Computation and Language (cs.CL)

Abstract: Fine-tuning language models on tasks with instructions has demonstrated potential in facilitating zero-shot generalization to unseen tasks. In this paper, we introduce a straightforward yet effective method for enhancing instruction tuning by employing symbolic tasks. Compared to crowdsourced human tasks or model-generated tasks, symbolic tasks present a unique advantage as they can be easily generated in vast quantities, theoretically providing an infinite supply of high-quality training instances. To explore the potential of symbolic tasks, we carry out an extensive case study on the representative symbolic task of SQL execution. Empirical results on various benchmarks validate that the integration of SQL execution leads to significant improvements in zero-shot scenarios, particularly in table reasoning. Notably, our 3B model surpasses both the 175B GPT-3 and ChatGPT in zero-shot table reasoning across four benchmarks. Furthermore, experimental results on BBH (27 tasks) and MMLU (57 tasks) reveal that language models can be enhanced through symbolic tasks without compromising their generality. We hope that our paper serves as a catalyst, inspiring increased efforts to incorporate symbolic tasks in instruction tuning.

Abstract: In this paper, we present our participation to CLEF MC2 2018 edition for the task 2 Mining opinion argumentation. It consists in detecting the most argumentative and diverse Tweets about some festivals in English and French from a massive multilingual collection. We measure argumentativity of a Tweet computing the amount of argumentation compounds it contains. We consider argumentation compounds as a combination between opinion expression and its support with facts and a particular structuration. Regarding diversity, we consider the amount of festival aspects covered by Tweets. An initial step filters the original dataset to fit the language and topic requirements of the task. Then, we compute and integrate linguistic descriptors to detect claims and their respective justifications in Tweets. The final step extracts the most diverse arguments by clustering Tweets according to their textual content and selecting the most argumentative ones from each cluster. We conclude the paper describing the different ways we combined the descriptors among the different runs we submitted and discussing their results.

Abstract: Large language models have unlocked strong multi-task capabilities from reading instructive prompts. However, recent studies have shown that existing large models still have difficulty with information extraction tasks. For example, gpt-3.5-turbo achieved an F1 score of 18.22 on the Ontonotes dataset, which is significantly lower than the state-of-the-art performance. In this paper, we propose InstructUIE, a unified information extraction framework based on instruction tuning, which can uniformly model various information extraction tasks and capture the inter-task dependency. To validate the proposed method, we introduce IE INSTRUCTIONS, a benchmark of 32 diverse information extraction datasets in a unified text-to-text format with expert-written instructions. Experimental results demonstrate that our method achieves comparable performance to Bert in supervised settings and significantly outperforms the state-of-the-art and gpt3.5 in zero-shot settings.

Abstract: Effectively utilizing LLMs for complex tasks is challenging, often involving a time-consuming and uncontrollable prompt engineering process. This paper introduces a novel human-LLM interaction framework, Low-code LLM. It incorporates six types of simple low-code visual programming interactions, all supported by clicking, dragging, or text editing, to achieve more controllable and stable responses. Through visual interaction with a graphical user interface, users can incorporate their ideas into the workflow without writing trivial prompts. The proposed Low-code LLM framework consists of a Planning LLM that designs a structured planning workflow for complex tasks, which can be correspondingly edited and confirmed by users through low-code visual programming operations, and an Executing LLM that generates responses following the user-confirmed workflow. We highlight three advantages of the low-code LLM: controllable generation results, user-friendly human-LLM interaction, and broadly applicable scenarios. We demonstrate its benefits using four typical applications. By introducing this approach, we aim to bridge the gap between humans and LLMs, enabling more effective and efficient utilization of LLMs for complex tasks. Our system will be soon publicly available at LowCodeLLM.

