Abstract:This paper investigates data sampling strategies to create a benchmark for dialectal sentiment classification of Google Places reviews written in English. Based on location-based filtering, we collect a self-supervised dataset of reviews in Australian (Australian English), Indian (Indian English), and British (British English) English with self-supervised sentiment labels (1-star to 5-star). We employ sampling techniques based on label semantics, review length, and sentiment proportion and report performances on three fine-tuned BERT-based models. Our multi-dialect evaluation provides pointers to challenging scenarios for inner-circle (Australian English and British English) as well as non-native dialects (Indian English) of English, highlighting the need for more diverse benchmarks.
Abstract:This paper explores the challenges of detecting LGBTQIA+ hate speech of large language models across multiple languages, including English, Italian, Chinese and (code-switched) English-Tamil, examining the impact of machine translation and whether the nuances of hate speech are preserved across translation. We examine the hate speech detection ability of zero-shot and fine-tuned GPT. Our findings indicate that: (1) English has the highest performance and the code-switching scenario of English-Tamil being the lowest, (2) fine-tuning improves performance consistently across languages whilst translation yields mixed results. Through simple experimentation with original text and machine-translated text for hate speech detection along with a qualitative error analysis, this paper sheds light on the socio-cultural nuances and complexities of languages that may not be captured by automatic translation.
Abstract:Dialect adapters that improve the performance of LLMs for NLU tasks on certain sociolects/dialects/national varieties ('dialects' for the sake of brevity) have been reported for encoder models. In this paper, we extend the idea of dialect adapters to decoder models in our architecture called LoRDD. Using MD-3, a publicly available dataset of word game-playing conversations between dialectal speakers, our task is Target Word Prediction (TWP) from a masked conversation. LoRDD combines task adapters and dialect adapters where the latter employ contrastive learning on pseudo-parallel conversations from MD-3. Our results for en-IN conversations on two models (Mistral and Gemma) show that LoRDD outperforms four baselines on TWP, while bridging the performance gap with en-US by 12% on word similarity and 25% on accuracy. The focused contribution of LoRDD is in its promise for dialect adaptation of decoder models.
Abstract:In the age of information overload, professionals across various fields face the challenge of navigating vast amounts of documentation and ever-evolving standards. Ensuring compliance with standards, regulations, and contractual obligations is a critical yet complex task across various professional fields. We propose a versatile conversational AI assistant framework designed to facilitate compliance checking on the go, in diverse domains, including but not limited to network infrastructure, legal contracts, educational standards, environmental regulations, and government policies. By leveraging retrieval-augmented generation using large language models, our framework automates the review, indexing, and retrieval of relevant, context-aware information, streamlining the process of verifying adherence to established guidelines and requirements. This AI assistant not only reduces the manual effort involved in compliance checks but also enhances accuracy and efficiency, supporting professionals in maintaining high standards of practice and ensuring regulatory compliance in their respective fields. We propose and demonstrate AuditNet, the first conversational AI security assistant designed to assist IoT network security experts by providing instant access to security standards, policies, and regulations.
Abstract:Children from bilingual backgrounds benefit from interactions with parents and teachers to re-acquire their heritage language. In this paper, we investigate how this insight from behavioral study can be incorporated into the learning of small-scale language models. We introduce BAMBINO-LM, a continual pretraining strategy for BabyLM that uses a novel combination of alternation and PPO-based perplexity reward induced from a parent Italian model. Upon evaluation on zero-shot classification tasks for English and Italian, BAMBINO-LM improves the Italian language capability of a BabyLM baseline. Our ablation analysis demonstrates that employing both the alternation strategy and PPO-based modeling is key to this effectiveness gain. We also show that, as a side effect, the proposed method leads to similar degradation in L1 effectiveness as human children would have had in an equivalent learning scenario.
