In order for NLP technology to be widely applicable, fair, and useful, it needs to serve a diverse set of speakers across the world's languages, be equitable, i.e., not unduly biased towards any particular language, and be inclusive of all users, particularly in low-resource settings where compute constraints are common. In this paper, we propose an evaluation paradigm that assesses NLP technologies across all three dimensions. While diversity and inclusion have received attention in recent literature, equity is currently unexplored. We propose to address this gap using the Gini coefficient, a well-established metric used for estimating societal wealth inequality. Using our paradigm, we highlight the distressed state of current technologies for Indian (IN) languages (a linguistically large and diverse set, with a varied speaker population), across all three dimensions. To improve upon these metrics, we demonstrate the importance of region-specific choices in model building and dataset creation, and more importantly, propose a novel, generalisable approach to optimal resource allocation during fine-tuning. Finally, we discuss steps to mitigate these biases and encourage the community to employ multi-faceted evaluation when building linguistically diverse and equitable technologies.
相關內容
A seller is pricing identical copies of a good to a stream of unit-demand buyers. Each buyer has a value on the good as his private information. The seller only knows the empirical value distribution of the buyer population and chooses the revenue-optimal price. We consider a widely studied third-degree price discrimination model where an information intermediary with perfect knowledge of the arriving buyer's value sends a signal to the seller, hence changing the seller's posterior and inducing the seller to set a personalized posted price. Prior work of Bergemann, Brooks, and Morris (American Economic Review, 2015) has shown the existence of a signaling scheme that preserves seller revenue, while always selling the item, hence maximizing consumer surplus. In a departure from prior work, we ask whether the consumer surplus generated is fairly distributed among buyers with different values. To this end, we aim to maximize welfare functions that reward more balanced surplus allocations. Our main result is the surprising existence of a novel signaling scheme that simultaneously $8$-approximates all welfare functions that are non-negative, monotonically increasing, symmetric, and concave, compared with any other signaling scheme. Classical examples of such welfare functions include the utilitarian social welfare, the Nash welfare, and the max-min welfare. Such a guarantee cannot be given by any consumer-surplus-maximizing scheme -- which are the ones typically studied in the literature. In addition, our scheme is socially efficient, and has the fairness property that buyers with higher values enjoy higher expected surplus, which is not always the case for existing schemes.
Lexical matching remains the de facto evaluation method for open-domain question answering (QA). Unfortunately, lexical matching fails completely when a plausible candidate answer does not appear in the list of gold answers, which is increasingly the case as we shift from extractive to generative models. The recent success of large language models (LLMs) for QA aggravates lexical matching failures since candidate answers become longer, thereby making matching with the gold answers even more challenging. Without accurate evaluation, the true progress in open-domain QA remains unknown. In this paper, we conduct a thorough analysis of various open-domain QA models, including LLMs, by manually evaluating their answers on a subset of NQ-open, a popular benchmark. Our assessments reveal that while the true performance of all models is significantly underestimated, the performance of the InstructGPT (zero-shot) LLM increases by nearly +60%, making it on par with existing top models, and the InstructGPT (few-shot) model actually achieves a new state-of-the-art on NQ-open. We also find that more than 50% of lexical matching failures are attributed to semantically equivalent answers. We further demonstrate that regex matching ranks QA models consistent with human judgments, although still suffering from unnecessary strictness. Finally, we demonstrate that automated evaluation models are a reasonable surrogate for lexical matching in some circumstances, but not for long-form answers generated by LLMs. The automated models struggle in detecting hallucinations in LLM answers and are thus unable to evaluate LLMs. At this time, there appears to be no substitute for human evaluation.
