Computation and Language (cs.CL)

Abstract: Intent detection and slot filling are critical tasks in spoken and natural language understanding for task-oriented dialog systems. In this work we describe our participation in the slot and intent detection for low-resource language varieties (SID4LR; Aepli et al. (2023)). We investigate the slot and intent detection (SID) tasks using a wide range of models and settings. Given the recent success of multitask-prompted finetuning of large language models, we also test the generalization capability of the recent encoder-decoder model mT0 (Muennighoff et al., 2022) on new tasks (i.e., SID) in languages they have never intentionally seen. We show that our best model outperforms the baseline by a large margin (up to +30 F1 points) in both SID tasks

Abstract: Recent advancements in Large Language Models (LLMs), such as Codex, ChatGPT and GPT-4 have significantly impacted the AI community, including Text-to-SQL tasks. Some evaluations and analyses on LLMs show their potential to generate SQL queries but they point out poorly designed prompts (e.g. simplistic construction or random sampling) limit LLMs' performance and may cause unnecessary or irrelevant outputs. To address these issues, we propose CBR-ApSQL, a Case-Based Reasoning (CBR)-based framework combined with GPT-3.5 for precise control over case-relevant and case-irrelevant knowledge in Text-to-SQL tasks. We design adaptive prompts for flexibly adjusting inputs for GPT-3.5, which involves (1) adaptively retrieving cases according to the question intention by de-semantizing the input question, and (2) an adaptive fallback mechanism to ensure the informativeness of the prompt, as well as the relevance between cases and the prompt. In the de-semanticization phase, we designed Semantic Domain Relevance Evaluator(SDRE), combined with Poincar\'e detector(mining implicit semantics in hyperbolic space), TextAlign(discovering explicit matches), and Positector (part-of-speech detector). SDRE semantically and syntactically generates in-context exemplar annotations for the new case. On the three cross-domain datasets, our framework outperforms the state-of-the-art(SOTA) model in execution accuracy by 3.7\%, 2.5\%, and 8.2\%, respectively.

Abstract: We propose a novel topological perspective on data languages recognizable by orbit-finite nominal monoids. For this purpose, we introduce pro-orbit-finite nominal topological spaces. Assuming globally bounded support sizes, they coincide with nominal Stone spaces and are shown to be dually equivalent to a subcategory of nominal boolean algebras. Recognizable data languages are characterized as topologically clopen sets of pro-orbit-finite words. In addition, we explore the expressive power of pro-orbit-finite equations by establishing a nominal version of Reiterman's pseudovariety theorem.

Abstract: Large-scale Language Models (LLMs) are constrained by their inability to process lengthy inputs. To address this limitation, we propose the Self-Controlled Memory (SCM) system to unleash infinite-length input capacity for large-scale language models. Our SCM system is composed of three key modules: the language model agent, the memory stream, and the memory controller. The language model agent iteratively processes ultra-long inputs and stores all historical information in the memory stream. The memory controller provides the agent with both long-term memory (archived memory) and short-term memory (flash memory) to generate precise and coherent responses. The controller determines which memories from archived memory should be activated and how to incorporate them into the model input. Our SCM system can be integrated with any LLMs to enable them to process ultra-long texts without any modification or fine-tuning. Experimental results show that our SCM system enables LLMs, which are not optimized for multi-turn dialogue, to achieve multi-turn dialogue capabilities that are comparable to ChatGPT, and to outperform ChatGPT in scenarios involving ultra-long document summarization or long-term conversations. Additionally, we will supply a test set, which covers common long-text input scenarios, for evaluating the abilities of LLMs in processing long documents.~\footnote{Working in progress.}\footnote{\url{https://github.com/wbbeyourself/SCM4LLMs}}

Abstract: We investigate the potential of ChatGPT as a multidimensional evaluator for the task of \emph{Text Style Transfer}, alongside, and in comparison to, existing automatic metrics as well as human judgements. We focus on a zero-shot setting, i.e. prompting ChatGPT with specific task instructions, and test its performance on three commonly-used dimensions of text style transfer evaluation: style strength, content preservation, and fluency. We perform a comprehensive correlation analysis for two transfer directions (and overall) at different levels. Compared to existing automatic metrics, ChatGPT achieves competitive correlations with human judgments. These preliminary results are expected to provide a first glimpse into the role of large language models in the multidimensional evaluation of stylized text generation.

Abstract: Language Models (LMs) have shown state-of-the-art performance in Natural Language Processing (NLP) tasks. Downstream tasks such as Named Entity Recognition (NER) or Part-of-Speech (POS) tagging are known to suffer from data imbalance issues, specifically in terms of the ratio of positive to negative examples, and class imbalance. In this paper, we investigate an additional specific issue for language models, namely the position bias of positive examples in token classification tasks. Therefore, we conduct an in-depth evaluation of the impact of position bias on the performance of LMs when fine-tuned on Token Classification benchmarks. Our study includes CoNLL03 and OntoNote5.0 for NER, English Tree Bank UD_en and TweeBank for POS tagging. We propose an evaluation approach to investigate position bias in Transformer models. We show that encoders like BERT, ERNIE, ELECTRA, and decoders such as GPT2 and BLOOM can suffer from this bias with an average drop of 3\% and 9\% in their performance. To mitigate this effect, we propose two methods: Random Position Shifting and Context Perturbation, that we apply on batches during the training process. The results show an improvement of $\approx$ 2\% in the performance of the model on CoNLL03, UD_en, and TweeBank.