Abstract: Recently, the instruction-tuning of large language models is a crucial area of research in the field of natural language processing. Due to resource and cost limitations, several researchers have employed parameter-efficient tuning techniques, such as LoRA, for instruction tuning, and have obtained encouraging results In comparison to full-parameter fine-tuning, LoRA-based tuning demonstrates salient benefits in terms of training costs. In this study, we undertook experimental comparisons between full-parameter fine-tuning and LoRA-based tuning methods, utilizing LLaMA as the base model. The experimental results show that the selection of the foundational model, training dataset scale, learnable parameter quantity, and model training cost are all important factors. We hope that the experimental conclusions of this paper can provide inspiration for training large language models, especially in the field of Chinese, and help researchers find a better trade-off strategy between training cost and model performance. To facilitate the reproduction of the paper's results, the dataset, model and code will be released.

Abstract: Autoregressive models used to generate responses in open-domain dialogue systems often struggle to take long-term context into account and to maintain consistency over a dialogue. Previous research in open-domain dialogue generation has shown that the use of \emph{auxiliary tasks} can introduce inductive biases that encourage the model to improve these qualities. However, most previous research has focused on encoder-only or encoder/decoder models, while the use of auxiliary tasks in \emph{decoder-only} autoregressive models is under-explored. This paper describes an investigation where four different auxiliary tasks are added to small and medium-sized GPT-2 models fine-tuned on the PersonaChat and DailyDialog datasets. The results show that the introduction of the new auxiliary tasks leads to small but consistent improvement in evaluations of the investigated models.

Abstract: In this paper, we present a transcribed corpus of the LIBE committee of the EU parliament, totalling 3.6 Million running words. The meetings of parliamentary committees of the EU are a potentially valuable source of information for political scientists but the data is not readily available because only disclosed as speech recordings together with limited metadata. The meetings are in English, partly spoken by non-native speakers, and partly spoken by interpreters. We investigated the most appropriate Automatic Speech Recognition (ASR) model to create an accurate text transcription of the audio recordings of the meetings in order to make their content available for research and analysis. We focused on the unsupervised domain adaptation of the ASR pipeline. Building on the transformer-based Wav2vec2.0 model, we experimented with multiple acoustic models, language models and the addition of domain-specific terms. We found that a domain-specific acoustic model and a domain-specific language model give substantial improvements to the ASR output, reducing the word error rate (WER) from 28.22 to 17.95. The use of domain-specific terms in the decoding stage did not have a positive effect on the quality of the ASR in terms of WER. Initial topic modelling results indicated that the corpus is useful for downstream analysis tasks. We release the resulting corpus and our analysis pipeline for future research.

Abstract: Large Language Models (LLMs), such as ChatGPT and GPT-4, have revolutionized natural language processing research and demonstrated potential in Artificial General Intelligence (AGI). However, the expensive training and deployment of LLMs present challenges to transparent and open academic research. To address these issues, this project open-sources the Chinese LLaMA and Alpaca large models, emphasizing instruction fine-tuning. We expand the original LLaMA's Chinese vocabulary by adding 20K Chinese tokens, increasing encoding efficiency and enhancing basic semantic understanding. By incorporating secondary pre-training using Chinese data and fine-tuning with Chinese instruction data, we substantially improve the models' comprehension and execution of instructions. Our pilot study serves as a foundation for researchers adapting LLaMA and Alpaca models to other languages. Resources are made publicly available through GitHub, fostering open research in the Chinese NLP community and beyond. GitHub repository: https://github.com/ymcui/Chinese-LLaMA-Alpaca

Abstract: Recent studies have demonstrated the potential of cross-lingual transferability by training a unified Transformer encoder for multiple languages. In addition to involving the masked language model objective, existing cross-lingual pre-training works leverage sentence-level contrastive learning or plugs in extra cross-attention module to complement the insufficient capabilities of cross-lingual alignment. Nonetheless, synonym pairs residing in bilingual corpus are not exploited and aligned, which is more crucial than sentence interdependence establishment for token-level tasks. In this work, we propose a cross-lingual pre-trained model VECO~2.0 based on contrastive learning with multi-granularity alignments. Specifically, the sequence-to-sequence alignment is induced to maximize the similarity of the parallel pairs and minimize the non-parallel pairs. Then, token-to-token alignment is integrated to bridge the gap between synonymous tokens excavated via the thesaurus dictionary from the other unpaired tokens in a bilingual instance. Experiments show the effectiveness of the proposed strategy for cross-lingual model pre-training on the XTREME benchmark.