NLP in the legal domain has seen increasing success with the emergence of Transformer-based Pre-trained Language Models (PLMs) pre-trained on legal text. PLMs trained over European and US legal text are available publicly; however, legal text from other domains (countries), such as India, have a lot of distinguishing characteristics. With the rapidly increasing volume of Legal NLP applications in various countries, it has become necessary to pre-train such LMs over legal text of other countries as well. In this work, we attempt to investigate pre-training in the Indian legal domain. We re-train (continue pre-training) two popular legal PLMs, LegalBERT and CaseLawBERT, on Indian legal data, as well as train a model from scratch with a vocabulary based on Indian legal text. We apply these PLMs over three benchmark legal NLP tasks -- Legal Statute Identification from facts, Semantic Segmentation of Court Judgment Documents, and Court Appeal Judgment Prediction -- over both Indian and non-Indian (EU, UK) datasets. We observe that our approach not only enhances performance on the new domain (Indian texts) but also over the original domain (European and UK texts). We also conduct explainability experiments for a qualitative comparison of all these different PLMs.
Online Controlled Experiments (OCEs) are the gold standard in evaluating the effectiveness of changes to websites. An important type of OCE evaluates different personalization strategies, which present challenges in low test power and lack of full control in group assignment. We argue that getting the right experiment setup -- the allocation of users to treatment/analysis groups -- should take precedence of post-hoc variance reduction techniques in order to enable the scaling of the number of experiments. We present an evaluation framework that, along with a few simple rule of thumbs, allow experimenters to quickly compare which experiment setup will lead to the highest probability of detecting a treatment effect under their particular circumstance.
This paper aims to benchmark recent progress in language understanding models that output contextualised representations at the character level. Many such modelling architectures and methods to train those architectures have been proposed, but it is currently unclear what the relative contributions of the architecture vs. the pretraining objective are to final model performance. We explore the design space of such models, comparing architectural innovations and a variety of different pretraining objectives on a suite of evaluation tasks with a fixed training procedure in order to find the currently optimal way to build and train character-level BERT-like models. We find that our best performing character-level model exceeds the performance of a token-based model trained with the same settings on the same data, suggesting that character-level models are ready for more widespread adoption. Unfortunately, the best method to train character-level models still relies on a subword-level tokeniser during pretraining, and final model performance is highly dependent on tokeniser quality. We believe our results demonstrate the readiness of character-level models for multilingual language representation, and encourage NLP practitioners to try them as drop-in replacements for token-based models.
Recent advancements in Large Language Models (LLMs) harness linguistic associations in vast natural language data for practical applications. However, their ability to understand the physical world using only language data remains a question. After reviewing existing protocols, we explore this question using a novel and tightly controlled reasoning test (ART) and compare human norms against versions of GPT-3. Our findings highlight the categories of common-sense relations models that could learn directly from data and areas of weakness. GPT-3 offers evidence for verbal reasoning on a par with human subjects for several relations including Synonymy, Antonymy, and Default inheritance, Without reinforcement learning from human judgements, it appears GPT-3 performs at the lower end of the reference interval for Has-part and Contained-in. Weaknesses were observed also in affordance characteristics through Necessary-quality, Order-of-size and Order-of-intensity. Combining LLMs with symbolic world grounding is a promising direction to address associative learning.
This research paper describes a realtime system for identifying American Sign Language (ASL) movements that employs modern computer vision and machine learning approaches. The suggested method makes use of the Mediapipe library for feature extraction and a Convolutional Neural Network (CNN) for ASL gesture classification. The testing results show that the suggested system can detect all ASL alphabets with an accuracy of 99.95%, indicating its potential for use in communication devices for people with hearing impairments. The proposed approach can also be applied to additional sign languages with similar hand motions, potentially increasing the quality of life for people with hearing loss. Overall, the study demonstrates the effectiveness of using Mediapipe and CNN for real-time sign language recognition, making a significant contribution to the field of computer vision and machine learning.