Abstract: Lexical ambiguity presents a profound and enduring challenge to the language sciences. Researchers for decades have grappled with the problem of how language users learn, represent and process words with more than one meaning. Our work offers new insight into psychological understanding of lexical ambiguity through a series of simulations that capitalise on recent advances in contextual language models. These models have no grounded understanding of the meanings of words at all; they simply learn to predict words based on the surrounding context provided by other words. Yet, our analyses show that their representations capture fine-grained meaningful distinctions between unambiguous, homonymous, and polysemous words that align with lexicographic classifications and psychological theorising. These findings provide quantitative support for modern psychological conceptualisations of lexical ambiguity and raise new challenges for understanding of the way that contextual information shapes the meanings of words across different timescales.

Abstract: Automatic chart to text summarization is an effective tool for the visually impaired people along with providing precise insights of tabular data in natural language to the user. A large and well-structured dataset is always a key part for data driven models. In this paper, we propose ChartSumm: a large-scale benchmark dataset consisting of a total of 84,363 charts along with their metadata and descriptions covering a wide range of topics and chart types to generate short and long summaries. Extensive experiments with strong baseline models show that even though these models generate fluent and informative summaries by achieving decent scores in various automatic evaluation metrics, they often face issues like suffering from hallucination, missing out important data points, in addition to incorrect explanation of complex trends in the charts. We also investigated the potential of expanding ChartSumm to other languages using automated translation tools. These make our dataset a challenging benchmark for future research.

Abstract: We present the findings of SemEval-2023 Task 12, a shared task on sentiment analysis for low-resource African languages using Twitter dataset. The task featured three subtasks; subtask A is monolingual sentiment classification with 12 tracks which are all monolingual languages, subtask B is multilingual sentiment classification using the tracks in subtask A and subtask C is a zero-shot sentiment classification. We present the results and findings of subtask A, subtask B and subtask C. We also release the code on github. Our goal is to leverage low-resource tweet data using pre-trained Afro-xlmr-large, AfriBERTa-Large, Bert-base-arabic-camelbert-da-sentiment (Arabic-camelbert), Multilingual-BERT (mBERT) and BERT models for sentiment analysis of 14 African languages. The datasets for these subtasks consists of a gold standard multi-class labeled Twitter datasets from these languages. Our results demonstrate that Afro-xlmr-large model performed better compared to the other models in most of the languages datasets. Similarly, Nigerian languages: Hausa, Igbo, and Yoruba achieved better performance compared to other languages and this can be attributed to the higher volume of data present in the languages.

Abstract: Question Generation (QG) is a task of Natural Language Processing (NLP) that aims at automatically generating questions from text. Many applications can benefit from automatically generated questions, but often it is necessary to curate those questions, either by selecting or editing them. This task is informative on its own, but it is typically done post-generation, and, thus, the effort is wasted. In addition, most existing systems cannot incorporate this feedback back into them easily. In this work, we present a system, GEN, that learns from such (implicit) feedback. Following a pattern-based approach, it takes as input a small set of sentence/question pairs and creates patterns which are then applied to new unseen sentences. Each generated question, after being corrected by the user, is used as a new seed in the next iteration, so more patterns are created each time. We also take advantage of the corrections made by the user to score the patterns and therefore rank the generated questions. Results show that GEN is able to improve by learning from both levels of implicit feedback when compared to the version with no learning, considering the top 5, 10, and 20 questions. Improvements go up from 10%, depending on the metric and strategy used.

Abstract: Human-spoken questions are critical to evaluating the performance of spoken question answering (SQA) systems that serve several real-world use cases including digital assistants. We present a new large-scale community-shared SQA dataset, HeySQuAD that consists of 76k human-spoken questions and 97k machine-generated questions and corresponding textual answers derived from the SQuAD QA dataset. The goal of HeySQuAD is to measure the ability of machines to understand noisy spoken questions and answer the questions accurately. To this end, we run extensive benchmarks on the human-spoken and machine-generated questions to quantify the differences in noise from both sources and its subsequent impact on the model and answering accuracy. Importantly, for the task of SQA, where we want to answer human-spoken questions, we observe that training using the transcribed human-spoken and original SQuAD questions leads to significant improvements (12.51%) over training using only the original SQuAD textual questions.

Abstract: This paper presents a comprehensive and practical guide for practitioners and end-users working with Large Language Models (LLMs) in their downstream natural language processing (NLP) tasks. We provide discussions and insights into the usage of LLMs from the perspectives of models, data, and downstream tasks. Firstly, we offer an introduction and brief summary of current GPT- and BERT-style LLMs. Then, we discuss the influence of pre-training data, training data, and test data. Most importantly, we provide a detailed discussion about the use and non-use cases of large language models for various natural language processing tasks, such as knowledge-intensive tasks, traditional natural language understanding tasks, natural language generation tasks, emergent abilities, and considerations for specific tasks.We present various use cases and non-use cases to illustrate the practical applications and limitations of LLMs in real-world scenarios. We also try to understand the importance of data and the specific challenges associated with each NLP task. Furthermore, we explore the impact of spurious biases on LLMs and delve into other essential considerations, such as efficiency, cost, and latency, to ensure a comprehensive understanding of deploying LLMs in practice. This comprehensive guide aims to provide researchers and practitioners with valuable insights and best practices for working with LLMs, thereby enabling the successful implementation of these models in a wide range of NLP tasks. A curated list of practical guide resources of LLMs, regularly updated, can be found at \url{https://github.com/Mooler0410/LLMsPracticalGuide}.