Abstract: Emotion Recognition in Conversations (ERC) has been gaining increasing importance as conversational agents become more and more common. Recognizing emotions is key for effective communication, being a crucial component in the development of effective and empathetic conversational agents. Knowledge and understanding of the conversational context are extremely valuable for identifying the emotions of the interlocutor. We thus approach Emotion Recognition in Conversations leveraging the conversational context, i.e., taking into attention previous conversational turns. The usual approach to model the conversational context has been to produce context-independent representations of each utterance and subsequently perform contextual modeling of these. Here we propose context-dependent embedding representations of each utterance by leveraging the contextual representational power of pre-trained transformer language models. In our approach, we feed the conversational context appended to the utterance to be classified as input to the RoBERTa encoder, to which we append a simple classification module, thus discarding the need to deal with context after obtaining the embeddings since these constitute already an efficient representation of such context. We also investigate how the number of introduced conversational turns influences our model performance. The effectiveness of our approach is validated on the widely used open-domain DailyDialog dataset and on the task-oriented EmoWOZ dataset, for which we attain state-of-the-art results, surpassing ERC models also resorting to RoBERTa but with more complex classification modules, indicating that our context-dependent embedding utterance representation approach with a simple classification model can be more effective than context-independent utterance representation approaches with more complex classification modules.

Abstract: Dual use, the intentional, harmful reuse of technology and scientific artefacts, is a problem yet to be well-defined within the context of Natural Language Processing (NLP). However, as NLP technologies continue to advance and become increasingly widespread in society, their inner workings have become increasingly opaque. Therefore, understanding dual use concerns and potential ways of limiting them is critical to minimising the potential harms of research and development. In this paper, we conduct a survey of NLP researchers and practitioners to understand the depth and their perspective of the problem as well as to assess existing available support. Based on the results of our survey, we offer a definition of dual use that is tailored to the needs of the NLP community. The survey revealed that a majority of researchers are concerned about the potential dual use of their research but only take limited action toward it. In light of the survey results, we discuss the current state and potential means for mitigating dual use in NLP and propose a checklist that can be integrated into existing conference ethics-frameworks, e.g., the ACL ethics checklist.

Abstract: Lifelogging has gained more attention due to its wide applications, such as personalized recommendations or memory assistance. The issues of collecting and extracting personal life events have emerged. People often share their life experiences with others through conversations. However, extracting life events from conversations is rarely explored. In this paper, we present Life Event Dialog, a dataset containing fine-grained life event annotations on conversational data. In addition, we initiate a novel conversational life event extraction task and differentiate the task from the public event extraction or the life event extraction from other sources like microblogs. We explore three information extraction (IE) frameworks to address the conversational life event extraction task: OpenIE, relation extraction, and event extraction. A comprehensive empirical analysis of the three baselines is established. The results suggest that the current event extraction model still struggles with extracting life events from human daily conversations. Our proposed life event dialog dataset and in-depth analysis of IE frameworks will facilitate future research on life event extraction from conversations.

Abstract: Twitter is a microblogging service for sending short, public text messages (tweets) that has recently received more attention in scientific comunity. In the works of Sasaki et al. (2010) and Earle et al., (2011) the authors explored the real-time interaction on Twitter for detecting natural hazards (e.g., earthquakes, typhoons) baed on users' tweets. An inherent challenge for such an application is the natural language processing (NLP), which basically consists in converting the words in number (vectors and tensors) in order to (mathematically/ computationally) make predictions and classifications. Recently advanced computational tools have been made available for dealing with text computationally. In this report we implement a NLP machine learning with TensorFlow, an end-to-end open source plataform for machine learning applications, to process and classify evenct based on files containing only text.