Unit testing is essential in detecting bugs in functionally-discrete program units. Manually writing high-quality unit tests is time-consuming and laborious. Although traditional techniques can generate tests with reasonable coverage, they exhibit low readability and cannot be directly adopted by developers. Recent work has shown the large potential of large language models (LLMs) in unit test generation, which can generate more human-like and meaningful test code. ChatGPT, the latest LLM incorporating instruction tuning and reinforcement learning, has performed well in various domains. However, It remains unclear how effective ChatGPT is in unit test generation. In this work, we perform the first empirical study to evaluate ChatGPT's capability of unit test generation. Specifically, we conduct a quantitative analysis and a user study to systematically investigate the quality of its generated tests regarding the correctness, sufficiency, readability, and usability. The tests generated by ChatGPT still suffer from correctness issues, including diverse compilation errors and execution failures. Still, the passing tests generated by ChatGPT resemble manually-written tests by achieving comparable coverage, readability, and even sometimes developers' preference. Our findings indicate that generating unit tests with ChatGPT could be very promising if the correctness of its generated tests could be further improved. Inspired by our findings above, we propose ChatTESTER, a novel ChatGPT-based unit test generation approach, which leverages ChatGPT itself to improve the quality of its generated tests. ChatTESTER incorporates an initial test generator and an iterative test refiner. Our evaluation demonstrates the effectiveness of ChatTESTER by generating 34.3% more compilable tests and 18.7% more tests with correct assertions than the default ChatGPT.
Recommender systems exploit interaction history to estimate user preference, having been heavily used in a wide range of industry applications. However, static recommendation models are difficult to answer two important questions well due to inherent shortcomings: (a) What exactly does a user like? (b) Why does a user like an item? The shortcomings are due to the way that static models learn user preference, i.e., without explicit instructions and active feedback from users. The recent rise of conversational recommender systems (CRSs) changes this situation fundamentally. In a CRS, users and the system can dynamically communicate through natural language interactions, which provide unprecedented opportunities to explicitly obtain the exact preference of users. Considerable efforts, spread across disparate settings and applications, have been put into developing CRSs. Existing models, technologies, and evaluation methods for CRSs are far from mature. In this paper, we provide a systematic review of the techniques used in current CRSs. We summarize the key challenges of developing CRSs into five directions: (1) Question-based user preference elicitation. (2) Multi-turn conversational recommendation strategies. (3) Dialogue understanding and generation. (4) Exploitation-exploration trade-offs. (5) Evaluation and user simulation. These research directions involve multiple research fields like information retrieval (IR), natural language processing (NLP), and human-computer interaction (HCI). Based on these research directions, we discuss some future challenges and opportunities. We provide a road map for researchers from multiple communities to get started in this area. We hope this survey helps to identify and address challenges in CRSs and inspire future research.
The goal of text ranking is to generate an ordered list of texts retrieved from a corpus in response to a query. Although the most common formulation of text ranking is search, instances of the task can also be found in many natural language processing applications. This survey provides an overview of text ranking with neural network architectures known as transformers, of which BERT is the best-known example. The combination of transformers and self-supervised pretraining has, without exaggeration, revolutionized the fields of natural language processing (NLP), information retrieval (IR), and beyond. In this survey, we provide a synthesis of existing work as a single point of entry for practitioners who wish to gain a better understanding of how to apply transformers to text ranking problems and researchers who wish to pursue work in this area. We cover a wide range of modern techniques, grouped into two high-level categories: transformer models that perform reranking in multi-stage ranking architectures and learned dense representations that attempt to perform ranking directly. There are two themes that pervade our survey: techniques for handling long documents, beyond the typical sentence-by-sentence processing approaches used in NLP, and techniques for addressing the tradeoff between effectiveness (result quality) and efficiency (query latency). Although transformer architectures and pretraining techniques are recent innovations, many aspects of how they are applied to text ranking are relatively well understood and represent mature techniques. However, there remain many open research questions, and thus in addition to laying out the foundations of pretrained transformers for text ranking, this survey also attempts to prognosticate where the field is heading.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191