Abstract:Linearization of attention using various kernel approximation and kernel learning techniques has shown promise. Past methods use a subset of combinations of component functions and weight matrices within the random features paradigm. We identify the need for a systematic comparison of different combinations of weight matrix and component functions for attention learning in Transformer. In this work, we introduce Spectraformer, a unified framework for approximating and learning the kernel function in linearized attention of the Transformer. We experiment with broad classes of component functions and weight matrices for three textual tasks in the LRA benchmark. Our experimentation with multiple combinations of component functions and weight matrices leads us to a novel combination with 23.4% faster training time and 25.2% lower memory consumption over the previous SOTA random feature Transformer, while maintaining the performance, as compared to the Original Transformer. Our code is available at: https://github.com/dukeraphaelng/spectraformer .
Abstract:While neural approaches using deep learning are the state-of-the-art for natural language processing (NLP) today, pre-neural algorithms and approaches still find a place in NLP textbooks and courses of recent years. In this paper, we compare two introductory NLP courses taught in Australia and India, and examine how Transformer and pre-neural approaches are balanced within the lecture plan and assessments of the courses. We also draw parallels with the objects-first and objects-later debate in CS1 education. We observe that pre-neural approaches add value to student learning by building an intuitive understanding of NLP problems, potential solutions and even Transformer-based models themselves. Despite pre-neural approaches not being state-of-the-art, the paper makes a case for their inclusion in NLP courses today.
Abstract:With an evergrowing number of LLMs reporting superlative performance for English, their ability to perform equitably for different dialects of English (i.e., dialect robustness) needs to be ascertained. Specifically, we use English language (US English or Indian English) conversations between humans who play the word-guessing game of `taboo'. We formulate two evaluative tasks: target word prediction (TWP) (i.e.predict the masked target word in a conversation) and target word selection (TWS) (i.e., select the most likely masked target word in a conversation, from among a set of candidate words). Extending MD3, an existing dialectic dataset of taboo-playing conversations, we introduce M-MD3, a target-word-masked version of MD3 with the USEng and IndEng subsets. We add two subsets: AITrans (where dialectic information is removed from IndEng) and AIGen (where LLMs are prompted to generate conversations). Our evaluation uses pre-trained and fine-tuned versions of two closed-source (GPT-4/3.5) and two open-source LLMs (Mistral and Gemma). LLMs perform significantly better for US English than Indian English for both TWP and TWS, for all settings. While GPT-based models perform the best, the comparatively smaller models work more equitably for short conversations (<8 turns). Our results on AIGen and AITrans (the best and worst-performing subset) respectively show that LLMs may learn a dialect of their own based on the composition of the training data, and that dialect robustness is indeed a challenging task. Our evaluation methodology exhibits a novel way to examine attributes of language models using pre-existing dialogue datasets.
Abstract:State-of-the-art natural language processing (NLP) models are trained on massive training corpora, and report a superlative performance on evaluation datasets. This survey delves into an important attribute of these datasets: the dialect of a language. Motivated by the performance degradation of NLP models for dialectic datasets and its implications for the equity of language technologies, we survey past research in NLP for dialects in terms of datasets, and approaches. We describe a wide range of NLP tasks in terms of two categories: natural language understanding (NLU) (for tasks such as dialect classification, sentiment analysis, parsing, and NLU benchmarks) and natural language generation (NLG) (for summarisation, machine translation, and dialogue systems). The survey is also broad in its coverage of languages which include English, Arabic, German among others. We observe that past work in NLP concerning dialects goes deeper than mere dialect classification, and . This includes early approaches that used sentence transduction that lead to the recent approaches that integrate hypernetworks into LoRA. We expect that this survey will be useful to NLP researchers interested in building equitable language technologies by rethinking LLM benchmarks and model architectures.
Abstract:This paper reports the findings of the ICON 2023 on Gendered Abuse Detection in Indic Languages. The shared task deals with the detection of gendered abuse in online text. The shared task was conducted as a part of ICON 2023, based on a novel dataset in Hindi, Tamil and the Indian dialect of English. The participants were given three subtasks with the train dataset consisting of approximately 6500 posts sourced from Twitter. For the test set, approximately 1200 posts were provided. The shared task received a total of 9 registrations. The best F-1 scores are 0.616 for subtask 1, 0.572 for subtask 2 and, 0.616 and 0.582 for subtask 3. The paper contains examples of hateful content owing to its topic.