Abstract: The usage of mathematical formulas as concise representations of a document's key ideas is common practice. Correctly interpreting these formulas, by identifying mathematical symbols and extracting their descriptions, is an important task in document understanding. This paper makes the following contributions to the mathematical identifier description reading (MIDR) task: (i) introduces the Math Formula Question Answering Dataset (MFQuAD) with $7508$ annotated identifier occurrences; (ii) describes novel variations of the noun phrase ranking approach for the MIDR task; (iii) reports experimental results for the SOTA noun phrase ranking approach and our novel variations of the approach, providing problem insights and a performance baseline; (iv) provides a position on the features that make an effective dataset for the MIDR task.

Abstract: Humans possess an extraordinary ability to create and utilize tools, allowing them to overcome physical limitations and explore new frontiers. With the advent of foundation models, AI systems have the potential to be equally adept in tool use as humans. This paradigm, i.e., tool learning with foundation models, combines the strengths of specialized tools and foundation models to achieve enhanced accuracy, efficiency, and automation in problem-solving. Despite its immense potential, there is still a lack of a comprehensive understanding of key challenges, opportunities, and future endeavors in this field. To this end, we present a systematic investigation of tool learning in this paper. We first introduce the background of tool learning, including its cognitive origins, the paradigm shift of foundation models, and the complementary roles of tools and models. Then we recapitulate existing tool learning research into tool-augmented and tool-oriented learning. We formulate a general tool learning framework: starting from understanding the user instruction, models should learn to decompose a complex task into several subtasks, dynamically adjust their plan through reasoning, and effectively conquer each sub-task by selecting appropriate tools. We also discuss how to train models for improved tool-use capabilities and facilitate the generalization in tool learning. Considering the lack of a systematic tool learning evaluation in prior works, we experiment with 17 representative tools and show the potential of current foundation models in skillfully utilizing tools. Finally, we discuss several open problems that require further investigation for tool learning. Overall, we hope this paper could inspire future research in integrating tools with foundation models.

Abstract: This study introduces novel methods for sentiment and opinion classification of tweets to support the New Product Development (NPD) process. Two popular word embedding techniques, Word2Vec and BERT, were evaluated as inputs for classic Machine Learning and Deep Learning algorithms to identify the best-performing approach in sentiment analysis and opinion detection with limited data. The results revealed that BERT word embeddings combined with Balanced Random Forest yielded the most accurate single model for both sentiment analysis and opinion detection on a use case. Additionally, the paper provides feedback for future product development performing word graph analysis of the tweets with same sentiment to highlight potential areas of improvement.

Abstract: Labeling speech down to the identity and time boundaries of phones is a labor-intensive part of phonetic research. To simplify this work, we created a free open-source tool generating phone sequences from Czech text and time-aligning them with audio. Low architecture complexity makes the design approachable for students of phonetics. Acoustic model ReLU NN with 56k weights was trained using PyTorch on small CommonVoice data. Alignment and variant selection decoder is implemented in Python with matrix library. A Czech pronunciation generator is composed of simple rule-based blocks capturing the logic of the language where possible, allowing modification of transcription approach details. Compared to tools used until now, data preparation efficiency improved, the tool is usable on Mac, Linux and Windows in Praat GUI or command line, achieves mostly correct pronunciation variant choice including glottal stop detection, algorithmically captures most of Czech assimilation logic and is both didactic and practical.

Abstract: The ever-growing diversity of pre-training text corpora has equipped language models with generalization capabilities across various downstream tasks. However, such diverse datasets are often too large for academic budgets; hence, most research on Transformer architectures, training procedures, optimizers, etc. gets conducted on smaller, homogeneous datasets. To this end, we present The MiniPile Challenge, where one pre-trains a language model on a diverse text corpus containing at most 1M documents. MiniPile is a 6GB subset of the deduplicated 825GB The Pile corpus. To curate MiniPile, we perform a simple, three-step data filtering process: we (1) infer embeddings for all documents of the Pile, (2) cluster the embedding space using $k$-means, and (3) filter out low-quality clusters. To verify MiniPile's suitability for language model pre-training, we use it to pre-train a BERT and T5 model, yielding a performance drop of only $1.9\%$/$2.5\%$ on the GLUE and SNI benchmarks compared to the original pre-trained checkpoints trained on $2.6$x/$745$x the amount of data. MiniPile is available at https://huggingface.co/datasets/JeanKaddour/minipile.

