org/docs/about/the-stack/.

Viaarxiv icon

OSLAT: Open Set Label Attention Transformer for Medical Entity Span Extraction

Jul 12, 2022
Raymond Li, Ilya Valmianski, Li Deng, Xavier Amatriain, Anitha Kannan

Figure 1 for OSLAT: Open Set Label Attention Transformer for Medical Entity Span Extraction
Figure 2 for OSLAT: Open Set Label Attention Transformer for Medical Entity Span Extraction
Figure 3 for OSLAT: Open Set Label Attention Transformer for Medical Entity Span Extraction
Figure 4 for OSLAT: Open Set Label Attention Transformer for Medical Entity Span Extraction

Identifying spans in medical texts that correspond to medical entities is one of the core steps for many healthcare NLP tasks such as ICD coding, medical finding extraction, medical note contextualization, to name a few. Existing entity extraction methods rely on a fixed and limited vocabulary of medical entities and have difficulty with extracting entities represented by disjoint spans. In this paper, we present a new transformer-based architecture called OSLAT, Open Set Label Attention Transformer, that addresses many of the limitations of the previous methods. Our approach uses the label-attention mechanism to implicitly learn spans associated with entities of interest. These entities can be provided as free text, including entities not seen during OSLAT's training, and the model can extract spans even when they are disjoint. To test the generalizability of our method, we train two separate models on two different datasets, which have very low entity overlap: (1) a public discharge notes dataset from hNLP, and (2) a much more challenging proprietary patient text dataset "Reasons for Encounter" (RFE). We find that OSLAT models trained on either dataset outperform rule-based and fuzzy string matching baselines when applied to the RFE dataset as well as to the portion of hNLP dataset where entities are represented by disjoint spans. Our code can be found at https://github.com/curai/curai-research/tree/main/OSLAT.

* 16 pages, 2 figures 
Viaarxiv icon

Evaluating the Text-to-SQL Capabilities of Large Language Models

Mar 15, 2022
Nitarshan Rajkumar, Raymond Li, Dzmitry Bahdanau

Figure 1 for Evaluating the Text-to-SQL Capabilities of Large Language Models
Figure 2 for Evaluating the Text-to-SQL Capabilities of Large Language Models
Figure 3 for Evaluating the Text-to-SQL Capabilities of Large Language Models
Figure 4 for Evaluating the Text-to-SQL Capabilities of Large Language Models

We perform an empirical evaluation of Text-to-SQL capabilities of the Codex language model. We find that, without any finetuning, Codex is a strong baseline on the Spider benchmark; we also analyze the failure modes of Codex in this setting. Furthermore, we demonstrate on the GeoQuery and Scholar benchmarks that a small number of in-domain examples provided in the prompt enables Codex to perform better than state-of-the-art models finetuned on such few-shot examples.

Viaarxiv icon

Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization

Dec 10, 2021
Raymond Li, Wen Xiao, Lanjun Wang, Giuseppe Carenini

Figure 1 for Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization
Figure 2 for Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization
Figure 3 for Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization
Figure 4 for Human Interpretation and Exploitation of Self-attention Patterns in Transformers: A Case Study in Extractive Summarization

The transformer multi-head self-attention mechanism has been thoroughly investigated recently. On one hand, researchers are interested in understanding why and how transformers work. On the other hand, they propose new attention augmentation methods to make transformers more accurate, efficient and interpretable. In this paper, we synergize these two lines of research in a human-in-the-loop pipeline to first find important task-specific attention patterns. Then those patterns are applied, not only to the original model, but also to smaller models, as a human-guided knowledge distillation process. The benefits of our pipeline are demonstrated in a case study with the extractive summarization task. After finding three meaningful attention patterns in the popular BERTSum model, experiments indicate that when we inject such patterns, both the original and the smaller model show improvements in performance and arguably interpretability.

Viaarxiv icon

T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP

Aug 31, 2021
Raymond Li, Wen Xiao, Lanjun Wang, Hyeju Jang, Giuseppe Carenini

Figure 1 for T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
Figure 2 for T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
Figure 3 for T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP
Figure 4 for T3-Vis: a visual analytic framework for Training and fine-Tuning Transformers in NLP

Transformers are the dominant architecture in NLP, but their training and fine-tuning is still very challenging. In this paper, we present the design and implementation of a visual analytic framework for assisting researchers in such process, by providing them with valuable insights about the model's intrinsic properties and behaviours. Our framework offers an intuitive overview that allows the user to explore different facets of the model (e.g., hidden states, attention) through interactive visualization, and allows a suite of built-in algorithms that compute the importance of model components and different parts of the input sequence. Case studies and feedback from a user focus group indicate that the framework is useful, and suggest several improvements.

* 10 pages, 4 figures, accepted to EMNLP 2021 System Demonstration 
Viaarxiv icon