Abstract: The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians, and it is typically written by radiologists based on the 'Findings' section. However, writing numerous impressions can be laborious and error-prone for radiologists. Although recent studies have achieved promising results in automatic impression generation using large-scale medical text data for pre-training and fine-tuning pre-trained language models, such models often require substantial amounts of medical text data and have poor generalization performance. While large language models (LLMs) like ChatGPT have shown strong generalization capabilities and performance, their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, which leverages the in-context learning capability of LLMs by constructing dynamic contexts using domain-specific, individualized data. This dynamic prompt approach enables the model to learn contextual knowledge from semantically similar examples from existing data. Additionally, we design an iterative optimization algorithm that performs automatic evaluation on the generated impression results and composes the corresponding instruction prompts to further optimize the model. The proposed ImpressionGPT model achieves state-of-the-art performance on both MIMIC-CXR and OpenI datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains.

Abstract: Various natural language processing (NLP) tasks necessitate models that are efficient and small based on their ultimate application at the edge or in other resource-constrained environments. While prior research has reduced the size of these models, increasing computational efficiency without considerable performance impacts remains difficult, especially for autoregressive tasks. This paper proposes \textit{modular linearized attention (MLA)}, which combines multiple efficient attention mechanisms, including cosFormer \cite{zhen2022cosformer}, to maximize inference quality while achieving notable speedups. We validate this approach on several autoregressive NLP tasks, including speech-to-text neural machine translation (S2T NMT), speech-to-text simultaneous translation (SimulST), and autoregressive text-to-spectrogram, noting efficiency gains on TTS and competitive performance for NMT and SimulST during training and inference.

Abstract: Instruction tuning enables language models to generalize more effectively and better follow user intent. However, obtaining instruction data can be costly and challenging. Prior works employ methods such as expensive human annotation, crowd-sourced datasets with alignment issues, or generating noisy examples via LLMs. We introduce the LongForm dataset, which is created by leveraging English corpus examples with augmented instructions. We select a diverse set of human-written documents from existing corpora such as C4 and Wikipedia and generate instructions for the given documents via LLMs. This approach provides a cheaper and cleaner instruction-tuning dataset and one suitable for long text generation. We finetune T5, OPT, and LLaMA models on our dataset and show that even smaller LongForm models have good generalization capabilities for text generation. Our models outperform 10x larger language models without instruction tuning on various tasks such as story/recipe generation and long-form question answering. Moreover, LongForm models outperform prior instruction-tuned models such as FLAN-T5 and Alpaca by a large margin. Finally, our models can effectively follow and answer multilingual instructions; we demonstrate this for news generation. We publicly release our data and models: https://github.com/akoksal/LongForm.

Abstract: Prompting is now the primary way to utilize the multitask capabilities of language models (LMs), but prompts occupy valuable space in the input context window, and re-encoding the same prompt is computationally inefficient. Finetuning and distillation methods allow for specialization of LMs without prompting, but require retraining the model for each task. To avoid this trade-off entirely, we present gisting, which trains an LM to compress prompts into smaller sets of "gist" tokens which can be reused for compute efficiency. Gist models can be easily trained as part of instruction finetuning via a restricted attention mask that encourages prompt compression. On decoder (LLaMA-7B) and encoder-decoder (FLAN-T5-XXL) LMs, gisting enables up to 26x compression of prompts, resulting in up to 40% FLOPs reductions, 4.2% wall time speedups, storage savings, and minimal loss in output quality.